Skip to content

Granite 4.2 8B

Granite 4.2 8B is a dense reasoning model from IBM.

Per 1M tokens
$0.063 · $0.2625
Context
131Ktokens
Supports
  • Calls tools
  • Thinks before it answers
opencode.json
{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "ibm-granite/granite-4.2-8b": { "limit": { "context": 131072, "output": 117964 } } }
    }
  }
}
Needs an API keyGet one

Pricing and limits

  • Cache read$0.0158per 1M tokens
  • Max output117,964tokens

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