CHAT COMPLETIONS API
One API, every chat model.
Access chat models from every major open-source provider through a single endpoint. DeepSeek, Llama, Qwen, Gemma, Mistral, and more. Standard OpenAI chat completions format with streaming, function calling, and JSON mode. Switch models with a single parameter change.
QUICK START
Integrate in minutes.
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
# Switch models by changing one parameter
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3", # or any of 200+ models
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What are the best practices for API design?"}
],
stream=True,
)
for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")AVAILABLE MODELS
Models you can use today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| deepseek-ai/DeepSeek-V3 | DeepSeek | Per-token | 128K context, MoE |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | Meta | Per-token | 17B MoE, 128K context |
| Qwen/Qwen3-32B | Alibaba | Per-token | 32B, strong multilingual |
| google/gemma-3-27b-it | Per-token | 27B, instruction-tuned | |
| mistralai/Mistral-Small-24B-Instruct-2501 | Mistral | Per-token | 24B, fast inference |
WHY RUNCRATE
Built for production.
Streaming Support
Server-sent events for real-time token streaming. Build responsive chat interfaces with time-to-first-token under 200ms.
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, one billing account, every provider. Compare models side by side and switch without re-integrating.
FAQ