APIs, MCP servers and models to chat with an LLM
15 tools in the catalog do this, by name.
Amazon BedrockProviderAWS service for calling 100+ foundation models through one API
AnthropicModelAPI for the Claude family of language models
CohereModelAPI for Command, Embed and Rerank models for enterprise search and agents
DeepSeekModelAPI for DeepSeek's V4 reasoning and chat models
Fireworks AIProviderInference, fine-tuning and dedicated GPU deployments for open models
Google GeminiModelGoogle's Gemini model API for text, images, audio and video
GroqProviderLow-latency inference API for open LLMs and Whisper
Hugging Face InferenceProviderOne API for open models served by many inference providers
Mistral AIModelAPI for Mistral's open-weight and commercial language models
OllamaPackageRun open models on your own machine behind a local REST API
OpenAIModelAPI for GPT language, image and audio models
OpenRouterModelOne API for hundreds of models across many providers
Together AIProviderServerless and dedicated inference, fine-tuning and GPUs for open models
Vercel AI GatewayProviderGateway that routes model requests across providers with fallbacks
xAIModelAPI for xAI's Grok models for text, code, images, video and voice