Skip to content

Mistral Large 4

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

Pricing

Input
$0.714per 1M tokens
Output
$2.19per 1M tokens
Cache read
$0.0735per 1M tokens
Max output
262,144tokens

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

opencode.json

{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "mistralai/mistral-large-4-0": { "limit": { "context": 1048576, "output": 262144 } } }
    }
  }
}
OpenCode, set up for Mistral Large 4

Find us on