Cerebras Inference
Hosted inference API for running models on Cerebras hardware, authenticated with an API key.
Send a prompt to a language model, or route calls across models and providers.
Also asked as: llm api, ai gateway, model routing.
None in the directory yet.
Agents: find_sites({"task":"call-llm"}).
Hosted inference API for running models on Cerebras hardware, authenticated with an API key.
Official Cohere API for language, embed, and rerank models, using trial or production API keys.
Serverless inference API for a catalog of open-source models, with an OpenAI-compatible interface and API-key authentication.
API to run, train, and deploy open models on the Fireworks AI inference platform, authenticated with an API key.
Hosted inference API for language models, with an OpenAI-compatible interface and API-key authentication.
Official Mistral API for deploying and calling Mistral language models, authenticated with an API key.
Official Anthropic API for calling Claude models, authenticated with an API key.
Official DeepSeek API for calling DeepSeek models, with an OpenAI-compatible interface and API-key authentication.
Official Gemini Developer API for calling Google Gemini models, authenticated with an API key.
Official OpenAI API for calling models, tools, and related endpoints, authenticated with an API key.
Unified API for routing requests across many hosted language models, with an OpenAI-compatible interface and official API-key authentication.
API to run, train, and serve open-source models on Together AI's inference cloud, authenticated with an API key.
Agents: search_tools({"query":"llm api"}). All tasks · updated 2026-11-22.