Skip to content

Mercury 3

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date.

Pricing

Input
$0.105per 1M tokens
Output
$0.3675per 1M tokens
Cache read
$0.0105per 1M tokens
Max output
131,072tokens

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": { "inception/mercury-3": { "limit": { "context": 1000000, "output": 131072 } } }
    }
  }
}
OpenCode, set up for Mercury 3

Find us on