Skip to content

Pareto 26.10

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Pricing

Input
$0.84per 1M tokens
Output
$3.36per 1M tokens
Cache read
$0.0315per 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": { "unbiased/pareto-26.10": { "limit": { "context": 1048576, "output": 131072 } } }
    }
  }
}
OpenCode, set up for Pareto 26.10