Skip to content

Beam 1.0 501B A23B

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

Pricing

Input
$0.315per 1M tokens
Output
$1.05per 1M tokens
Cache read
$0.042per 1M tokens
Max output
943,718tokens

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": { "reflection/beam-1.0-501b-a23b": { "limit": { "context": 1048576, "output": 943718 } } }
    }
  }
}
OpenCode, set up for Beam 1.0 501B A23B

Find us on