MISTRAL API
Mistral models, zero setup.
Run Mistral models through a single OpenAI-compatible endpoint. From lightweight instruction-following to powerful code generation, Mistral models deliver strong performance at competitive token costs. Same API format as OpenAI, same SDK, different model parameter.
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",
)
response = client.chat.completions.create(
model="mistralai/Mistral-Small-24B-Instruct-2501",
messages=[
{"role": "user", "content": "Write a Python function to merge two sorted lists."}
],
)
print(response.choices[0].message.content)AVAILABLE MODELS
Models you can use today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| mistralai/Mistral-Small-24B-Instruct-2501 | Mistral | Per-token | 24B params, strong instruction following |
| mistralai/Voxtral-Small | Mistral | Per-minute | Audio transcription, multilingual |
WHY RUNCRATE
Built for production.
Efficient Architecture
Mistral models use sliding-window attention and grouped-query attention for fast inference at lower memory footprint, translating to lower per-token costs.
Strong Code Generation
Mistral excels at code generation, bug fixing, and code review tasks. Competitive with much larger models on coding benchmarks.
Multilingual
Solid performance across English, French, German, Spanish, Italian, and many more languages for global applications.
Instruction Following
Instruct-tuned variants follow complex instructions precisely, making them reliable for structured outputs, JSON generation, and tool use.
FAQ