@agentjido/llmdb 2026.8.2

package/dist/providers/impossibl.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "impossibl",
+  "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-5" | "cerebras/gpt-oss-120b" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-pro" | "fireworks/glm-5.2" | "fireworks/gpt-oss-120b" | "fireworks/gpt-oss-20b" | "google/gemini-2.5-flash" | "google/gemini-2.5-flash-lite" | "google/gemini-2.5-pro" | "google/gemini-3.1-flash-lite" | "google/gemini-3.1-pro-preview" | "google/gemini-3.5-flash" | "google/gemini-3.5-flash-lite" | "google/gemini-3.6-flash" | "groq/gpt-oss-120b" | "groq/gpt-oss-20b" | "moonshotai/kimi-k3" | "openai/gpt-3.5-turbo" | "openai/gpt-4-turbo" | "openai/gpt-4.1" | "openai/gpt-4.1-mini" | "openai/gpt-4.1-nano" | "openai/gpt-4o" | "openai/gpt-4o-mini" | "openai/gpt-5" | "openai/gpt-5-codex" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5-pro" | "openai/gpt-5.1" | "openai/gpt-5.1-codex" | "openai/gpt-5.1-codex-mini" | "openai/gpt-5.2" | "openai/gpt-5.2-codex" | "openai/gpt-5.3-codex" | "openai/gpt-5.4" | "openai/gpt-5.4-mini" | "openai/gpt-5.4-nano" | "openai/gpt-5.4-pro" | "openai/gpt-5.5" | "openai/gpt-5.5-pro" | "openai/gpt-5.6-luna" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/o1" | "openai/o3" | "openai/o3-mini" | "openai/o4-mini" | "qwen/qwen3.6-flash" | "qwen/qwen3.7-max" | "qwen/qwen3.7-plus" | "qwen/qwen3.8-max-preview" | "thinkingmachines/inkling" | "xai/grok-4.20-0309-non-reasoning" | "xai/grok-4.20-0309-reasoning" | "xai/grok-4.3" | "xai/grok-4.5" | "xai/grok-build-0.1" | "xiaomi/mimo-v2.5" | "zai/glm-4.5" | "zai/glm-4.5-air" | "zai/glm-4.6" | "zai/glm-4.7" | "zai/glm-5" | "zai/glm-5-turbo" | "zai/glm-5.1" | "zai/glm-5.2"
+>;
+export default provider;

package/dist/providers/impossibl.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.impossibl.com/v1","catalog_only":true,"config_schema":null,"doc":"https://impossibl.com/docs/models","env":["IMPOSSIBL_API_KEY"],"exclude_models":null,"extra":null,"id":"impossibl","models":{"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 model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"impossibl","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 lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"toggle"},{"min":1024,"type":"budget_tokens"}],"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":"impossibl","provider_model_id":null,"release_date":"2025-10-15","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":"toggle"},{"min":1024,"type":"budget_tokens"},{"type":"effort","values":["low","medium","high"]}],"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":"impossibl","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":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"min":1024,"type":"budget_tokens"},{"type":"effort","values":["low","medium","high","max"]}],"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":"impossibl","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":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"impossibl","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":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"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":"impossibl","provider_model_id":null,"release_date":"2026-05-28","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":"toggle"},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"impossibl","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":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"min":1024,"type":"budget_tokens"},{"type":"effort","values":["low","medium","high","max"]}],"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":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"impossibl","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":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"impossibl","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"cerebras/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":{"input":0.35,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"cerebras/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-05","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":0.19,"output":0.51},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-04-24","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":0.145,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"fireworks/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":0.14,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"fireworks/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"fireworks/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":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"fireworks/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"fireworks/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":0.035,"input":0.07,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"fireworks/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-05","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,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","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":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-06-17","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,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"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":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite","pricing":null,"provider":"impossibl","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,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, 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":"impossibl","provider_model_id":null,"release_date":"2025-06-17","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,"input":0.25,"output":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":["minimal","low","medium","high"]}],"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":"impossibl","provider_model_id":null,"release_date":"2026-05-07","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,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":"impossibl","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,"input":1.5,"output":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":["minimal","low","medium","high"]}],"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":"impossibl","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,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"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":"impossibl","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,"input":1.5,"output":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-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":"impossibl","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"groq/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":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"groq/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"groq/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":0.0375,"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"groq/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-05","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":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":false,"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"],"output":["text"]},"model":null,"name":"GPT-3.5-turbo","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2023-03-01","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":false,"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"],"output":["text"]},"model":null,"name":"GPT-4 Turbo","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2023-11-06","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":"Long-lived GPT workhorse for coding, instruction following, and production apps","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":"impossibl","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":"Affordable GPT-4.1 lane for fast coding help and structured extraction","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":"impossibl","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":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","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":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"impossibl","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":"Omni-era GPT for multimodal chat, practical coding, and general assistants","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":"impossibl","provider_model_id":null,"release_date":"2024-05-13","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":"Small omni GPT for cheap multimodal assistance and production-scale traffic","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":"impossibl","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":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"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"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-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":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"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"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-codex","knowledge":"2024-09-30","last_updated":"2025-09-15","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5-Codex","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-09-15","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":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"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"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"impossibl","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":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"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"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"impossibl","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":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["high"]}],"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":272000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Pro","pricing":null,"provider":"impossibl","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":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"impossibl","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":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"impossibl","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":0.025,"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"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex mini","pricing":null,"provider":"impossibl","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":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-12-11","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":"Code-specialist GPT for repository edits, reviews, and long-running software agents","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":"impossibl","provider_model_id":null,"release_date":"2025-12-11","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":["none","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":"impossibl","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":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":"impossibl","provider_model_id":null,"release_date":"2026-03-05","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":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"impossibl","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":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"impossibl","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":{"cache_read":3,"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"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"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"impossibl","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":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":"impossibl","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":{"cache_read":3,"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"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":"impossibl","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":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":"impossibl","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":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":"impossibl","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":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"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":"impossibl","provider_model_id":null,"release_date":"2026-07-09","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":["low","medium","high"]}],"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":"impossibl","provider_model_id":null,"release_date":"2024-12-05","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":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":"impossibl","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":false,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2024-12-20","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":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-04-16","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_read":0.05,"input":0.25,"output":1.5},"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":"toggle"}],"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":"impossibl","provider_model_id":null,"release_date":"2026-04-27","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":0.5,"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"qwen/qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"impossibl","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":0.08,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"qwen/qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"qwen/qwen3.8-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":{"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"temperature":true},"family":null,"id":"qwen/qwen3.8-max-preview","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max Preview","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-07-19","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":0.374,"input":1.87,"output":4.68},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"xai/grok-4.20-0309-non-reasoning":{"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":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,"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.20-0309-non-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"xai/grok-4.20-0309-reasoning":{"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":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.20-0309-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"xai/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":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"xai/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":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"xai/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":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/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":"impossibl","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","open_weights":true,"reasoning_options":[],"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":"impossibl","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"zai/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":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/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":"impossibl","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai/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":0.03,"input":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/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":"impossibl","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai/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":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai/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":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai/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":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/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":"impossibl","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai/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":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5-turbo","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5-Turbo","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"zai/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":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai/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":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"impossibl","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Impossibl","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/inception.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "inception",
+  "mercury-2" | "mercury-edit-2"
+>;
+export default provider;

package/dist/providers/inception.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.inceptionlabs.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://platform.inceptionlabs.ai/docs","env":["INCEPTION_API_KEY"],"exclude_models":null,"extra":null,"id":"inception","models":{"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":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mercury-2","knowledge":"2025-01-01","last_updated":"2026-02-24","lifecycle":null,"limits":{"context":128000,"output":50000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury 2","pricing":null,"provider":"inception","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"mercury-edit-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":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","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mercury-edit-2","knowledge":null,"last_updated":"2026-03-30","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury Edit 2","pricing":null,"provider":"inception","provider_model_id":null,"release_date":"2026-03-30","retired":false,"tags":null}},"name":"Inception","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/inceptron.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "inceptron",
+  "MiniMaxAI/MiniMax-M2.5" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.6-Fast" | "moonshotai/Kimi-K2.7-Code" | "zai-org/GLM-5.1-FP8" | "zai-org/GLM-5.2"
+>;
+export default provider;

package/dist/providers/inceptron.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.inceptron.io/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.inceptron.io","env":["INCEPTRON_API_KEY"],"exclude_models":null,"extra":null,"id":"inceptron","models":{"MiniMaxAI/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":0.05,"cache_write":0,"input":0.15,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/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":"inceptron","provider_model_id":null,"release_date":"2026-02-12","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":0.2,"cache_write":0,"input":0.66,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"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":"inceptron","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.6-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":0.4,"cache_write":0,"input":1.32,"output":7},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"status":"alpha","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6-Fast","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 Fast","pricing":null,"provider":"inceptron","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":0.2,"cache_write":0,"input":0.75,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"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":"inceptron","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"zai-org/GLM-5.1-FP8":{"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,"cache_write":0,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":494825,"hf_likes":119,"matched_hugging_face_id":"zai-org/GLM-5.1-FP8","memory":{"min_ram_gb":421.3,"min_vram_gb":386.2,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1-FP8","moe":{"active_experts":8,"active_parameters":60077205033,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753910024032,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1-FP8","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":202752},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/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,"cache_write":0,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Inceptron","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/inference.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "inference",
+  "google/gemma-3" | "meta/llama-3.1-8b-instruct" | "meta/llama-3.2-11b-vision-instruct" | "meta/llama-3.2-1b-instruct" | "meta/llama-3.2-3b-instruct" | "mistral/mistral-nemo-12b-instruct" | "osmosis/osmosis-structure-0.6b" | "qwen/qwen-2.5-7b-vision-instruct" | "qwen/qwen3-embedding-4b"
+>;
+export default provider;

package/dist/providers/inference.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://inference.net/v1","catalog_only":true,"config_schema":null,"doc":"https://inference.net/models","env":["INFERENCE_API_KEY"],"exclude_models":null,"extra":null,"id":"inference","models":{"google/gemma-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":{"input":0.15,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"temperature":true},"family":null,"id":"google/gemma-3","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":125000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemma 3","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"meta/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":0.025,"output":0.025},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-3.1-8b-instruct","knowledge":"2023-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"meta/llama-3.2-11b-vision-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":0.055,"output":0.055},"deprecated":false,"extra":{"attachment":true,"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-3.2-11b-vision-instruct","knowledge":"2023-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 3.2 11B Vision Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"meta/llama-3.2-1b-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":0.01,"output":0.01},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-3.2-1b-instruct","knowledge":"2023-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 1B Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"meta/llama-3.2-3b-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":0.02},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-3.2-3b-instruct","knowledge":"2023-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"mistral/mistral-nemo-12b-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":0.038,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":true,"temperature":true},"family":null,"id":"mistral/mistral-nemo-12b-instruct","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo 12B Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"osmosis/osmosis-structure-0.6b":{"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":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"osmosis","open_weights":true,"temperature":true},"family":null,"id":"osmosis/osmosis-structure-0.6b","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":4000,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Osmosis Structure 0.6B","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen/qwen-2.5-7b-vision-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":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen-2.5-7b-vision-instruct","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":125000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 2.5 7B Vision Instruct","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen/qwen3-embedding-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen/qwen3-embedding-4b","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":32000,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Embedding 4B","pricing":null,"provider":"inference","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null}},"name":"Inference","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/inferx.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "inferx",
+  "google/gemma-4-31b-it-fp8" | "qwen/qwen3.5-122b-a10b-nvfp4" | "qwen/qwen3.6-27b-fp8" | "qwen/qwen3.6-35b-a3b-fp8" | "qwen3-coder-next-fp8" | "qwen3-coder-next-fp8-1m"
+>;
+export default provider;

package/dist/providers/inferx.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://model.inferx.net/endpoints/v1","catalog_only":true,"config_schema":null,"doc":"https://model.inferx.net/endpoints","env":["INFERX_API_KEY"],"exclude_models":null,"extra":null,"id":"inferx","models":{"google/gemma-4-31b-it-fp8":{"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":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it-fp8","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b-nvfp4":{"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":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b-nvfp4","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":256144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 122B A10B NVFP4","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.6-27b-fp8":{"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":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b-fp8","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"qwen/qwen3.6-35b-a3b-fp8":{"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 multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-35b-a3b-fp8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"qwen3-coder-next-fp8":{"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,"output":0},"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":"qwen3-coder-next-fp8","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":256144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"qwen3-coder-next-fp8-1m":{"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,"output":0},"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":"qwen3-coder-next-fp8-1m","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":1024000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next FP8 1M","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null}},"name":"InferX","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/infomaniak.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "infomaniak",
+  "Qwen/Qwen3.5-122B-A10B-FP8" | "Qwen/Qwen3.5-397B-A17B-FP8" | "bge_multilingual_gemma2" | "google/gemma-4-31B-it" | "mini_lm_l12_v2" | "mistralai/Ministral-3-14B-Instruct-2512" | "mistralai/Mistral-Small-4-119B-2603" | "moonshotai/Kimi-K2.6" | "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8" | "swiss-ai/Apertus-v1.5-70B"
+>;
+export default provider;

package/dist/providers/infomaniak.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://www.infomaniak.com/en/hosting/ai-services/open-source-models","env":["INFOMANIAK_API_KEY","INFOMANIAK_PRODUCT_ID"],"exclude_models":null,"extra":null,"id":"infomaniak","models":{"Qwen/Qwen3.5-122B-A10B-FP8":{"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":0.5,"output":3.97},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":1257096,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B-FP8","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B-FP8","moe":{"active_experts":8,"active_parameters":9968428637,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125094006512,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-FP8":{"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":0.99,"output":4.46},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-FP8-GGUF"}],"hf_downloads":832304,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B-FP8","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B-FP8","moe":{"active_experts":10,"active_parameters":27656495656,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403422386928,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"bge_multilingual_gemma2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.08,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"bge_multilingual_gemma2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":8000,"output":3584},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Multilingual Gemma2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2024-07-25","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":{"input":0.25,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"mini_lm_l12_v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"mini_lm_l12_v2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":128,"output":384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"All-MiniLM-L12-v2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2021-08-30","retired":false,"tags":null},"mistralai/Ministral-3-14B-Instruct-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":{"input":0.37,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"mistralai/Ministral-3-14B-Instruct-2512","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":25600},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Instruct","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/Mistral-Small-4-119B-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":{"input":0.25,"output":0.93},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","interleaved":true,"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/Mistral-Small-4-119B-2603","knowledge":"2025-06","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-03-16","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":{"input":0.74,"output":3.72},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":true,"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8":{"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":0.06,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","interleaved":true,"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":606279,"hf_likes":355,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","moe":{"active_experts":6,"active_parameters":2985102726,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577946256,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1000000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"swiss-ai/Apertus-v1.5-70B":{"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":0.87,"output":3.1},"deprecated":false,"extra":{"attachment":true,"description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","open_weights":true,"status":"beta","temperature":true},"family":null,"id":"swiss-ai/Apertus-v1.5-70B","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":8192},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Apertus v1.5 70B","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null}},"name":"Infomaniak","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/io_net.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "io_net",
+  "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar" | "Qwen/Qwen2.5-VL-32B-Instruct" | "Qwen/Qwen3-235B-A22B-Thinking-2507" | "Qwen/Qwen3-Next-80B-A3B-Instruct" | "deepseek-ai/DeepSeek-R1-0528" | "meta-llama/Llama-3.2-90B-Vision-Instruct" | "meta-llama/Llama-3.3-70B-Instruct" | "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" | "mistralai/Devstral-Small-2505" | "mistralai/Magistral-Small-2506" | "mistralai/Mistral-Large-Instruct-2411" | "mistralai/Mistral-Nemo-Instruct-2407" | "moonshotai/Kimi-K2-Instruct-0905" | "moonshotai/Kimi-K2-Thinking" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "zai-org/GLM-4.6"
+>;
+export default provider;