Last refreshed 2026-10-19. Next refresh: weekly.
Why use Beam on OpenRouter?
OpenRouter offers Beam with pay-as-you-go pricing at $1.00/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.
Compare Beam across 2 providers to find the best fit for your use caseInput / 1M
$1.00
Output / 1M
$3.00
Cache
read $0.10
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: reflection/beam-1.0-501b-a23bModel ID
reflection/beam-1.0-501b-a23bRequest example
Curated snippets for this provider are not sourced yet. Use OpenRouter documentation with model ID
reflection/beam-1.0-501b-a23b.Gotchas
- Use provider model ID "reflection/beam-1.0-501b-a23b", not the LLMReference slug "beam".
Compare Beam Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Vercel AI Gateway | $1.30 | $4.30 |
| OpenRouter | $1.00 | $3.00 |
Pricing
| Type | Price (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.
Get Started
Model Specs
Released2026-10-05
Parameters501B (23B activated)
Context1M
ArchitectureMixture of Experts
Knowledge cutoff2026-06