Skip to content

Grok 4.5

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Per 1M tokens
$2.10 · $6.30
Context
500Ktokens
Supports
  • Reads images
  • 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": { "x-ai/grok-4.5": { "limit": { "context": 500000, "output": 450000 } } }
    }
  }
}
Needs an API keyGet one

Pricing and limits

  • Cache read$0.315per 1M tokens
  • Max output450,000tokens

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