CHAT COMPLETIONS API
One API, every chat model.
Switch chat models by changing one parameter. DeepSeek, Llama, Qwen, Gemma and Mistral behind one OpenAI-compatible endpoint, with streaming, function calling and JSON mode.
Hand this to your agent
Add a Runcrate model to this project: run curl -fsSL"https://runcrate.ai/agents.md?intent=build"and follow it.
Your agent asks for an API key. Create a key
Quick start
Hand it to your agent. Or read the request it sends.
Your agent writes and runs it. The same key works for every model and every GPU.
Available models
Models you can call today. Billed prices, as charged.
| Model | Maker | Price | Detail |
|---|---|---|---|
| meta-llama/Llama-4-Scout-17B-16E-Instruct | Meta | $0.105 in, $0.315 out per 1M tokens | 17B MoE, 128K context |
| google/gemma-3-27b-it | $0.084 in, $0.168 out per 1M tokens | 27B, instruction-tuned |
Why Runcrate
Built for production. One key, one balance.
Streaming support
Server-sent events for real-time token streaming. Build chat interfaces that render tokens as they arrive.
Function calling
Standard OpenAI tools format for structured function calls. Build AI agents that interact with your APIs and databases.
JSON mode
Force structured JSON output from any model. Reliable for data extraction, form filling, and API integrations.
Multi-provider
One API key and one balance across many model makers. Compare models side by side and switch without re-integrating.
FAQ