tokenstat
tokenstat

Beam 1.0 501B A23B

together_ai/reflection/Beam-1.0-501B-A23B · rates as of · How this catalog is built · Benchmarks

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$1
$/MTok
Context
1.0M
tokens
Sources
3
8 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ higherOutput $0.98 → $1
  • ↑ higherInput $0.24 → $0.25
  • ↓ lowerOutput $1 → $0.98
  • ↓ lowerInput $0.25 → $0.24

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (2 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestreflection/beam-1.0-501b-a23bKilo Gateway$0.25$1$0.051.0M
OpenRouterreflection/beam-1.0-501b-a23bOpenRouter$0.25$1$0.051.0M
models.devreflection/Beam-1.0-501B-A23BCoreWeave$0.3$1$0.041.0M
models.devtogether_ai/reflection/Beam-1.0-501B-A23BEden AI$0.4$1.20$0.041.0M
models.devreflection/Beam-1.0-501B-A23BTogether AI$0.4$1.20$0.041.0M
LiteLLMBeam-1.0-501B-A23BN/A$0.4$1.20$0.04N/A
LiteLLMreflection/Beam-1.0-501B-A23BN/A$0.4$1.20$0.04N/A
LiteLLMwandb/reflection/Beam-1.0-501B-A23BN/A$1$3$0.1N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2026-06-30Released: 2026-10-05Output limit: 131K tokensFamily: beam

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.