@agentjido/llmdb 2026.8.2

package/dist/providers/kilo.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.kilo.ai/api/gateway","catalog_only":true,"config_schema":null,"doc":"https://kilo.ai","env":["KILO_API_KEY"],"exclude_models":null,"extra":null,"id":"kilo","models":{"ai21/jamba-large-1.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"jamba","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"ai21/jamba-large-1.7","knowledge":null,"last_updated":"2025-08-08","lifecycle":null,"limits":{"context":256000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AI21: Jamba Large 1.7","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-08","retired":false,"tags":null},"aion-labs/aion-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.8,"output":1.6},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"aion-labs/aion-2.0","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-2.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"aion-labs/aion-3.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.75,"input":3,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"aion-labs/aion-3.0","knowledge":null,"last_updated":"2026-07-07","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-3.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"aion-labs/aion-3.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.18,"input":0.7,"output":1.4},"deprecated":false,"extra":{"attachment":false,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"aion-labs/aion-3.0-mini","knowledge":null,"last_updated":"2026-07-07","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-3.0-Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"aion-labs/aion-rp-llama-3.1-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.8,"output":1.6},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"aion-labs/aion-rp-llama-3.1-8b","knowledge":null,"last_updated":"2025-02-04","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-RP 1.0 (8B)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-02-04","retired":false,"tags":null},"allenai/olmo-3-32b-think":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.15,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"allenai","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"allenai/olmo-3-32b-think","knowledge":null,"last_updated":"2025-11-21","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AllenAI: Olmo 3 32B Think","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-21","retired":false,"tags":null},"amazon/nova-2-lite-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/nova-2-lite-v1","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"model":null,"name":"Amazon: Nova 2 Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"amazon/nova-lite-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"amazon/nova-lite-v1","knowledge":null,"last_updated":"2024-12-05","lifecycle":null,"limits":{"context":300000,"output":5120},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Lite 1.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"amazon/nova-micro-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.035,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"amazon/nova-micro-v1","knowledge":null,"last_updated":"2024-12-05","lifecycle":null,"limits":{"context":128000,"output":5120},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Amazon: Nova Micro 1.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"amazon/nova-premier-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.625,"input":2.5,"output":12.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"amazon/nova-premier-v1","knowledge":null,"last_updated":"2025-10-31","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Premier 1.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-31","retired":false,"tags":null},"amazon/nova-pro-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.8,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"amazon/nova-pro-v1","knowledge":null,"last_updated":"2024-12-05","lifecycle":null,"limits":{"context":300000,"output":5120},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Pro 1.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"anthracite-org/magnum-v4-72b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"anthracite-org/magnum-v4-72b","knowledge":null,"last_updated":"2024-10-22","lifecycle":null,"limits":{"context":16384,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magnum v4 72B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"anthropic/claude-3-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"anthropic/claude-3-haiku","knowledge":null,"last_updated":"2024-03-13","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3 Haiku","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"anthropic/claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic/claude-haiku-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-haiku-4.5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5 (latest)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic/claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"anthropic/claude-opus-4","knowledge":null,"last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4 ($$$$)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-opus-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1 (latest)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.5","knowledge":"2025-05","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5 (latest)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic/claude-opus-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"anthropic/claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-opus-4.7-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":3,"cache_write":37.5,"input":30,"output":150},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.7-fast","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-opus-4.8-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.8-fast","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-opus-5-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-5-fast","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":null,"last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"anthropic/claude-sonnet-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic/claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"arcee-ai/trinity-large-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.22,"output":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"trinity","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"arcee-ai/trinity-large-thinking","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Arcee AI: Trinity Large Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"arcee-ai/virtuoso-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.75,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"arcee-ai/virtuoso-large","knowledge":null,"last_updated":"2025-05-05","lifecycle":null,"limits":{"context":131072,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Arcee AI: Virtuoso Large","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-05","retired":false,"tags":null},"baidu/ernie-4.5-vl-424b-a47b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.42,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-424b-a47b","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":123000,"output":16000},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Baidu: ERNIE 4.5 VL 424B A47B ","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"bytedance-seed/seed-1.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"bytedance-seed/seed-1.6","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed 1.6","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"bytedance-seed/seed-1.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"bytedance-seed/seed-1.6-flash","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed 1.6 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"bytedance-seed/seed-2.0-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"bytedance-seed/seed-2.0-lite","knowledge":null,"last_updated":"2026-03-10","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed-2.0-Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"bytedance-seed/seed-2.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"bytedance-seed/seed-2.0-mini","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed-2.0-Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"bytedance/ui-tars-1.5-7b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.1,"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"bytedance/ui-tars-1.5-7b","knowledge":null,"last_updated":"2025-07-22","lifecycle":null,"limits":{"context":128000,"output":2048},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"ByteDance: UI-TARS 7B ","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"cognitivecomputations/dolphin-mistral-24b-venice-edition":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","family":"mistral","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Venice: Uncensored","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"cohere/command-a":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-a","knowledge":null,"last_updated":"2025-03-13","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: Command A","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere/command-r-08-2024":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r-plus-08-2024":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r-plus-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R+","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r7b-12-2024":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0375,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r7b-12-2024","knowledge":"2024-06-01","last_updated":"2024-12-02","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R7B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-02","retired":false,"tags":null},"cohere/north-mini-code:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","family":"north","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"cohere/north-mini-code:free","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: North Mini Code (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"deepcogito/cogito-v2.1-671b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1.25,"output":1.25},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"cogito","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepcogito/cogito-v2.1-671b","knowledge":null,"last_updated":"2025-11-13","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deep Cogito: Cogito v2.1 671B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"deepseek/deepseek-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-chat","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":128000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Chat","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-chat-v3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.27,"output":1.12},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-chat-v3-0324","knowledge":null,"last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3 0324","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-24","retired":false,"tags":null},"deepseek/deepseek-chat-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-chat-v3.1","knowledge":null,"last_updated":"2025-08-21","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek/deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":64000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek/deepseek-r1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.35,"input":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-0528","knowledge":null,"last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: R1 0528","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek/deepseek-r1-distill-llama-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.8,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-distill-llama-70b","knowledge":null,"last_updated":"2025-01-23","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: R1 Distill Llama 70B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-23","retired":false,"tags":null},"deepseek/deepseek-v3.1-terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1-terminus","knowledge":null,"last_updated":"2025-09-22","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.1 Terminus","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"deepseek/deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1345,"input":0.269,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2","knowledge":null,"last_updated":"2025-12-01","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v3.2-exp":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.41},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2-exp","knowledge":null,"last_updated":"2025-09-29","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.2 Exp","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek/deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek/deepseek-v4-flash:discounted":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28,"reasoning":0},"deprecated":false,"extra":{"attachment":false,"description":"This DeepSeek V4 Flash endpoint provides the lowest cost for multi-turn conversations for this model. This is accomplished with an exceptionally low cache read price. By using this endpoint you agree prompts and completions may be retained by DeepSeek and used to train future models.","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash:discounted","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V4 Flash (lowest price)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":1.6,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v4-pro:discounted":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.003625,"input":0.435,"output":0.87,"reasoning":0},"deprecated":false,"extra":{"attachment":false,"description":"This DeepSeek V4 Pro endpoint provides the lowest cost for multi-turn conversations for this model. This is accomplished with an exceptionally low cache read price. By using this endpoint you agree prompts and completions may be retained by DeepSeek and used to train future models.","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro:discounted","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V4 Pro (lowest price)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"google/gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["image","text","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"google/gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"cache_write":0.083333,"input":0.1,"output":0.4,"reasoning":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"cache_write":0.375,"input":1.25,"output":10,"reasoning":10},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"cache_write":0.375,"input":1.25,"output":10,"reasoning":10},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","open_weights":false,"reasoning_options":[{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-pro-preview","knowledge":null,"last_updated":"2025-06-05","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Pro Preview 06-05","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-05","retired":false,"tags":null},"google/gemini-2.5-pro-preview-05-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"cache_write":0.375,"input":1.25,"output":10,"reasoning":10},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","open_weights":false,"reasoning_options":[{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-pro-preview-05-06","knowledge":null,"last_updated":"2025-05-07","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Pro Preview 05-06","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"google/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.083333,"input":0.5,"output":3,"reasoning":3},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"google/gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["image","text","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"google/gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["image","text","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"google/gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["image","text","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"google/gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"google/gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.083333,"input":0.25,"output":1.5,"reasoning":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"google/gemini-3.1-flash-lite-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-image","knowledge":"2025-01","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["image","text","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2 Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"google/gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.083333,"input":0.25,"output":1.5,"reasoning":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview Custom Tools","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"output":9,"reasoning":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"output":7.5,"reasoning":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemma-2-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.65,"output":0.65},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma2","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/gemma-2-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-2-27b-it-GGUF"}],"hf_downloads":118485,"hf_likes":568,"matched_hugging_face_id":"google/gemma-2-27b-it","memory":{"min_ram_gb":15.2,"min_vram_gb":13.9,"recommended_ram_gb":25.4},"model_id":"google/gemma-2-27b-it","parameter_count":"27.2B","parameters_raw":27227128320,"pipeline_tag":"text-generation","provider":"Google","quantization":"Q4_K_M","release_date":"2024-06-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-2-27b-it","knowledge":null,"last_updated":"2024-07-13","lifecycle":null,"limits":{"context":8192,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Google: Gemma 2 27B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-13","retired":false,"tags":null},"google/gemma-3-12b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-12b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-12b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-12b-it-GGUF"}],"hf_downloads":1281955,"hf_likes":797,"matched_hugging_face_id":"google/gemma-3-12b-it","memory":{"min_ram_gb":6.8,"min_vram_gb":6.2,"recommended_ram_gb":11.4},"model_id":"google/gemma-3-12b-it","parameter_count":"12.2B","parameters_raw":12187325040,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3-12b-it","knowledge":null,"last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 12B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"google/gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.16},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-27b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-27b-it-GGUF"}],"hf_downloads":847078,"hf_likes":2005,"matched_hugging_face_id":"google/gemma-3-27b-it","memory":{"min_ram_gb":15.3,"min_vram_gb":14.1,"recommended_ram_gb":25.5},"model_id":"google/gemma-3-27b-it","parameter_count":"27.4B","parameters_raw":27432406640,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3-27b-it","knowledge":null,"last_updated":"2025-03-12","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 27B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"google/gemma-3-4b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.05,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-4b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-4b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-4b-it-GGUF"}],"hf_downloads":1869741,"hf_likes":1441,"matched_hugging_face_id":"google/gemma-3-4b-it","memory":{"min_ram_gb":2.4,"min_vram_gb":2.2,"recommended_ram_gb":4.0},"model_id":"google/gemma-3-4b-it","parameter_count":"4.3B","parameters_raw":4300079472,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-02-20","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3-4b-it","knowledge":null,"last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 4B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"google/gemma-3n-e4b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.06,"output":0.12},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3n-e4b-it","knowledge":null,"last_updated":"2025-05-20","lifecycle":null,"limits":{"context":32768,"output":6554},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Google: Gemma 3n 4B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.09,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/lyria-3-clip-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"google/lyria-3-clip-preview","knowledge":null,"last_updated":"2026-03-25","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"model":null,"name":"Lyria 3 Clip Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-25","retired":false,"tags":null},"google/lyria-3-pro-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"google/lyria-3-pro-preview","knowledge":null,"last_updated":"2026-03-25","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"model":null,"name":"Lyria 3 Pro Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-25","retired":false,"tags":null},"gryphe/mythomax-l2-13b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.06,"output":0.06},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gryphe/mythomax-l2-13b","knowledge":null,"last_updated":"2023-07-02","lifecycle":null,"limits":{"context":4096,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MythoMax 13B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-07-02","retired":false,"tags":null},"ibm-granite/granite-4.0-h-micro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.017,"output":0.112},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","llmfit":{"architecture":"granitemoehybrid","context_length":131072,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/granite-4.0-h-micro-GGUF"},{"provider":"mradermacher","repo":"mradermacher/granite-4.0-h-micro-GGUF"}],"hf_downloads":24846,"hf_likes":148,"matched_hugging_face_id":"ibm-granite/granite-4.0-h-micro","memory":{"min_ram_gb":1.8,"min_vram_gb":1.6,"recommended_ram_gb":3.0},"model_id":"ibm-granite/granite-4.0-h-micro","parameter_count":"3.2B","parameters_raw":3191396096,"pipeline_tag":"text-generation","provider":"ibm-granite","quantization":"Q4_K_M","release_date":"2025-09-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"ibm-granite/granite-4.0-h-micro","knowledge":null,"last_updated":"2025-10-20","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IBM: Granite 4.0 Micro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-20","retired":false,"tags":null},"ibm-granite/granite-4.1-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.05,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"granite","llmfit":{"architecture":"granite","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/granite-4.1-8b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/granite-4.1-8b-GGUF"}],"hf_downloads":4085575,"hf_likes":243,"matched_hugging_face_id":"ibm-granite/granite-4.1-8b","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"ibm-granite/granite-4.1-8b","parameter_count":"8.8B","parameters_raw":8791592960,"pipeline_tag":"text-generation","provider":"ibm-granite","quantization":"Q4_K_M","release_date":"2026-04-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"ibm-granite/granite-4.1-8b","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IBM: Granite 4.1 8B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"inception/mercury-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"inception/mercury-2","knowledge":null,"last_updated":"2026-03-04","lifecycle":null,"limits":{"context":128000,"output":50000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Inception: Mercury 2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-04","retired":false,"tags":null},"inclusionai/ling-2.6-1t":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ling","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-1t","knowledge":null,"last_updated":"2026-04-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ling-2.6-1T","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"inclusionai/ling-2.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-flash","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ling-2.6-flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"inclusionai/ling-3.0-flash:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","family":"ling","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"inclusionai/ling-3.0-flash:free","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling-3.0-flash (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"inclusionai/ring-2.6-1t":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"inclusionai/ring-2.6-1t","knowledge":null,"last_updated":"2026-05-08","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ring-2.6-1T","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-08","retired":false,"tags":null},"kilo-auto/balanced":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0325,"cache_write":0.40625,"input":0.325,"output":1.95,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"kilo-auto/balanced","knowledge":null,"last_updated":"1970-01-01","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Auto Balanced","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"1970-01-01","retired":false,"tags":null},"kilo-auto/efficient":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0325,"cache_write":0.40625,"input":0.325,"output":1.95,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","family":"auto","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"kilo-auto/efficient","knowledge":null,"last_updated":"1970-01-01","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Auto Efficient","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"1970-01-01","retired":false,"tags":null},"kilo-auto/free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0,"cache_write":0,"input":0,"output":0,"reasoning":0},"deprecated":false,"extra":{"attachment":false,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"kilo-auto/free","knowledge":null,"last_updated":"1970-01-01","lifecycle":null,"limits":{"context":256000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Auto Free","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"1970-01-01","retired":false,"tags":null},"kilo-auto/frontier":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"kilo-auto/frontier","knowledge":null,"last_updated":"1970-01-01","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Auto Frontier","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"1970-01-01","retired":false,"tags":null},"kilo-auto/small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"kilo-auto/small","knowledge":null,"last_updated":"1970-01-01","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Auto Small","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"1970-01-01","retired":false,"tags":null},"kwaipilot/kat-coder-air-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","family":"kat-coder","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-air-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Air V2.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2","knowledge":null,"last_updated":"2026-03-27","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Pro V2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.74,"output":2.96},"deprecated":false,"extra":{"attachment":false,"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","family":"kat-coder","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Pro V2.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"mancer/weaver":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"alpha","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mancer/weaver","knowledge":null,"last_updated":"2023-08-02","lifecycle":null,"limits":{"context":8000,"output":2000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mancer: Weaver (alpha)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-08-02","retired":false,"tags":null},"meituan/longcat-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.75,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","family":"longcat","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"meituan/longcat-2.0","knowledge":null,"last_updated":"2026-07-20","lifecycle":null,"limits":{"context":1048756,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meituan: LongCat 2.0","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"meta-llama/llama-3.1-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-3.1-70b-instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.1 70B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.04},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-3.1-8b-instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.1 8B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/llama-3.2-1b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.027,"output":0.201},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"meta-llama/llama-3.2-1b-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":60000,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.2 1B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"meta-llama/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.05,"output":0.33},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-3.2-3b-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.2 3B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"meta-llama/llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.32},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/llama-4-maverick":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.696},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-4-maverick","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta: Llama 4 Maverick","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/llama-4-scout":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-4-scout","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":327680,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta: Llama 4 Scout","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/llama-guard-4-12b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.18,"output":0.18},"deprecated":false,"extra":{"attachment":true,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"meta-llama/llama-guard-4-12b","knowledge":null,"last_updated":"2025-04-30","lifecycle":null,"limits":{"context":163840,"output":16384},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Meta: Llama Guard 4 12B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"meta/muse-spark-1.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","family":"muse","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"meta/muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"microsoft/phi-4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.07,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","llmfit":{"architecture":"phi3","context_length":16384,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/phi-4-GGUF"},{"provider":"bartowski","repo":"bartowski/phi-4-GGUF"},{"provider":"mradermacher","repo":"mradermacher/phi-4-GGUF"}],"hf_downloads":664421,"hf_likes":2285,"matched_hugging_face_id":"microsoft/phi-4","memory":{"min_ram_gb":8.2,"min_vram_gb":7.5,"recommended_ram_gb":13.7},"model_id":"microsoft/phi-4","parameter_count":"14.7B","parameters_raw":14659507200,"pipeline_tag":"text-generation","provider":"Microsoft","quantization":"Q4_K_M","release_date":"2024-12-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"microsoft/phi-4","knowledge":null,"last_updated":"2025-01-10","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Microsoft: Phi 4","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-10","retired":false,"tags":null},"microsoft/wizardlm-2-8x22b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.62,"output":0.62},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"microsoft/wizardlm-2-8x22b","knowledge":null,"last_updated":"2024-04-16","lifecycle":null,"limits":{"context":65535,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"WizardLM-2 8x22B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-04-16","retired":false,"tags":null},"minimax/minimax-01":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"minimax/minimax-01","knowledge":null,"last_updated":"2025-01-15","lifecycle":null,"limits":{"context":1000192,"output":1000192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax-01","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"minimax/minimax-m1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"minimax/minimax-m1","knowledge":null,"last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1000000,"output":40000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"minimax/minimax-m2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"minimax/minimax-m2-her":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"minimax/minimax-m2-her","knowledge":null,"last_updated":"2026-01-23","lifecycle":null,"limits":{"context":65536,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2-her","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-23","retired":false,"tags":null},"minimax/minimax-m2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"minimax/minimax-m2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196608,"output":196608},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":524288,"output":512000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"mistralai/codestral-2508":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/codestral-2508","knowledge":null,"last_updated":"2025-08-01","lifecycle":null,"limits":{"context":256000,"output":51200},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Mistral: Codestral 2508","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-01","retired":false,"tags":null},"mistralai/ministral-14b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/ministral-14b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 14B 2512","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/ministral-3b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/ministral-3b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 3B 2512","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/ministral-8b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/ministral-8b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 8B 2512","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/mistral-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-large","knowledge":null,"last_updated":"2024-02-26","lifecycle":null,"limits":{"context":128000,"output":25600},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Mistral Large","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-02-26","retired":false,"tags":null},"mistralai/mistral-large-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-large-2407","knowledge":null,"last_updated":"2024-11-19","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Mistral Large 2407","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-11-19","retired":false,"tags":null},"mistralai/mistral-large-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-large-2512","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral Large 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistralai/mistral-medium-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3","knowledge":null,"last_updated":"2025-05-07","lifecycle":null,"limits":{"context":131072,"output":26215},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistralai/mistral-medium-3-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3-5","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"mistralai/mistral-medium-3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3.1","knowledge":null,"last_updated":"2025-08-13","lifecycle":null,"limits":{"context":131072,"output":26215},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"mistralai/mistral-nemo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.019,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-nemo","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"mistralai/mistral-saba":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-saba","knowledge":null,"last_updated":"2025-02-17","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Mistral: Saba","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-02-17","retired":false,"tags":null},"mistralai/mistral-small-24b-instruct-2501":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.05,"output":0.08},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-small-24b-instruct-2501","knowledge":null,"last_updated":"2025-01-30","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-30","retired":false,"tags":null},"mistralai/mistral-small-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-small-2603","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"mistralai/mistral-small-3.1-24b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.351,"output":0.555},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"mistralai/mistral-small-3.1-24b-instruct","knowledge":null,"last_updated":"2025-03-17","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3.1 24B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-17","retired":false,"tags":null},"mistralai/mistral-small-3.2-24b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09375,"output":0.25},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-small-3.2-24b-instruct","knowledge":null,"last_updated":"2025-06-20","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3.2 24B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"mistralai/mixtral-8x22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mixtral-8x22b-instruct","knowledge":null,"last_updated":"2024-04-17","lifecycle":null,"limits":{"context":65536,"output":13108},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Mistral: Mixtral 8x22B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-04-17","retired":false,"tags":null},"mistralai/voxtral-small-24b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/voxtral-small-24b-2507","knowledge":null,"last_updated":"2025-10-30","lifecycle":null,"limits":{"context":32000,"output":6400},"modalities":{"input":["text","audio","pdf"],"output":["text"]},"model":null,"name":"Mistral: Voxtral Small 24B 2507","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"moonshotai/kimi-k2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.57,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"moonshotai/kimi-k2","knowledge":null,"last_updated":"2025-07-11","lifecycle":null,"limits":{"context":131072,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2 0711","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"moonshotai/kimi-k2-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-0905","knowledge":null,"last_updated":"2025-09-04","lifecycle":null,"limits":{"context":262144,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2 0905","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"moonshotai/kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":262144,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"moonshotai/kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"moonshotai/kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.8,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"morph/morph-v3-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.8,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"morph/morph-v3-fast","knowledge":null,"last_updated":"2025-07-07","lifecycle":null,"limits":{"context":81920,"output":38000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph: Morph V3 Fast","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-07","retired":false,"tags":null},"morph/morph-v3-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.9,"output":1.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"morph/morph-v3-large","knowledge":null,"last_updated":"2025-07-07","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph: Morph V3 Large","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-07","retired":false,"tags":null},"nex-agi/nex-n2-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0025,"input":0.025,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...","family":"agi","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nex-agi/nex-n2-mini","knowledge":null,"last_updated":"2026-06-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nex AGI: Nex-N2-Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"nex-agi/nex-n2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...","family":"agi","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"nex-agi/nex-n2-pro","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nex AGI: Nex-N2-Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-08","retired":false,"tags":null},"nousresearch/hermes-3-llama-3.1-405b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"nousresearch/hermes-3-llama-3.1-405b","knowledge":null,"last_updated":"2024-08-16","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 3 405B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-16","retired":false,"tags":null},"nousresearch/hermes-3-llama-3.1-70b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.7,"output":0.7},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"nousresearch/hermes-3-llama-3.1-70b","knowledge":null,"last_updated":"2024-08-18","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 3 70B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-18","retired":false,"tags":null},"nousresearch/hermes-4-405b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nousresearch","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"nousresearch/hermes-4-405b","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":26215},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 4 405B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"nousresearch/hermes-4-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nousresearch","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"nousresearch/hermes-4-70b","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 4 70B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"nvidia/nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-30b-a3b","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"structured_output":false,"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.085,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b:free","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Super (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/nemotron-3-ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":512288,"output":512288},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-3-ultra-550b-a55b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Ultra (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-3.5-content-safety:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"nvidia/nemotron-3.5-content-safety:free","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo","knowledge":"2021-09-01","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"GPT-3.5-turbo","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"openai/gpt-3.5-turbo-0613":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-0613","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":4095,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/gpt-3.5-turbo-16k":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-16k","knowledge":null,"last_updated":"2023-08-28","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo 16k","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-08-28","retired":false,"tags":null},"openai/gpt-3.5-turbo-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.5,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-instruct","knowledge":null,"last_updated":"2023-09-28","lifecycle":null,"limits":{"context":4095,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-09-28","retired":false,"tags":null},"openai/gpt-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8191,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"GPT-4","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4-turbo","knowledge":"2023-12","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4 Turbo","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4-turbo-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4-turbo-preview","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4 Turbo Preview ($$$$)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-05-13":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-05-13","knowledge":"2023-09","last_updated":"2024-05-13","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o (2024-05-13)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-08-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-08-06","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o (2024-08-06)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-06","retired":false,"tags":null},"openai/gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-11-20","knowledge":"2023-09","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o (2024-11-20)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"openai/gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-4o-mini-2024-07-18":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-mini-2024-07-18","knowledge":null,"last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":1.25,"input":10,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5-image","knowledge":null,"last_updated":"2025-10-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5 Image ($$$$)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"openai/gpt-5-image-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5-image-mini","knowledge":null,"last_updated":"2025-10-16","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5 Image Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-16","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-pro","knowledge":"2024-09-30","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"openai/gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex-mini","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-chat","knowledge":null,"last_updated":"2025-12-10","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.2 Chat (retires Aug 10)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-10","retired":false,"tags":null},"openai/gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":21,"output":168},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.3-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.3-chat","knowledge":null,"last_updated":"2026-03-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.3 Chat (retires Aug 10)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai/gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.4-image-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":2,"input":8,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5.4 Image 2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-luna-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-audio":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-audio","knowledge":null,"last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"model":null,"name":"OpenAI: GPT Audio","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"openai/gpt-audio-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-audio-mini","knowledge":null,"last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"model":null,"name":"OpenAI: GPT Audio Mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"openai/gpt-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-chat-latest","knowledge":null,"last_updated":"2026-05-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"OpenAI: GPT Chat Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.03,"output":0.17},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-safeguard-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0375,"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-safeguard-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-safeguard-20b-GGUF"}],"hf_downloads":101805,"hf_likes":243,"matched_hugging_face_id":"openai/gpt-oss-safeguard-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-safeguard-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-09-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-safeguard-20b","knowledge":null,"last_updated":"2025-10-29","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: gpt-oss-safeguard-20b","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-29","retired":false,"tags":null},"openai/o1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"openai/o1-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":150,"output":600},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o1-pro","knowledge":"2023-09","last_updated":"2025-03-19","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o1-pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-19","retired":false,"tags":null},"openai/o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"openai/o3-mini-high":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3-mini-high","knowledge":null,"last_updated":"2025-02-12","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: o3 Mini High","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-02-12","retired":false,"tags":null},"openai/o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":80},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3-pro","knowledge":"2024-05","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf","image"],"output":["text"]},"model":null,"name":"o3-pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"openai/o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o4-mini-high":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o4-mini-high","knowledge":null,"last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"OpenAI: o4 Mini High","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openrouter/auto":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"openrouter/auto","knowledge":null,"last_updated":"2026-03-15","lifecycle":null,"limits":{"context":2000000,"output":32768},"modalities":{"input":["audio","image","pdf","text","video"],"output":["image","text"]},"model":null,"name":"Auto Router","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"openrouter/bodybuilder":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Preview model for early access evaluation, prototyping, and compatibility testing","open_weights":false,"status":"beta"},"family":null,"id":"openrouter/bodybuilder","knowledge":null,"last_updated":"2026-03-15","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Body Builder (beta)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"openrouter/free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openrouter/free","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenRouter Free Models Router","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"openrouter/pareto-code":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","open_weights":false,"temperature":false},"family":null,"id":"openrouter/pareto-code","knowledge":null,"last_updated":"2026-05-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Pareto Code Router","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"perceptron/perceptron-mk1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.15,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"perceptron/perceptron-mk1","knowledge":null,"last_updated":"2026-05-12","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Perceptron: Perceptron Mk1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-12","retired":false,"tags":null},"perplexity/sonar":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"perplexity/sonar","knowledge":null,"last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127072,"output":25415},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"perplexity/sonar-deep-research":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":8,"reasoning":3},"deprecated":false,"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"perplexity/sonar-deep-research","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":128000,"output":25600},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Deep Research","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"perplexity/sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"perplexity/sonar-pro","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"perplexity/sonar-pro-search":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"perplexity/sonar-pro-search","knowledge":null,"last_updated":"2025-10-30","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Pro Search","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"perplexity/sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"perplexity/sonar-reasoning-pro","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":128000,"output":25600},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Reasoning Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"poolside/laguna-s-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna S 2.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"poolside/laguna-s-2.1:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1:free","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna S 2.1 (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"poolside/laguna-xs-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-xs-2.1","knowledge":null,"last_updated":"2026-07-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna XS 2.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-02","retired":false,"tags":null},"poolside/laguna-xs-2.1:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-xs-2.1:free","knowledge":null,"last_updated":"2026-07-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna XS 2.1 (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-02","retired":false,"tags":null},"qwen/qwen-2.5-72b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.36,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-2.5-72b-instruct","knowledge":null,"last_updated":"2024-09-19","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 72B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"qwen/qwen-2.5-7b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-2.5-7b-instruct","knowledge":null,"last_updated":"2024-10-16","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen2.5 7B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-10-16","retired":false,"tags":null},"qwen/qwen-2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.66,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen-2.5-coder-32b-instruct","knowledge":null,"last_updated":"2024-11-11","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 Coder 32B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-11-11","retired":false,"tags":null},"qwen/qwen-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.052,"cache_write":0.325,"input":0.26,"output":0.78},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-plus","knowledge":"2024-04","last_updated":"2025-09-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Plus","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"qwen/qwen-plus-2025-07-28":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":0.78},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-plus-2025-07-28","knowledge":null,"last_updated":"2025-09-08","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen Plus 0728","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-08","retired":false,"tags":null},"qwen/qwen-plus-2025-07-28:thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.5,"input":0.4,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-plus-2025-07-28:thinking","knowledge":null,"last_updated":"2025-09-08","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen Plus 0728 (thinking)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-08","retired":false,"tags":null},"qwen/qwen2.5-vl-72b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen2.5-vl-72b-instruct","knowledge":null,"last_updated":"2025-02-01","lifecycle":null,"limits":{"context":32000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen2.5 VL 72B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-02-01","retired":false,"tags":null},"qwen/qwen3-14b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2275,"output":0.91},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-14b","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 14B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-235b-a22b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.455,"output":1.82},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B-A22B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen/qwen3-235b-a22b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1495,"output":0.598},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-2507","knowledge":null,"last_updated":"2025-07-21","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"qwen/qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.23,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","knowledge":null,"last_updated":"2025-07-25","lifecycle":null,"limits":{"context":131072,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 235B A22B Thinking 2507","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"qwen/qwen3-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.52},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-30b-a3b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.52},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","knowledge":null,"last_updated":"2025-07-29","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-29","retired":false,"tags":null},"qwen/qwen3-30b-a3b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-thinking-2507","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":81920,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B Thinking 2507","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"qwen/qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.104,"output":0.416},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-32b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen/qwen3-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.117,"output":0.455},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-8b","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 8B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.975,"output":4.875},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder","knowledge":null,"last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder 480B A35B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"qwen/qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2925,"output":1.4625},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":160000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen/qwen3-coder-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.039,"cache_write":0.24375,"input":0.195,"output":0.975},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-coder-flash","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"qwen/qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-next","knowledge":null,"last_updated":"2026-02-04","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder Next","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-04","retired":false,"tags":null},"qwen/qwen3-coder-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"cache_write":0.8125,"input":0.65,"output":3.25},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-plus","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Plus","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"qwen/qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.156,"cache_write":0.975,"input":0.78,"output":3.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-max-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.78,"output":3.9},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-max-thinking","knowledge":null,"last_updated":"2026-02-09","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Max Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-09","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.0975,"output":0.78},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-thinking","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B (Thinking)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":1.04},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-thinking","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 235B A22B Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.52},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","knowledge":null,"last_updated":"2025-10-06","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 30B A3B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","knowledge":null,"last_updated":"2025-10-06","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 30B A3B Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"qwen/qwen3-vl-32b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.104,"output":0.416},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-32b-instruct","knowledge":null,"last_updated":"2025-10-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 32B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-23","retired":false,"tags":null},"qwen/qwen3-vl-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.117,"output":0.455},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-8b-instruct","knowledge":null,"last_updated":"2025-10-14","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 8B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"qwen/qwen3-vl-8b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":2.1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-8b-thinking","knowledge":null,"last_updated":"2025-10-14","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 8B Thinking","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":2.08},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.195,"output":1.56},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-27b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1625,"output":1.3},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-35b-a3b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.39,"output":2.34},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"qwen/qwen3.5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-9b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-flash-02-23":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.065,"output":0.26},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-flash-02-23","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen/qwen3.5-plus-02-15":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":1.56},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-plus-02-15","knowledge":null,"last_updated":"2026-02-16","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5 Plus 2026-02-15","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen/qwen3.5-plus-20260420":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.375,"input":0.3,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-plus-20260420","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":2.7},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"qwen/qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"qwen/qwen3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.234375,"input":0.1875,"output":1.125},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-flash","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":1.28375,"input":1.027,"output":6.162},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-max-preview","knowledge":"2025-04","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 Max Preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"qwen/qwen3.6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.40625,"input":0.325,"output":1.95},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"qwen/qwen3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3.7-flash","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"qwen/qwen3.7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"cache_write":1.5625,"input":1.25,"output":3.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"qwen/qwen3.7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.032,"cache_write":0.4,"input":0.32,"output":1.28},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"qwen/qwen3.8-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.8-max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"rekaai/reka-edge":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"rekaai/reka-edge","knowledge":null,"last_updated":"2026-03-20","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Reka Edge","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-20","retired":false,"tags":null},"rekaai/reka-flash-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"reka","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"rekaai/reka-flash-3","knowledge":null,"last_updated":"2025-03-12","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Reka Flash 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"relace/relace-apply-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.85,"output":1.25},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","open_weights":false,"structured_output":false,"temperature":false},"family":null,"id":"relace/relace-apply-3","knowledge":null,"last_updated":"2025-09-26","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Relace: Relace Apply 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-26","retired":false,"tags":null},"relace/relace-search":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"relace/relace-search","knowledge":null,"last_updated":"2025-12-08","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Relace: Relace Search","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"sakana/fugu-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","family":"fugu","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"sakana/fugu-ultra","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-15","retired":false,"tags":null},"sao10k/l3-lunaris-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.04,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"sao10k/l3-lunaris-8b","knowledge":null,"last_updated":"2024-08-13","lifecycle":null,"limits":{"context":8192,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3 8B Lunaris","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-13","retired":false,"tags":null},"sao10k/l3.1-euryale-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.85,"output":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"sao10k/l3.1-euryale-70b","knowledge":null,"last_updated":"2024-08-28","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-08-28","retired":false,"tags":null},"sao10k/l3.3-euryale-70b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.65,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"sao10k/l3.3-euryale-70b","knowledge":null,"last_updated":"2024-12-18","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3.3 Euryale 70B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-12-18","retired":false,"tags":null},"stealth/claude-opus-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/claude-opus-4.6","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Stealth: Claude Opus 4.6 (20% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stealth/claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/claude-opus-4.7","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Stealth: Claude Opus 4.7 (20% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stealth/claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.8 is offered at 20% lower cost than standard Claude Opus 4.8 pricing and is not served by Anthropic or Kilo Code.","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/claude-opus-4.8","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Stealth: Claude Opus 4.8 (20% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stealth/claude-sonnet-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"cache_write":3,"input":2.4,"output":12,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/claude-sonnet-4.6","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Stealth: Claude Sonnet 4.6 (20% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stealth/gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"cache_write":5,"input":4,"output":24,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of GPT-5.6 Sol is offered at 20% lower cost than standard GPT-5.6 Sol pricing and is not served by OpenAI or Kilo Code.","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/gpt-5.6-sol","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Stealth: GPT-5.6 Sol (20% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stealth/qwen3.6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.3125,"input":0.25,"output":1.5,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.","family":"qwen3.6","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"stealth/qwen3.6-plus","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Stealth: Qwen3.6 Plus (50% off)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"stepfun/step-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"stepfun/step-3.5-flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Step 3.5 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"stepfun/step-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"stepfun/step-3.7-flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"stepfun/step-3.7-flash:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0,"input":0,"output":0,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"stepfun/step-3.7-flash:free","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"StepFun: Step 3.7 Flash (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"tencent/hunyuan-a13b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"tencent/hunyuan-a13b-instruct","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Tencent: Hunyuan A13B Instruct","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"tencent/hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","family":"Hy","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"tencent/hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"tencent/hy3-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.18,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"tencent/hy3-preview","knowledge":null,"last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3 preview","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"tencent/hy3:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0,"input":0,"output":0,"reasoning":0},"deprecated":false,"extra":{"attachment":false,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent, activating 21B parameters per token. It supports configurable reasoning effort, agentic workflows, reliable tool calling, and long-context tasks across coding, document processing, financial analysis, and frontend development.","family":"Hy","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"tencent/hy3:free","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Tencent: Hy3 (free)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"thedrummer/cydonia-24b-v4.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.15,"input":0.3,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"thedrummer/cydonia-24b-v4.1","knowledge":null,"last_updated":"2025-09-27","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Cydonia 24B V4.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-27","retired":false,"tags":null},"thedrummer/rocinante-12b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.25,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"thedrummer/rocinante-12b","knowledge":null,"last_updated":"2024-09-30","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Rocinante 12B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-09-30","retired":false,"tags":null},"thedrummer/skyfall-36b-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.25,"input":0.55,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"thedrummer/skyfall-36b-v2","knowledge":null,"last_updated":"2025-03-10","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Skyfall 36B V2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-03-10","retired":false,"tags":null},"thedrummer/unslopnemo-12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"thedrummer/unslopnemo-12b","knowledge":null,"last_updated":"2024-11-08","lifecycle":null,"limits":{"context":1024000,"output":1024000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: UnslopNemo 12B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2024-11-08","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","family":"ling","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":524288,"output":524288},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/inkling-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","family":"ling","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":524288},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"undi95/remm-slerp-l2-13b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.45,"output":0.65},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"undi95/remm-slerp-l2-13b","knowledge":null,"last_updated":"2023-07-22","lifecycle":null,"limits":{"context":6144,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ReMM SLERP 13B","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2023-07-22","retired":false,"tags":null},"upstage/solar-pro-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"upstage/solar-pro-3","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Upstage: Solar Pro 3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"writer/palmyra-x5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.6,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"palmyra","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"writer/palmyra-x5","knowledge":null,"last_updated":"2026-01-21","lifecycle":null,"limits":{"context":1040000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Writer: Palmyra X5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-21","retired":false,"tags":null},"x-ai/grok-4.20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"x-ai/grok-4.20","knowledge":null,"last_updated":"2026-03-31","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.20","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-31","retired":false,"tags":null},"x-ai/grok-4.20-multi-agent":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"x-ai/grok-4.20-multi-agent","knowledge":null,"last_updated":"2026-03-31","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.20 Multi-Agent","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-31","retired":false,"tags":null},"x-ai/grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"x-ai/grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"x-ai/grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"x-ai/grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"x-ai/grok-build-0.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"x-ai/grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"xiaomi/mimo-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.003,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"xiaomi/mimo-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.004,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"z-ai/glm-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"z-ai/glm-4.5-air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.13,"output":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-4.5-air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5-Air","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"z-ai/glm-4.5v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-4.5v","knowledge":"2025-04","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM-4.5V","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"z-ai/glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"z-ai/glm-4.6v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.055,"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-4.6v","knowledge":"2025-04","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"GLM-4.6V","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"z-ai/glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"z-ai/glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"z-ai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"z-ai/glm-5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-5-turbo","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5-Turbo","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"z-ai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.38,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"z-ai/glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"z-ai/glm-5v-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"z-ai/glm-5v-turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"GLM-5V-Turbo","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"~anthropic/claude-fable-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"This model always redirects to the latest model in the Claude Fable family.","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"~anthropic/claude-fable-latest","knowledge":null,"last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Anthropic: Claude Fable Latest ($$$$)","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"~anthropic/claude-haiku-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"~anthropic/claude-haiku-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Anthropic Claude Haiku Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~anthropic/claude-opus-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"~anthropic/claude-opus-latest","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"~anthropic/claude-sonnet-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"~anthropic/claude-sonnet-latest","knowledge":"2025-08-31","last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Anthropic Claude Sonnet Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~deepseek/deepseek-v4-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.018,"input":0.09,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"~deepseek/deepseek-v4-flash-latest","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-08-01","retired":false,"tags":null},"~google/gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"output":7.5,"reasoning":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"~google/gemini-flash-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"model":null,"name":"Google Gemini Flash Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~google/gemini-pro-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"~google/gemini-pro-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]},"model":null,"name":"Google Gemini Pro Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~moonshotai/kimi-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.29,"input":2.9,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"~moonshotai/kimi-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MoonshotAI Kimi Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~openai/gpt-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"~openai/gpt-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"OpenAI GPT Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~openai/gpt-mini-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"~openai/gpt-mini-latest","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"OpenAI GPT Mini Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"~x-ai/grok-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"This model always redirects to the latest Grok model from xAI.","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"~x-ai/grok-latest","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"xAI: Grok Latest","pricing":null,"provider":"kilo","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null}},"name":"Kilo Gateway","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;