Home / Providers

Providers

10 providers tracked. Probed every 5 minutes.

→ Groq

The fastest LLM inference on the planet (LPU)

… 4 models OpenAI-compatible
→ Google AI Studio (Gemini)

Free Gemini API access — 1M-token context, multimodal

… 4 models OpenAI-compatible
→ OpenRouter

One API, 300+ models — including many free ones

… 4 models OpenAI-compatible
→ Together AI

Wide open-source model catalog with serverless + dedicated

… 4 models OpenAI-compatible
→ Cerebras Inference

Wafer-scale chips → fastest open-model inference (often >2,000 tok/s)

… 3 models OpenAI-compatible
→ Mistral La Plateforme

EU-based; Mistral Small / Codestral with experimental free tier

… 5 models Custom SDK
→ Cohere

Trial keys for Command R+, Embed, Rerank — RAG-friendly

… 4 models Custom SDK
→ Hugging Face Inference

300k+ open-source models, free serverless inference

… 4 models OpenAI-compatible
→ GitHub Models

Free GPT-4o, Llama, Mistral via your GitHub PAT

… 5 models OpenAI-compatible
→ SambaNova Cloud

RDU-accelerated Llama 3 with very high tok/s

… 4 models OpenAI-compatible