Reflection: Beam 1.0 501B A23B

reflection · Released Oct 16, 2026
DFO score #283 / 753
12.9 leaderboard score
Speed
471 tok/s · best OpenRouter provider
Input Price #427 / 753
$0.300 per 1M tokens
Output Price #409 / 753
$1.00 per 1M tokens
Context #39 / 753
1M tokens

Analysis Summary

Beam 1.0 501B A23B is a text-only mixture-of-experts model from Reflection, with 501B total parameters and 23B active per token. It supports tool use and function calling and provides a 1M token context. Pricing is $0.30 per million input tokens and $1.00 per million output tokens.

The large context and modest price make it a plausible option for long-document analysis and tool-driven automation. No independent results on reasoning, coding, or agentic behaviour have been published yet, so its quality relative to other value-tier models is unknown. It has no vision input.

Run it through internal evaluations on representative prompts before assigning it any client work. It is a candidate to watch, not yet a model we would deploy.

Assessed November 15, 2026

Editorial notes

Beam 1.0 from Reflection is a 501B parameter model with 23B active, a 1M token context, and tool calling at low pricing. Independent benchmark results have not been published yet.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

Beam 1.0 from Reflection is a 501B parameter model with 23B active, a 1M token context, and tool calling at low pricing. Independent benchmark results have not been published yet.

#283 of 753 overall Up 479 this week

Benchmarks

Intelligence Index Not tested Artificial Analysis
Coding Index Not tested Artificial Analysis
Agentic Index Not tested Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following 1,439 #26 of 35 · Arena rating

Artificial Analysis data refreshed Nov 17, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control.

How Reflection: Beam 1.0 501B A23B compares

Its 1M-token context window is larger than 95% of the models we list. At $0.30 per million input tokens it is cheaper than 43% of comparable models.

Position in the field
DFO score: ahead of 63% of models #282
Price: cheaper than 43% of models #427
Context: larger than 95% of models #39
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Reflection: Beam 1.0 501B A23B $0.30 in $1.00 out
Anthropic: Claude Fable 5.2 $8.00 in $40.00 out
Google: Gemini 4 Carbon $2.00 in $10.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.30 $0.000300
Output $1.00 $0.001000

What would Reflection: Beam 1.0 501B A23B cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$1.84/mo Reflection: Beam 1.0 501B A23B $0.0006 per request
$63.36/mo Anthropic: Claude Fable 5.2 $0.02 per request
$15.84/mo Google: Gemini 4 Carbon · best value $0.0053 per request

Full calculator with 753 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save Reflection: Beam 1.0 501B A23B for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About Reflection: Beam 1.0 501B A23B

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..

Frequently asked questions about Reflection: Beam 1.0 501B A23B

How much does Reflection: Beam 1.0 501B A23B cost?

Reflection: Beam 1.0 501B A23B costs $0.30 per million input tokens and $1.00 per million output tokens.

What is the context window of Reflection: Beam 1.0 501B A23B?

Reflection: Beam 1.0 501B A23B has a context window of 1,048,576 tokens (1M).

What can Reflection: Beam 1.0 501B A23B do?

Reflection: Beam 1.0 501B A23B supports tool use and function calling.

Who created Reflection: Beam 1.0 501B A23B?

Reflection: Beam 1.0 501B A23B is developed by Reflection and was released on October 16, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.