All models
Mistral AIFast·Open weights: Apache 2.0Available

Mistral Small 3.2

mistralai/mistral-small-3.2

License: Apache 2.0

Compact, fast, understands images

visiontoolsfast
Try in chat Get API key
Input
7.9 pts
per 1M tokens
Output
21 pts
per 1M tokens
Typical reply
≈ 0.018 pts
1k tokens in, 500 out
Context
128K
Context
Speed
130 tok/s
*
Time to first token
0.4 s
*

* Speed and latency are approximate.

How charges are rounded: each request is charged for the tokens it actually processes at the model's listed price, converted at 100 Points = USD 1 and rounded up to the nearest 0.0001 Point. Prices on this page are rounded for display.

How to use

Use the model ID in the model field of any OpenAI-compatible request.

curl https://taldermont.com/v1/chat/completions \
  -H "Authorization: Bearer sk-taldermont-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-small-3.2",
    "messages": [{"role": "user", "content": "Hello! What can you do?"}]
  }'

Replace sk-taldermont-YOUR_KEY with your key from the API keys page.

Similar models

  • Alibaba · Fast

    Qwen3 Coder

    Open model for agents in your IDE

    32 pts/ 105 pts

    Input / 1M · Output / 1M

    Context 256K140 tok/s

  • Meta · Fast

    Llama 4 Scout

    Long context and image input

    11 pts/ 32 pts

    Input / 1M · Output / 1M

    Context 320K150 tok/s

  • Meta · Fast

    Llama 3.3 70B

    Reliable workhorse for chat and RAG

    11 pts/ 34 pts

    Input / 1M · Output / 1M

    Context 128K120 tok/s