token.app › Reflection › Beam 1.0 501B A23B

Beam 1.0 501B A23B pricing & benchmarks

Beam 1.0 501B A23B is available from Reflection at $0.250 per million input tokens and $1.00 per million output tokens ($0.438 blended at 3:1). It accepts up to 1,048,576 tokens of context. 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...

Pricing
Per million tokens · OpenRouter
Input$0.250
Output$1.00
Blended (3:1)$0.438
Specification
reflection/beam-1.0-501b-a23b
Context window1.0M
Max output131K
ReleasedOct 2026
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Beam 1.0 501B A23B yet. We show nothing rather than reprinting an unverified figure.
Where to run Beam 1.0 501B A23B
4 hosts · 1.4× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
Nebius $0.438 $0.250 / $1.00 1.0M fp8 100.0%
CoreWeave $0.475 $0.300 / $1.00 1.0M fp4 100.0%
BaseTen $0.600 $0.400 / $1.20 1.0M fp4 100.0%
Together $0.600 $0.400 / $1.20 1.0M — 100.0%
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Beam 1.0 501B A23B
Beam 1.0 501B A23B vs Gemini 3.7 Flash Beam 1.0 501B A23B vs Grok 4.6 Beam 1.0 501B A23B vs DeepSeek V4 Flash 0731 Beam 1.0 501B A23B vs Inkling Small Beam 1.0 501B A23B vs Qwen3.7 Flash Beam 1.0 501B A23B vs Claude Opus 5 Beam 1.0 501B A23B vs Gemini 3.6 Flash Beam 1.0 501B A23B vs Gemini 3.5 Flash Lite
FAQ
How much does Beam 1.0 501B A23B cost?
Beam 1.0 501B A23B costs $0.250 per million input tokens and $1.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.438 per million tokens.
What is Beam 1.0 501B A23B's context window?
Beam 1.0 501B A23B accepts up to 1,048,576 tokens of context, and can generate up to 131,072 output tokens.