Magistral Medium (latest)

Model details

← Back

Magistral Medium (latest)

Model
magistral-medium-latest
Provider
mistral
API
mistral-conversations
Base URL
https://api.mistral.ai
Input
text
Reasoning
Yes
Context window
128,000
Max tokens
16,384
Cost / million input
$2
Cost / million output
$5
Cost / million cache read
$0
Cost / million cache write
$0

Also available from other providers

No obvious cross-provider matches found.

Model config JSON
{
  "providers": {
    "mistral": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "magistral-medium-latest",
          "name": "Magistral Medium (latest)",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 128000,
          "maxTokens": 16384,
          "cost": {
            "input": 2,
            "output": 5,
            "cacheRead": 0,
            "cacheWrite": 0
          }
        }
      ],
      "api": "mistral-conversations",
      "baseUrl": "https://api.mistral.ai"
    }
  }
}