@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/privatemode_ai.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "privatemode_ai",
-  "gpt-oss-120b" | "kimi-k2.6" | "qwen3-embedding-4b" | "voxtral-mini-3b" | "whisper-large-v3"
+  "deepseek-ocr-2" | "gpt-oss-120b" | "kimi-k2.6" | "kimi-latest" | "qwen3-embedding-4b" | "voxtral-mini-3b" | "whisper-large-v3"
 >;
 export default provider;

package/dist/providers/privatemode_ai.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"http://localhost:8080/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.privatemode.ai/api/overview","env":["PRIVATEMODE_API_KEY","PRIVATEMODE_ENDPOINT"],"exclude_models":null,"extra":null,"id":"privatemode_ai","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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":"2025-08","last_updated":"2025-08-14","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-08-04","retired":false,"tags":null},"kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"qwen3-embedding-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"qwen3-embedding-4b","knowledge":"2025-06","last_updated":"2025-06-06","lifecycle":null,"limits":{"context":32000,"output":2560},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding 4B","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-06-06","retired":false,"tags":null},"voxtral-mini-3b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Speech-to-text model for audio transcription, translation, and audio understanding","family":"voxtral","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"voxtral-mini-3b","knowledge":null,"last_updated":"2025-07","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Voxtral Mini 3B","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-07","retired":false,"tags":null},"whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"whisper-large-v3","knowledge":"2023-09","last_updated":"2023-09-01","lifecycle":null,"limits":{"output":4096},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper large-v3","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2023-09-01","retired":false,"tags":null}},"name":"Privatemode AI","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"http://localhost:8080/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.privatemode.ai/api/overview","env":["PRIVATEMODE_API_KEY","PRIVATEMODE_ENDPOINT"],"exclude_models":null,"extra":null,"id":"privatemode_ai","models":{"deepseek-ocr-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0924,"input":0.8897,"output":1.4675},"deprecated":false,"extra":{"attachment":true,"description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","open_weights":true,"status":"beta"},"family":null,"id":"deepseek-ocr-2","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek OCR 2","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0462,"input":0.4969,"output":1.9644},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"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":0.1733,"input":1.791,"output":8.9436},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":256000,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1733,"input":1.791,"output":8.9436},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-latest","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":256000,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi (latest)","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"qwen3-embedding-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.1502,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"qwen3-embedding-4b","knowledge":"2025-06","last_updated":"2025-06-06","lifecycle":null,"limits":{"context":32000,"output":2560},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding 4B","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-06-06","retired":false,"tags":null},"voxtral-mini-3b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.00462,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Speech-to-text model for audio transcription, translation, and audio understanding","family":"voxtral","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"voxtral-mini-3b","knowledge":null,"last_updated":"2025-07","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Voxtral Mini 3B","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2025-07","retired":false,"tags":null},"whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01618,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","open_weights":true},"family":null,"id":"whisper-large-v3","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":448,"output":4096},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper large-v3","pricing":null,"provider":"privatemode_ai","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null}},"name":"Privatemode AI","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/regolo_ai.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "regolo_ai",
-  "gpt-oss-120b" | "gpt-oss-20b" | "llama-3.1-8b-instruct" | "llama-3.3-70b-instruct" | "minimax-m2.5" | "mistral-small-4-119b" | "mistral-small3.2" | "qwen-image" | "qwen3-coder-next" | "qwen3-embedding-8b" | "qwen3-reranker-4b" | "qwen3.5-122b" | "qwen3.5-9b"
+  "apertus-70b" | "brick-complexity-pro" | "brick-v1-beta" | "deepseek-ocr-2" | "faster-whisper-large-v3" | "gemma4-31b" | "glm5.2" | "gpt-oss-120b" | "gpt-oss-20b" | "llama-3.3-70b-instruct" | "mistral-small-4-119b" | "qwen-image" | "qwen3-coder-next" | "qwen3-embedding-8b" | "qwen3-reranker-4b" | "qwen3.5-122b" | "qwen3.5-9b" | "qwen3.6-27b"
 >;
 export default provider;

package/dist/providers/regolo_ai.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.regolo.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.regolo.ai/","env":["REGOLO_API_KEY"],"exclude_models":null,"extra":null,"id":"regolo_ai","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":1,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-120B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-08-05","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":0.4,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-20b","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-20B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.1-8b-instruct","knowledge":null,"last_updated":"2025-04-07","lifecycle":null,"limits":{"context":120000,"output":120000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-04-07","retired":false,"tags":null},"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":0.6,"output":2.7},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"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":{"input":0.8,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":null,"last_updated":"2026-03-10","lifecycle":null,"limits":{"context":190000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax 2.5","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"mistral-small-4-119b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.75,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mistral-small-4-119b","knowledge":null,"last_updated":"2026-03-15","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4 119B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"mistral-small3.2":{"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":{"input":0.5,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mistral-small3.2","knowledge":null,"last_updated":"2025-01-31","lifecycle":null,"limits":{"context":120000,"output":120000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-01-31","retired":false,"tags":null},"qwen-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen-image","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Qwen-Image","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-coder-next","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-Next","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"qwen3-embedding-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen3-embedding-8b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding-8B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"qwen3-reranker-4b":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.12,"output":0.12},"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen3-reranker-4b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Reranker-4B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"qwen3.5-122b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.9,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.5-122b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-122B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","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":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.5-9b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-9B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null}},"name":"Regolo AI","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.regolo.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.regolo.ai/","env":["REGOLO_API_KEY"],"exclude_models":null,"extra":null,"id":"regolo_ai","models":{"apertus-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.46,"output":2.42},"deprecated":false,"extra":{"attachment":false,"description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","open_weights":true,"temperature":true},"family":null,"id":"apertus-70b","knowledge":"2025-09","last_updated":"2025-09-02","lifecycle":null,"limits":{"context":30000,"output":30000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Apertus 70B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-09-02","retired":false,"tags":null},"brick-complexity-pro":{"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":0.12,"output":0.46},"deprecated":false,"extra":{"attachment":true,"description":"Complexity classifier that powers the Brick semantic router by extracting query difficulty","open_weights":false,"temperature":true},"family":null,"id":"brick-complexity-pro","knowledge":null,"last_updated":"2026-02-06","lifecycle":null,"limits":{"context":100000,"output":15000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Brick Complexity Pro","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-06","retired":false,"tags":null},"brick-v1-beta":{"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":"Semantic router by Regolo.ai that directs each request to the most suitable model, optimizing costs and performance","family":"model-router","open_weights":false,"status":"beta","temperature":true},"family":null,"id":"brick-v1-beta","knowledge":null,"last_updated":"2026-02-06","lifecycle":null,"limits":{"context":100000,"output":15000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Brick v1 Beta","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-06","retired":false,"tags":null},"deepseek-ocr-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","open_weights":true},"family":null,"id":"deepseek-ocr-2","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":4000,"output":4000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek OCR 2","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"faster-whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","open_weights":true},"family":null,"id":"faster-whisper-large-v3","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":448,"output":4096},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Faster Whisper Large v3","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"gemma4-31b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.46,"output":2.42},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"gemma4-31b","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":100000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"glm5.2":{"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":{"input":2.31,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":96000,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"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":1,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-120B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-08-05","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":0.4,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-20b","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-20B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"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":0.6,"output":2.7},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"mistral-small-4-119b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.75,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"mistral-small-4-119b","knowledge":null,"last_updated":"2026-03-15","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4 119B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"qwen-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen-image","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Qwen-Image","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-coder-next","knowledge":null,"last_updated":"2026-03-01","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-Next","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-03-01","retired":false,"tags":null},"qwen3-embedding-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen3-embedding-8b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding-8B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"qwen3-reranker-4b":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.12,"output":0.12},"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen3-reranker-4b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Reranker-4B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"qwen3.5-122b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.9,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.5-122b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-122B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","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":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.5-9b","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-9B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-02-01","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":0.58,"output":2.42},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":120000,"output":120000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"regolo_ai","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null}},"name":"Regolo AI","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/requesty.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "requesty",
-  "claude-fable-5" | "claude-haiku-4-5" | "claude-haiku-4-5@eu" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-5@eu" | "claude-opus-4-6" | "claude-opus-4-6@eu" | "claude-opus-4-7" | "claude-opus-4-7@eu" | "claude-opus-4-8" | "claude-opus-4-8@eu" | "claude-opus-5" | "claude-opus-5@eu" | "claude-sonnet-4-5" | "claude-sonnet-4-5@eu" | "claude-sonnet-4-6" | "claude-sonnet-4-6@eu" | "claude-sonnet-4@eu" | "claude-sonnet-5" | "claude-sonnet-5@eu" | "deepseek-v4-flash-0731" | "deepseek-v4-flash-0731@eu" | "gemini-2.5-flash@eu" | "gemini-3.1-flash-lite@eu" | "gemini-3.5-flash-lite" | "gemini-3.5-flash@eu" | "gemini-3.6-flash" | "glm-5.2" | "glm-5.2@eu" | "gpt-4.1-mini@eu" | "gpt-4.1-nano@eu" | "gpt-4.1@eu" | "gpt-4o-mini@eu" | "gpt-5-mini@eu" | "gpt-5-nano@eu" | "gpt-5.1@eu" | "gpt-5.4@eu" | "gpt-5.5@eu" | "gpt-5.6-luna@eu" | "gpt-5.6-sol@eu" | "gpt-5.6-terra@eu" | "gpt-5@eu" | "grok-4.5" | "kimi-k3" | "kimi-k3@eu" | "o4-mini@eu"
+  "claude-fable-5" | "claude-haiku-4-5" | "claude-haiku-4-5@eu" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-5@eu" | "claude-opus-4-6" | "claude-opus-4-6@eu" | "claude-opus-4-7" | "claude-opus-4-7@eu" | "claude-opus-4-8" | "claude-opus-4-8@eu" | "claude-opus-5" | "claude-opus-5@eu" | "claude-sonnet-4-5" | "claude-sonnet-4-5@eu" | "claude-sonnet-4-6" | "claude-sonnet-4-6@eu" | "claude-sonnet-4@eu" | "claude-sonnet-5" | "claude-sonnet-5@eu" | "deepseek-v4-flash-0731" | "deepseek-v4-flash-0731@eu" | "gemini-2.5-flash@eu" | "gemini-3.1-flash-lite@eu" | "gemini-3.5-flash-lite" | "gemini-3.5-flash@eu" | "gemini-3.6-flash" | "gemini-3.7-flash" | "gemini-3.7-flash@eu" | "glm-5.2" | "glm-5.2@eu" | "gpt-4.1-mini@eu" | "gpt-4.1-nano@eu" | "gpt-4.1@eu" | "gpt-4o-mini@eu" | "gpt-5-mini@eu" | "gpt-5-nano@eu" | "gpt-5.1@eu" | "gpt-5.4@eu" | "gpt-5.5@eu" | "gpt-5.6-luna@eu" | "gpt-5.6-sol@eu" | "gpt-5.6-terra@eu" | "gpt-5@eu" | "grok-4.5" | "kimi-k3" | "kimi-k3@eu" | "o4-mini@eu"
 >;
 export default provider;

package/dist/providers/requesty.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://router.requesty.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://requesty.ai/solution/llm-routing/models","env":["REQUESTY_API_KEY"],"exclude_models":null,"extra":null,"id":"requesty","models":{"claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-haiku-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-haiku-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":1.375,"input":1.1,"output":5.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-haiku-4-5@eu","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) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-5@eu","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) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-6@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.88,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-6@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-7@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-7@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4-8@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8@eu","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-opus-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5@eu","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":4.125,"input":3.3,"output":16.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5@eu","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4-6@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":4.125,"input":3.3,"output":16.5},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4@eu","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4 (latest) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"claude-sonnet-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"cache_write":2.75,"input":2.2,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5@eu","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-v4-flash-0731@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731@eu","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"gemini-2.5-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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,"cache_write":0.55,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash@eu","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3.1-flash-lite@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.08333,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite@eu","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.5-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":1.583,"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash@eu","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":7},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2@eu","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-4.1-mini@eu":{"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":0.11,"input":0.44,"output":1.76},"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":"gpt-4.1-mini@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano@eu":{"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":0.0275,"input":0.11,"output":0.44},"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":"gpt-4.1-nano@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1@eu":{"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":0.55,"input":2.2,"output":8.8},"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":"gpt-4.1@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o-mini@eu":{"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":0.0825,"input":0.165,"output":0.66},"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":"gpt-4o-mini@eu","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5-mini@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0275,"input":0.275,"output":2.2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-mini@eu","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0055,"input":0.055,"output":0.44},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-nano@eu","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1375,"input":1.375,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.4@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5.6-luna@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":1.1,"output":6.6},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-luna@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":5.5,"output":33},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-sol@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":2.75,"output":16.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-terra@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1375,"input":1.375,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"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":0.225,"input":2.25,"output":11.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"kimi-k3@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.225,"input":2.25,"output":11.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3@eu","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"o4-mini@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3025,"input":1.21,"output":4.84},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"o4-mini@eu","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null}},"name":"Requesty","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://router.requesty.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://requesty.ai/solution/llm-routing/models","env":["REQUESTY_API_KEY"],"exclude_models":null,"extra":null,"id":"requesty","models":{"claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-haiku-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-haiku-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":1.375,"input":1.1,"output":5.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-haiku-4-5@eu","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) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-5@eu","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) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-6@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-6@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"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":"requesty","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-7@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-7@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4-8@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8@eu","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-opus-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"cache_write":6.875,"input":5.5,"output":27.5},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5@eu","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":4.125,"input":3.3,"output":16.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5@eu","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4-6@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":4.125,"input":3.3,"output":16.5},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4@eu","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4 (latest) (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"claude-sonnet-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"cache_write":2.75,"input":2.2,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5@eu","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-v4-flash-0731@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731@eu","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"gemini-2.5-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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,"cache_write":0.55,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash@eu","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3.1-flash-lite@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0275,"cache_write":0.091663,"input":0.275,"output":1.65},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite@eu","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.5-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.165,"cache_write":1.7413,"input":1.65,"output":9.9},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash@eu","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":7},"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":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.7-flash","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"gemini-3.7-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0825,"input":0.825,"output":4.125},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.7-flash@eu","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2@eu","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-4.1-mini@eu":{"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":0.11,"input":0.44,"output":1.76},"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":"gpt-4.1-mini@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano@eu":{"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":0.0275,"input":0.11,"output":0.44},"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":"gpt-4.1-nano@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1@eu":{"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":0.55,"input":2.2,"output":8.8},"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":"gpt-4.1@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o-mini@eu":{"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":0.0825,"input":0.165,"output":0.66},"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":"gpt-4o-mini@eu","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5-mini@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0275,"input":0.275,"output":2.2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-mini@eu","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0055,"input":0.055,"output":0.44},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-nano@eu","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1375,"input":1.375,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.4@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5.6-luna@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.022,"input":0.22,"output":1.32},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-luna@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":5.5,"output":33},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-sol@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"input":2.2,"output":13.2},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.6-terra@eu","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1375,"input":1.375,"output":11},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5@eu","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 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"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":0.225,"input":2.25,"output":11.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"kimi-k3@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.225,"input":2.25,"output":11.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3@eu","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3 (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"o4-mini@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3025,"input":1.21,"output":4.84},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"o4-mini@eu","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini (EU)","pricing":null,"provider":"requesty","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null}},"name":"Requesty","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;