Step 3.7 Flash model profile

Evidence snapshot: 2026-09-06

Step 3.7 Flash is a StepFun model profile with a 262,144-token context window. The dated catalog snapshot records text, image, video modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.

Step 3.7 Flash is a reference profile: StepFun publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Step 3.7 Flash is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.

Step 3.7 Flash accepts text, image, and video and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, tool calling, video input, and vision as capabilities or interfaces.

The dated reference snapshot lists $0.16 input and $0.92 output per million tokens. Cached input is $0.032 per million tokens.

Step 3.7 Flash ranked #33 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Model research profile
Provider or publisher: StepFun
Context window: 262,144 tokens
Snapshot date: 2026-09-06
Knowledge cutoff: Not disclosed
Reference catalog ID: stepfun/step-3.7-flash

When to pick Step 3.7 Flash

Step 3.7 Flash is a reference profile: StepFun publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.

Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
Look elsewhere when the request is trivial and latency-sensitive. Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.

Context, modalities, and identity

Provider or publisher: StepFun
Context window: 262,144 tokens
Maximum output: 230,400 tokens
Input modalities: text, image, and video
Output modalities: text
Knowledge cutoff: Not disclosed

Model overview

Reference model ID: stepfun/step-3.7-flash
Canonical version: stepfun/step-3.7-flash-20260528
Hugging Face ID: stepfun-ai/Step-3.7-Flash

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

prompt caching
reasoning controls
structured output
text generation
tool calling
video input
vision

Dated pricing snapshot

The dated reference snapshot lists $0.16 input and $0.92 output per million tokens. Cached input is $0.032 per million tokens.

These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.

Price date: 2026-09-06
Input: $0.16 per 1M tokens
Cached input: $0.032 per 1M tokens
Output: $0.92 per 1M tokens

Provider routes, performance, and uptime

The snapshot retains 3 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

Active provider endpoints: 3
Best p50 latency: 0.25 s
Best p50 throughput: 102 tok/s
Availability with routing: 99.96% over the sampled window
Availability without routing: 98.97% over the sampled window
Performance date: 2026-09-06

Provider	Quantization	Input / 1M	Output / 1M	Cache read / 1M	Context	p50 latency	p50 throughput	Uptime (1d)
DeepInfra	unknown	$0.16 / 1M	$0.92 / 1M	$0.032 / 1M	262,144 tokens	0.25 s	102 tok/s	99.90%
NovitaAI	fp8	$0.2 / 1M	$1.15 / 1M	$0.04 / 1M	262,144 tokens	2.20 s	8 tok/s	98.60%
StepFun	fp8	$0.2 / 1M	$1.15 / 1M	$0.04 / 1M	256,000 tokens	4.82 s	40 tok/s	98.18%

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Coding Index: 39.6

Design Arena category	Elo	Win rate	Rank
3d	1164	41.8%	#63
asciiart	1175	45.4%	#30
codecategories	1196	43.8%	#53
dataviz	1193	44.2%	#54
gamedev	1184	40.5%	#57
svg	1108	37.7%	#59
uicomponent	1199	43.5%	#52
website	1207	45.1%	#52

Popularity and market context

Third-party catalog rank: #33
Global market share: Not inferred
Observation date: 2026-09-06

Frequently asked questions

When should I use Step 3.7 Flash?

Step 3.7 Flash is a reference profile: StepFun publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the request is trivial and latency-sensitive: Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.

What is Step 3.7 Flash?

What context window does Step 3.7 Flash have?

The dated profile lists 262,144 tokens of context and up to 230,400 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for Step 3.7 Flash?

The 2026-09-06 snapshot includes 1 Artificial Analysis index and 8 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Is Step 3.7 Flash available through Kendr?

This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.

Does the popularity rank represent Step 3.7 Flash's global market share?

Sources and evidence dates

Step 3.7 Flash third-party catalog record (catalog, checked 2026-09-06)
Third-party model catalog methodology (methodology, checked 2026-09-06)
Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)