Skip to content

Mistral Small 3

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

Per 1M tokens
$0.0525 · $0.084
Context
33Ktokens
opencode.json
{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "mistralai/mistral-small-24b-instruct-2501": { "limit": { "context": 32768, "output": 16384 } } }
    }
  }
}
Needs an API keyGet one

Pricing and limits

  • Max output16,384tokens

OpenRouter's price plus OpenRouter's 5% platform fee. Deference adds no markup.