Beam 1.0 501B A23B

Reflection · On OpenRouter since October 16, 2026 · Pinned version id: reflection/beam-1.0-501b-a23b-20261016

Price

$0.60

mixed / 1M tokens

Mixed price per 1M tokens: 3 input tokens to 1 output token.

in $0.40 · out $1.20 · Cached input $0.04

via DigitalOcean

Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.

US dollars per million tokens, converted to your currency at the NBP rate.

Tasks, with the evidence

Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.

Writing code

Measured by a third party

Code: 1,216 · Rank 56 of 122, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.26

Hard questions and reasoning

Measured by a third party

Intelligence Index: 17.7 · Rank 47 of 66, among scored models · Artificial Analysis, read November 21, 2026

Cost of this job: $0.11

Models that score at least as high for less in this scenario: 14

Websites and apps

Measured by a third party

Websites: 1,232 · Rank 53 of 127, among scored models · Design Arena, read November 21, 2026

UI components: 1,267 · Rank 34 of 118, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.13

Models that score at least as high for less in this scenario: 6

Games and 3D

Measured by a third party

Game development: 1,180 · Rank 60 of 121, among scored models · Design Arena, read November 21, 2026

3D scenes: 1,109 · Rank 72 of 114, among scored models · Design Arena, read November 21, 2026

Cost of this job: $0.13

Models that score at least as high for less in this scenario: 7

Long documents

Declared, not measured

Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.

Cost of this job: $0.49

The size of each job is our assumption; the prices are real.

  • Writing code: Requests: 40. Input tokens per request: 30,000. Output tokens per request: 1,500. Share of input served from cache: 70%.
  • Hard questions and reasoning: Requests: 10. Input tokens per request: 3,000. Output tokens per request: 8,000. Share of input served from cache: 0%.
  • Websites and apps; Games and 3D: Requests: 8. Input tokens per request: 12,000. Output tokens per request: 10,000. Share of input served from cache: 30%.
  • Long documents: Requests: 3. Input tokens per request: 400,000. Output tokens per request: 4,000. Share of input served from cache: 0%.

Thinking is billed as output tokens; a model that thinks longer costs more than this estimate. Ranks are among all models we list, including older ones.

Cheaper models with a similar benchmark score

Rule: an Intelligence Index of at least 14.7, a mixed price at least 25% lower, at least the same input types, and tool support. Lower mixed price (3 input tokens to 1 output token); check the flags and your own prompt sizes.

  1. Ling 3.1 Flash inclusionAI 85% cheaper $0.09 · Index 29.6 (this model: 17.7) Differences to check: No structured output Compare
  2. Inkling 2 Mini Thinking Machines 74% cheaper $0.1588 · Index 20.1 (this model: 17.7) Compare
  3. MiMo-V2.6-Flash Xiaomi 71% cheaper $0.175 · Index 26.7 (this model: 17.7) Compare
  4. Claude Haiku 5.5 Anthropic 67% cheaper $0.20 · Index 36.5 (this model: 17.7) Differences to check: Price rises for long prompts Compare
  5. Muse Ember Meta 67% cheaper $0.20 · Index 36.0 (this model: 17.7) Compare
Show more: 5
  1. GPT-6 Luna OpenAI 67% cheaper $0.20 · Index 27.9 (this model: 17.7) Differences to check: Price rises for long prompts Compare
  2. Qwen3.8 Flash Qwen 62% cheaper $0.23 · Index 28.6 (this model: 17.7) Compare
  3. GLM 5.3 Flash Z.ai 60% cheaper $0.2375 · Index 27.8 (this model: 17.7) Compare
  4. MiniMax M3.1 Flash MiniMax 56% cheaper $0.2625 · Index 29.1 (this model: 17.7) Compare
  5. GPT-5.6 Luna OpenAI 25% cheaper $0.45 · Index 23.8 (this model: 17.7) Differences to check: Price rises for long prompts Compare

Price by provider

The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.

ProviderInputOutputCached inputMixedNotes
Nebius $0.25$1.00 $0.05 $0.4375 27% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
CoreWeave $0.30$1.00 $0.04 $0.475 21% cheaper nvfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
BaseTen $0.40$1.20 $0.04 $0.60 fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
DigitalOcean Price used here $0.40$1.20 $0.04 $0.60
Together $0.40$1.20 $0.04 $0.60

Specifications

Context window
1M
Max output
131k
Accepts
text
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Always on
Thinking effort levels: low, medium, high, xhigh, and max
Weights on Hugging Face
Hugging Face A Hugging Face repository is linked. We did not check the licence; read it before you build on it.
Knowledge cutoff
June 30, 2026
On OpenRouter since
October 16, 2026
Price check
one source

As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.

Benchmark scores

Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.

SourceScoreRank among scored
Intelligence Index
Artificial Analysis, read November 21, 2026
17.7Rank 47 of 66, among scored models
Websites
Design Arena, read November 21, 2026
1,232Rank 53 of 127, among scored models
UI components
Design Arena, read November 21, 2026
1,267Rank 34 of 118, among scored models
Game development
Design Arena, read November 21, 2026
1,180Rank 60 of 121, among scored models
3D scenes
Design Arena, read November 21, 2026
1,109Rank 72 of 114, among scored models
Code
Design Arena, read November 21, 2026
1,216Rank 56 of 122, among scored models
agents/pdf
Design Arena, read November 21, 2026
1,182Rating 1,182; rank 27 at the source. Too few scored models for a tier.

Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.

Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab

Sources and dates

Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.