Description
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Mistral: Mixtral 8x22B Instruct (mistralai/mixtral-8x22b-instruct)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "mistralai/mixtral-8x22b-instruct",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Mistral: Mixtral 8x22B Instruct model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 2$ / 1M tokens
- Output: 6$ / 1M tokens
Token Limits
- Max Output: 65,536 tokens
- Max Context: 65,536 tokens
Subscription Tiers
- free
- pro
- ultimate