Using Beam on OpenRouter

Implementation guide · Beam · Reflection AI

Serverless
Open Source

OpenRouter exposes Beam through model ID reflection/beam-1.0-501b-a23b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at OpenRouter and generate an API key.
  2. 2
    Use the OpenRouter SDK or REST API to call reflection/beam-1.0-501b-a23b — see the documentation for request format.
  3. 3
    You'll be billed $1.00/1M input, $3.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See OpenRouter documentation for integration details.

Pricing on OpenRouter

TypePrice (per 1M)
Input tokens$1.00
Output tokens$3.00

Capabilities

ReasoningJSON / Tool useStructured Outputs

About Beam

Beam is an open-weight sparse mixture-of-experts language model with 501B total and 23B active parameters, built for coding, reasoning, and long-horizon agentic work and trained from scratch. It is text-only, with a 1M-token context window, up to 128K output tokens, five reasoning effort levels (low to max, default medium), tool calling, and structured outputs, and a June 30, 2026 knowledge cutoff.

Full model details →

Model Specs

Released2026-10-05
Parameters501B (23B activated)
Context1M
ArchitectureMixture of Experts
Knowledge cutoff2026-06

Also available on(1)

Vercel AI Gateway$1.30/1M
Compare all providers →

Provider

OpenRouter

OpenRouter, Inc.

New York, NY, USA