Skip to content
Alpha
  • Models
  • Rankings
  • Ori
ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for reflection

Reflection

Access 1 Reflection model through the OpenRouter unified API including Beam 1.0 501B A23B. Compare pricing, context windows, benchmarks, and capabilities between different Reflection models.

Reflection tokens processed on OpenRouter

  • Favicon for reflection
    Reflection: Beam 1.0 501B A23BBeam 1.0 501B A23B
    127M tokens

    Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a 1M-token context window. Beam targets software engineering, multi-step tool use, and mathematical and scientific reasoning, with an emphasis on token efficiency. It takes text input and produces text output, supports configurable reasoning effort, function calling and structured outputs, and is released under Apache 2.0.

    by reflectionOct 16, 20261.05M context$0.25/M input tokens$1/M output tokens

Frequently asked questions

OpenRouter serves 1 Reflection model behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as reflection/beam-1.0-501b-a23b. The quickstart has request examples for every supported SDK.

Beam 1.0 501B A23B has the largest context window of any Reflection model on OpenRouter, accepting up to 1,048,576 tokens per request.

Beam 1.0 501B A23B is the most recently added Reflection model on OpenRouter, listed on October 16, 2026.