AI model comparison

Beam 1.0 501B A23B vs Step 3.7 Flash

Side by side comparison of Beam 1.0 501B A23B and Step 3.7 Flash on pricing, benchmark scores, context window, and more.

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

Input / 1M
$0.25
Output / 1M
$1
Context
1.05M

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.

Input / 1M
$0.20
Output / 1M
$1.15
Context
262K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

stepfun logo

Step 3.7 Flash

1.0x cheaper for a typical chat

Higher intelligence score

stepfun logo

Step 3.7 Flash

19.5 vs 17.7 on Artificial Analysis

Larger context window

reflection logo

Beam 1.0 501B A23B

1.05M vs 262K tokens

Newer release

reflection logo

Beam 1.0 501B A23B

Released October 16, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

reflection logoBeam 1.0 501B A23B17.7
stepfun logoStep 3.7 Flash19.5

Coding index

reflection logoBeam 1.0 501B A23BNot available
stepfun logoStep 3.7 Flash39.6

Agentic index

reflection logoBeam 1.0 501B A23BNot available
stepfun logoStep 3.7 FlashNot available

Pricing

Beam 1.0 501B A23B vs Step 3.7 Flash API pricing

Per-token API rates. Cheaper option highlighted.

Metricreflection logoBeam 1.0 501B A23Bstepfun logoStep 3.7 Flash
Input tokensPer 1M tokens$0.25$0.20
Output tokensPer 1M tokens$1$1.15
Cached input (read)Per 1M tokens$0.05$0.04
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

reflection logoBeam 1.0 501B A23B$1
stepfun logoStep 3.7 Flash$0.98

Coding task

30K in, 4K out

reflection logoBeam 1.0 501B A23B$11.50$5.50 cached
stepfun logoStep 3.7 Flash$10.60$5.80 cached

Long document summary

150K in, 2K out

reflection logoBeam 1.0 501B A23B$39.50$9.50 cached
stepfun logoStep 3.7 Flash$32.30$8.30 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricreflection logoBeam 1.0 501B A23Bstepfun logoStep 3.7 Flash
Context window1.05M tokens262K tokens
Max output131K tokens230K tokens
Input typesTextImage, Text, Video
Output typesTextText
Reasoning effort levelsMax, Extra high, High, Medium, LowHigh, Medium, Low
Default reasoning effortMaxMedium
Release dateOctober 16, 2026May 28, 2026

Features

Supported features

API features available for each model.

Metricreflection logoBeam 1.0 501B A23Bstepfun logoStep 3.7 Flash
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Step 3.7 Flash is 1.0x cheaper for a typical chat. Step 3.7 Flash scores higher on the Artificial Analysis Intelligence Index (19.5 vs 17.7). Beam 1.0 501B A23B has the larger context window (1.05M vs 262K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Beam 1.0 501B A23B or Step 3.7 Flash cheaper?

Step 3.7 Flash is cheaper for a typical chat (2K input tokens and 500 output tokens). Step 3.7 Flash costs $0.20 per 1M input tokens and $1.15 per 1M output tokens, while Beam 1.0 501B A23B costs $0.25 per 1M input tokens and $1 per 1M output tokens.

Which has a bigger context window, Beam 1.0 501B A23B or Step 3.7 Flash?

Beam 1.0 501B A23B supports up to 1.05M tokens of context, compared with 262K for Step 3.7 Flash.

Is Beam 1.0 501B A23B smarter than Step 3.7 Flash?

On the Artificial Analysis Intelligence Index, Beam 1.0 501B A23B scores 17.7 and Step 3.7 Flash scores 19.5, putting Step 3.7 Flash ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Beam 1.0 501B A23B and Step 3.7 Flash at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Beam 1.0 501B A23B and Step 3.7 Flash answer side by side and keep the better response.

reflection logostepfun logo

Why choose? Ask both.

Send one prompt to Beam 1.0 501B A23B and Step 3.7 Flash at the same time. Compare the answers side by side and keep the best one.