@agentjido/llmdb 2026.8.2

package/dist/providers/orcarouter.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "orcarouter",
+  "anthropic/claude-haiku-4.5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4.1" | "anthropic/claude-opus-4.5" | "anthropic/claude-opus-4.6" | "anthropic/claude-opus-4.7" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4.5" | "anthropic/claude-sonnet-4.6" | "deepseek/deepseek-chat" | "deepseek/deepseek-reasoner" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-pro" | "google/gemini-2.5-flash" | "google/gemini-2.5-flash-lite" | "google/gemini-2.5-pro" | "google/gemini-3-flash-preview" | "google/gemini-3-pro-preview" | "google/gemini-3.1-flash-lite-preview" | "google/gemini-3.1-pro-preview" | "google/gemini-3.1-pro-preview-customtools" | "google/gemini-flash-latest" | "google/gemini-flash-lite-latest" | "google/gemma-4-26b-a4b-it" | "google/gemma-4-31b-it" | "grok/grok-4.3" | "kimi/kimi-k2.5" | "kimi/kimi-k2.6" | "minimax/minimax-m2.5" | "minimax/minimax-m2.5-highspeed" | "minimax/minimax-m2.7" | "minimax/minimax-m2.7-highspeed" | "openai/gpt-3.5-turbo" | "openai/gpt-4" | "openai/gpt-4-turbo" | "openai/gpt-4.1" | "openai/gpt-4.1-mini" | "openai/gpt-4.1-nano" | "openai/gpt-4o" | "openai/gpt-4o-2024-05-13" | "openai/gpt-4o-2024-08-06" | "openai/gpt-4o-2024-11-20" | "openai/gpt-4o-mini" | "openai/gpt-5" | "openai/gpt-5-chat-latest" | "openai/gpt-5-codex" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5-pro" | "openai/gpt-5.1" | "openai/gpt-5.1-chat-latest" | "openai/gpt-5.1-codex" | "openai/gpt-5.1-codex-max" | "openai/gpt-5.1-codex-mini" | "openai/gpt-5.2" | "openai/gpt-5.2-chat-latest" | "openai/gpt-5.2-codex" | "openai/gpt-5.2-pro" | "openai/gpt-5.3-chat-latest" | "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" | "orcarouter/auto" | "qwen/qwen3-max" | "qwen/qwen3.5-122b-a10b" | "qwen/qwen3.5-27b" | "qwen/qwen3.5-35b-a3b" | "qwen/qwen3.5-397b-a17b" | "qwen/qwen3.5-plus" | "qwen/qwen3.6-35b-a3b" | "qwen/qwen3.6-plus" | "z-ai/glm-4.5" | "z-ai/glm-4.5-air" | "z-ai/glm-4.6" | "z-ai/glm-4.7" | "z-ai/glm-5" | "z-ai/glm-5.1"
+>;
+export default provider;

package/dist/providers/orcarouter.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.orcarouter.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.orcarouter.ai","env":["ORCAROUTER_API_KEY"],"exclude_models":null,"extra":null,"id":"orcarouter","models":{"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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic/claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"anthropic/claude-opus-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4 (latest)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-opus-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1 (latest)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"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":"orcarouter","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","experimental":{"modes":{"fast":{"cost":{"cache_read":3,"cache_write":37.5,"input":30,"output":150},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":"orcarouter","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","experimental":{"modes":{"fast":{"cost":{"cache_read":3,"cache_write":37.5,"input":30,"output":150},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":"orcarouter","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4 (latest)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"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":"orcarouter","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":"effort","values":["low","medium","high"]}],"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":"orcarouter","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"deepseek/deepseek-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek/deepseek-chat","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Chat","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-reasoner":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":true,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-reasoner","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Reasoner","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-12-01","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":0.0028,"input":0.19,"output":0.37},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"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":"orcarouter","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":0.003625,"input":0.56,"output":1.12},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"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":"orcarouter","provider_model_id":null,"release_date":"2026-04-24","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,"input_audio":1,"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":"effort","values":["low","medium","high"]}],"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":"orcarouter","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,"input_audio":0.3,"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":"effort","values":["low","medium","high"]}],"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":"orcarouter","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":2.5,"output":15},"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":[{"type":"effort","values":["low","medium","high"]}],"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":"orcarouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"input_audio":1,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"google/gemini-3-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":4,"output":18},"deprecated":false,"extra":{"attachment":true,"description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","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-pro-preview","knowledge":"2025-01","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Pro Preview","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"google/gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"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":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":4,"output":18},"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":"orcarouter","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":4,"output":18},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview Custom Tools","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":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-flash-latest","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 Flash Latest","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemini-flash-lite-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"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-flash-lite-latest","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 Flash-Lite Latest","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.33},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.38},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"grok/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":"grok/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":"orcarouter","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"kimi/kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"kimi/kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"kimi/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"minimax/minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.5-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.5-highspeed","knowledge":null,"last_updated":"2026-02-13","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5-highspeed","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-13","retired":false,"tags":null},"minimax/minimax-m2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m2.7-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.7-highspeed","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7-highspeed","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0,"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":"orcarouter","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"openai/gpt-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-4","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":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":"orcarouter","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":"orcarouter","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":"orcarouter","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":"orcarouter","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":"orcarouter","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-05-13":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-05-13","knowledge":"2023-09","last_updated":"2024-05-13","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o (2024-05-13)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-08-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-08-06","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o (2024-08-06)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2024-08-06","retired":false,"tags":null},"openai/gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-11-20","knowledge":"2023-09","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o (2024-11-20)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"openai/gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"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":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-chat-latest":{"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":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5-chat-latest","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 Chat (latest)","pricing":null,"provider":"orcarouter","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":[],"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":"orcarouter","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":[],"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":"orcarouter","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":[],"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":"orcarouter","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":["low","medium","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":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1-chat-latest","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Chat","pricing":null,"provider":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"orcarouter","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":[],"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":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-chat-latest","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Chat","pricing":null,"provider":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":21,"output":168},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":false},"family":null,"id":"openai/gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Pro","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.3-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.3-chat-latest","knowledge":"2025-08-31","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Chat (latest)","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"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":"orcarouter","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":5,"output":22.5},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","experimental":{"modes":{"fast":{"cost":{"cache_read":0.5,"input":5,"output":30},"provider":{"body":{"service_tier":"priority"}}}}},"family":"gpt","open_weights":false,"reasoning_options":[],"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":"orcarouter","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","experimental":{"modes":{"fast":{"cost":{"cache_read":0.15,"input":1.5,"output":9},"provider":{"body":{"service_tier":"priority"}}}}},"family":"gpt-mini","open_weights":false,"reasoning_options":[],"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":"orcarouter","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":[],"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":"orcarouter","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":60,"output":270},"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":["low","medium","high"]}],"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":"orcarouter","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","experimental":{"modes":{"fast":{"cost":{"cache_read":1.25,"input":12.5,"output":75},"provider":{"body":{"service_tier":"priority"}}}}},"family":"gpt","open_weights":false,"reasoning_options":[],"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":"orcarouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":"orcarouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"orcarouter/auto":{"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":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"orcarouter/auto","knowledge":null,"last_updated":"2026-05-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OrcaRouter Auto","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen/qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.359,"output":1.434},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.115,"output":0.917},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.086,"output":0.688},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-27b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.057,"output":0.459},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-35b-a3b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.172,"output":1.032},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"qwen/qwen3.5-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":{"input":0.115,"output":0.688,"reasoning":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3.5-plus","knowledge":"2025-04","last_updated":"2026-02-16","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 Plus","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen/qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.248,"output":1.485},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"qwen/qwen3.6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"z-ai/glm-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"cache_write":0,"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":[],"temperature":true},"family":null,"id":"z-ai/glm-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"z-ai/glm-4.5-air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0,"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":[],"temperature":true},"family":null,"id":"z-ai/glm-4.5-air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5-Air","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"z-ai/glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"cache_write":0,"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":[],"temperature":true},"family":null,"id":"z-ai/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":"orcarouter","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"z-ai/glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"cache_write":0,"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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"z-ai/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":"orcarouter","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"z-ai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"z-ai/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"z-ai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"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"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"orcarouter","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null}},"name":"OrcaRouter","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/ovhcloud.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "ovhcloud",
+  "gpt-oss-120b" | "gpt-oss-20b" | "meta-llama-3_3-70b-instruct" | "mistral-7b-instruct-v0.3" | "mistral-nemo-instruct-2407" | "mistral-small-3.2-24b-instruct-2506" | "qwen2.5-vl-72b-instruct" | "qwen3-32b" | "qwen3-coder-30b-a3b-instruct" | "qwen3.5-397b-a17b" | "qwen3.5-9b" | "qwen3.6-27b" | "qwen3guard-gen-0.6b" | "qwen3guard-gen-8b"
+>;
+export default provider;

package/dist/providers/ovhcloud.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","catalog_only":true,"config_schema":null,"doc":"https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//","env":["OVHCLOUD_API_KEY"],"exclude_models":null,"extra":null,"id":"ovhcloud","models":{"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":0.09,"output":0.47},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"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":{"input":0.05,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"gpt-oss-20b","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-20b","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"meta-llama-3_3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.74,"output":0.74},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama-3_3-70b-instruct","knowledge":null,"last_updated":"2025-04-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta-Llama-3_3-70B-Instruct","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-04-01","retired":false,"tags":null},"mistral-7b-instruct-v0.3":{"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":0.11,"output":0.11},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral-7b-instruct-v0.3","knowledge":null,"last_updated":"2025-04-01","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral-7B-Instruct-v0.3","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-04-01","retired":false,"tags":null},"mistral-nemo-instruct-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral-nemo-instruct-2407","knowledge":null,"last_updated":"2024-11-20","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral-Nemo-Instruct-2407","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"mistral-small-3.2-24b-instruct-2506":{"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":0.31},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral-small-3.2-24b-instruct-2506","knowledge":null,"last_updated":"2025-07-16","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral-Small-3.2-24B-Instruct-2506","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-07-16","retired":false,"tags":null},"qwen2.5-vl-72b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.01,"output":1.01},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen2.5-vl-72b-instruct","knowledge":null,"last_updated":"2025-03-31","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5-VL-72B-Instruct","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-03-31","retired":false,"tags":null},"qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-32b","knowledge":null,"last_updated":"2025-07-16","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-32B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-07-16","retired":false,"tags":null},"qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-coder-30b-a3b-instruct","knowledge":null,"last_updated":"2025-10-28","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-30B-A3B-Instruct","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"qwen3.5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.71,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-05-18","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2026-05-18","retired":false,"tags":null},"qwen3.5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.18},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-9b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-9B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"qwen3.6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.47,"output":3.19},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-27b","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6-27B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"qwen3guard-gen-0.6b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"qwen3guard-gen-0.6b","knowledge":null,"last_updated":"2026-01-22","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3Guard-Gen-0.6B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2026-01-22","retired":false,"tags":null},"qwen3guard-gen-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"qwen3guard-gen-8b","knowledge":null,"last_updated":"2026-01-22","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3Guard-Gen-8B","pricing":null,"provider":"ovhcloud","provider_model_id":null,"release_date":"2026-01-22","retired":false,"tags":null}},"name":"OVHcloud AI Endpoints","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/perplexity.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "perplexity",
+  "sonar" | "sonar-deep-research" | "sonar-pro" | "sonar-reasoning-pro"
+>;
+export default provider;

package/dist/providers/perplexity.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":null,"config_schema":null,"doc":"https://docs.perplexity.ai","env":["PERPLEXITY_API_KEY"],"exclude_models":null,"extra":null,"id":"perplexity","models":{"sonar":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","open_weights":false,"temperature":true},"family":null,"id":"sonar","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sonar","pricing":null,"provider":"perplexity","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"sonar-deep-research":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":2,"output":8,"reasoning":3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":false},"family":null,"id":"sonar-deep-research","knowledge":"2025-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar Deep Research","pricing":null,"provider":"perplexity","provider_model_id":null,"release_date":"2025-02-01","retired":false,"tags":null},"sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":3,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","open_weights":false,"temperature":true},"family":null,"id":"sonar-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Pro","pricing":null,"provider":"perplexity","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":2,"output":8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"sonar-reasoning-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Reasoning Pro","pricing":null,"provider":"perplexity","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null}},"name":"Perplexity","pricing_defaults":null,"runtime":{"auth":{"env":["PERPLEXITY_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.perplexity.ai","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://docs.perplexity.ai"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/perplexity_agent.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "perplexity_agent",
+  "anthropic/claude-haiku-4-5" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "google/gemini-2.5-flash" | "google/gemini-2.5-pro" | "google/gemini-3-flash-preview" | "google/gemini-3.1-pro-preview" | "moonshot-ai/kimi-k2.7-code" | "moonshot-ai/kimi-k3" | "nvidia/nemotron-3-super-120b-a12b" | "openai/gpt-5-mini" | "openai/gpt-5.1" | "openai/gpt-5.2" | "openai/gpt-5.4" | "openai/gpt-5.5" | "perplexity/sonar" | "xai/grok-4-1-fast-non-reasoning"
+>;
+export default provider;

package/dist/providers/perplexity_agent.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.perplexity.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.perplexity.ai/docs/agent-api/models","env":["PERPLEXITY_API_KEY"],"exclude_models":null,"extra":null,"id":"perplexity_agent","models":{"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,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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","pricing":null,"provider":"perplexity_agent","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,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4-5","knowledge":"2025-03-31","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","pricing":null,"provider":"perplexity_agent","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,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"perplexity_agent","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,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["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":"perplexity_agent","provider_model_id":null,"release_date":"2026-04-16","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,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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","pricing":null,"provider":"perplexity_agent","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,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-02-17","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2026-02-17","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 model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"google/gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-05","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":"perplexity_agent","provider_model_id":null,"release_date":"2025-03-20","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":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"google/gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-05","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":"perplexity_agent","provider_model_id":null,"release_date":"2025-03-20","retired":false,"tags":null},"google/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"google/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2025-12-17","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":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"perplexity_agent","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"moonshot-ai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshot-ai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-07-30","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshot-ai/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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshot-ai/kimi-k3","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":"2026-02","last_updated":"2026-03-11","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"perplexity_agent","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"perplexity_agent","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"perplexity_agent","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"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":"perplexity_agent","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"perplexity/sonar":{"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":0.0625,"input":0.25,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","open_weights":false,"temperature":true},"family":null,"id":"perplexity/sonar","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sonar","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"xai/grok-4-1-fast-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":0.05,"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-4-1-fast-non-reasoning","knowledge":"2025-07","last_updated":"2025-11-19","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast (Non-Reasoning)","pricing":null,"provider":"perplexity_agent","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null}},"name":"Perplexity Agent","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/pioneer.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "pioneer",
+  "HuggingFaceTB/SmolLM3-3B-Base" | "LiquidAI/LFM2-24B-A2B" | "MiniMaxAI/MiniMax-M2.7" | "MiniMaxAI/MiniMax-M3" | "Qwen/Qwen3-1.7B-Base" | "Qwen/Qwen3-32B" | "Qwen/Qwen3-4B-Base" | "Qwen/Qwen3-4B-Instruct-2507" | "Qwen/Qwen3-8B" | "Qwen/Qwen3.5-9B" | "Qwen/Qwen3.6-27B" | "Qwen/Qwen3.6-35B-A3B" | "XiaomiMiMo/MiMo-V2.5" | "XiaomiMiMo/MiMo-V2.5-Pro" | "claude-haiku-4-5" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-6" | "claude-opus-4-7" | "claude-opus-4-8" | "claude-sonnet-4-5" | "claude-sonnet-4-6" | "deepseek-ai/DeepSeek-V4-Flash" | "deepseek-ai/DeepSeek-V4-Pro" | "fastino/gliguard-LLMGuardrails-300M" | "fastino/gliner2-base-v1" | "fastino/gliner2-large-v1" | "fastino/gliner2-multi-large-v1" | "fastino/gliner2-multi-v1" | "fastino/gliner2-privacy-filter-PII-multi" | "gemini-3-flash" | "gemini-3.1-pro" | "gemini-3.5-flash" | "google/diffusiongemma-26B-A4B-it" | "google/gemma-3-4b-pt" | "google/gemma-4-12B-it" | "google/gemma-4-31B-it" | "google/gemma-4-E2B-it" | "google/gemma-4-E4B-it" | "gpt-4.1" | "gpt-4.1-mini" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5-mini" | "gpt-5-nano" | "gpt-5.1" | "gpt-5.3-codex" | "gpt-5.4" | "gpt-5.4-mini" | "gpt-5.4-nano" | "gpt-5.5" | "meta-llama/Llama-3.1-8B-Instruct" | "meta-llama/Llama-3.2-1B-Instruct" | "meta-llama/Llama-3.2-3B-Instruct" | "meta-llama/Llama-3.3-70B-Instruct" | "mistral-medium-3.5" | "mistralai/Mistral-7B-Instruct-v0.3" | "mistralai/Mistral-Nemo-Instruct-2407" | "mistralai/Mistral-Small-4-119B-2603" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16" | "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8" | "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "pioneer/auto" | "qwen3.6-flash" | "qwen3.6-max-preview" | "qwen3.6-plus" | "qwen3.7-max" | "qwen3.7-plus" | "sakana/fugu-ultra" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2"
+>;
+export default provider;