From 9c86dc62e69b018cf80599582dfa4029d39127e1 Mon Sep 17 00:00:00 2001 From: Thibault Jaigu Date: Thu, 24 Sep 2026 21:53:59 +0100 Subject: [PATCH] docs: add Requesty to the provider docs and README --- README.md | 2 +- docs/docs/configure/providers.md | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 313cac85b..9c4d57b7e 100644 --- a/README.md +++ b/README.md @@ -203,7 +203,7 @@ First-class support with schema indexing, query execution, and metadata introspe Model-agnostic — bring your own provider or run locally. -Altimate LLM Gateway · Anthropic · OpenAI · Google Gemini · Google Vertex AI · Amazon Bedrock · Azure OpenAI · Databricks AI Gateway · Snowflake Cortex · Mistral · Groq · DeepInfra · Cerebras · Cohere · Together AI · Perplexity · xAI · OpenRouter · LM Studio · Ollama · GitHub Copilot +Altimate LLM Gateway · Anthropic · OpenAI · Google Gemini · Google Vertex AI · Amazon Bedrock · Azure OpenAI · Databricks AI Gateway · Snowflake Cortex · Mistral · Groq · DeepInfra · Cerebras · Cohere · Together AI · Perplexity · xAI · OpenRouter · Requesty · LM Studio · Ollama · GitHub Copilot ## Skills diff --git a/docs/docs/configure/providers.md b/docs/docs/configure/providers.md index 38ee4c2dd..4937490a6 100644 --- a/docs/docs/configure/providers.md +++ b/docs/docs/configure/providers.md @@ -340,6 +340,29 @@ Run local models through [LM Studio](https://lmstudio.ai)'s OpenAI-compatible se Access 150+ models through a single API key. +## Requesty + +```json +{ + "provider": { + "requesty": { + "options": { + "apiKey": "{env:REQUESTY_API_KEY}" + }, + "models": { + "openai/gpt-4o-mini": { + "name": "GPT-4o mini", + "limit": { "context": 128000, "output": 16384 } + } + } + } + }, + "model": "requesty/openai/gpt-4o-mini" +} +``` + +[Requesty](https://docs.requesty.ai) is an OpenAI-compatible router. It is already in the models.dev catalog, so `/connect` or `altimate-code auth login` lists it, and setting `REQUESTY_API_KEY` is enough to use its catalog models (for example `requesty/gpt-5.4-mini`) with no config. Any other `vendor/model` id from Requesty's `/v1/models` can be added under `models` as shown above. Get a key at [app.requesty.ai/api-keys](https://app.requesty.ai/api-keys). + ## Copilot ```json