How much does Beam 1.0 501B A23B cost?

Beam 1.0 501B A23B costs $0.25/M input tokens and $1.00/M output tokens, with separate rates for Cache Read at $0.05/M tokens.

What is the context length of Beam 1.0 501B A23B?

Beam 1.0 501B A23B has a 1,048,576 token context window. It supports up to 131,072 completion tokens.

Does Beam 1.0 501B A23B support tool calling and structured outputs?

Yes. Beam 1.0 501B A23B accepts tools and tool_choice for function calling on 4 of the 5 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Which providers serve Beam 1.0 501B A23B?

Beam 1.0 501B A23B is served by 5 providers on OpenRouter: Nebius Token Factory, CoreWeave, DigitalOcean, Baseten, and Together. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Beam 1.0 501B A23B released?

Beam 1.0 501B A23B was released on October 16, 2026. Its knowledge cutoff is June 30, 2026.

Reflection: Beam 1.0 501B A23B

reflection/beam-1.0-501b-a23b

Model weights

Compare

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 1M-token context window.

Beam targets software engineering, multi-step tool use, and mathematical and scientific reasoning, with an emphasis on token efficiency. It takes text input and produces text output, supports configurable reasoning effort, function calling and structured outputs, and is released under Apache 2.0.

Modalities

In / out price

$0.25 / $1per 1M

Context

1.0M

Released

Oct 16, 2026

Knowledge cutoff

Jun 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


$0.30	$1.00	$0.04	0.35s	172 tok/s	100.00%
$0.25	$1.00	$0.05	0.77s	177 tok/s	100.00%
$0.40	$1.20	$0.04	0.32s	210 tok/s	99.79%
$0.40	$1.20	$0.04	0.18s	406 tok/s	100.00%
$0.40	$1.20	$0.04	0.55s	158 tok/s	99.40%

Input $0.30Output $1.00
172 tok/s100.00% uptime
Input $0.25Output $1.00
177 tok/s100.00% uptime
Input $0.40Output $1.20
210 tok/s99.79% uptime
Input $0.40Output $1.20
406 tok/s100.00% uptime
Input $0.40Output $1.20
158 tok/s99.40% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.06904/M tokens

Output

$1.033/M tokens

Beam 1.0 501B A23B — Price history

Price history

No effective price data for this selection

$0.0613	$1.20	94.1%	3.5%
$0.0648	$1.20	93.1%	7.3%
$0.0679	$1.00	91.0%	66.5%
$0.0733	$1.00	87.2%	21.4%
$0.1130	$1.20	79.7%	1.2%

Effective in $0.0613Effective out $1.20
Token share
3.5%
Effective in $0.0648Effective out $1.20
Token share
7.3%
Effective in $0.0679Effective out $1.00
Token share
66.5%
Effective in $0.0733Effective out $1.00
Token share
21.4%
Effective in $0.1130Effective out $1.20
Token share
1.2%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

406tok/s

P50, best across providers

Latency

0.18s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchNebius Token Factory90.0%--DigitalOcean89.4%--CoreWeave89.3%--Baseten89.3%--Together88.6%--

+2 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.94%

Availability over the last 3 days

Last 72 hours

Availability 99.94%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.83%

Without Routing

99.37%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Reflection: Beam 1.0 501B A23B (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Beam 1.0 Intelligence Index	17.7
Artificial Analysis	Beam 1.0 HLE	34.7%
Artificial Analysis	Beam 1.0 AA-LCR	78.0%
Artificial Analysis	Beam 1.0 GDPval-AA	33.9%
Artificial Analysis	Beam 1.0 CritPt	13.1%
Artificial Analysis	Beam 1.0 SciCode	48.5%
Artificial Analysis	Beam 1.0 Terminal-Bench 4.0	3.0%
Artificial Analysis	Beam 1.0 AA-Omniscience Accuracy	30.7%
Artificial Analysis	Beam 1.0 AA-Omniscience Non-Hallucination Rate	59.0%
Design Arena	Beam 1.0 (max) Models Arena 3D Elo	1116
Design Arena	Beam 1.0 (max) Models Arena Code Categories Elo	1223
Design Arena	Beam 1.0 (max) Models Arena Game Development Elo	1185
Design Arena	Beam 1.0 (max) Models Arena UI Component Elo	1260
Design Arena	Beam 1.0 (max) Models Arena Website Elo	1239
Vals AI	Beam 1.0 BioMysteryBench	42.6%
Vals AI	Beam 1.0 Code Migration v1.1	22.8%
Vals AI	Beam 1.0 EMB v1.1	64.7%
Vals AI	Beam 1.0 Finance Agent v2.1	51.8%
Vals AI	Beam 1.0 Vals Finance Index	46.5%
Vals AI	Beam 1.0 HLAB-Vals-1.1	4.6%
Vals AI	Beam 1.0 IOI	22.8%
Vals AI	Beam 1.0 Vals Legal Index	61.8%
Vals AI	Beam 1.0 Legal Research Bench	28.8%
Vals AI	Beam 1.0 MysteryMechanism	22.1%
Vals AI	Beam 1.0 ProofBench v1.1	18.0%
Vals AI	Beam 1.0 Vals Science Index	22.0%
Vals AI	Beam 1.0 Tax Agent Bench	8.8%
Vals AI	Beam 1.0 Terminal-Bench 4.0	4.0%
Vals AI	Beam 1.0 Terminal-Bench-Science	1.4%
Vals AI	Beam 1.0 Vals Index	43.4%
Vals AI	Beam 1.0 Vibe Code Bench v1.1	66.4%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Codex

A coding agent that helps you build and ship with AI

10.2Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

3.78Btokens

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

2.4Btokens

Portkey AI

Control panel for AI apps

2.34Btokens

There are many coding agents, but this one is yours.

852Mtokens

Rest of OpenRouter

500M

Top 5 Apps

52.3M

Not currently available through EU in-region routing. In-region routing docs

Reflection: Beam 1.0 501B A23B

Providers