Mistral AI/pixtral-12b/Released Sep 2024

Pixtral 12B

Vision-language model, 128K context

Text

About Pixtral 12B

Pixtral 12B is a Multimodal LLM that excels in handling both images and text, supporting tasks like image captioning, visual question answering, and document analysis. It maintains strong performance in text-only tasks as well.

MetricValue
Parameter Count12 billion
Mixture of ExpertsNo
Context Length128,000 tokens
MultilingualYes
Quantized*No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Ready to build with Pixtral 12B?

Try Pixtral 12B in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "pixtral-12b",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'

API endpoint

See the API reference for request and response formats.

POSThttps://hub.oxen.ai/api/ai/chat/completions