Reflection

Beam 1.0 501B A23B

Launched 2026-10-05 · Knowledge up to 2026-06-30 · Listed on OpenRouter 2026-10-16

Prices updated . Benchmarks updated .

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...

You send / 1M

$0.300

tokens in

It replies / 1M

$1.00

tokens out

Context

1.05M

tokens it can read at once

Typical request

$0.0009

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Arena Elo (text)1,425Independent2026-10-28LMArena
Arena Elo (webdev)1,436Independent2026-10-28LMArena

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
CoreWeave · nvfp4$0.300$1.00100%Read
Nebius · fp4$0.250$1.00100%Read
DigitalOcean$0.400$1.20100%Read
BaseTen · fp4$0.400$1.20100%Read
Together$0.400$1.20100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 131K tokens
  • Repeated text is billed at $0.040 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with Beam 1.0 501B A23B

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.