Step 3.5 Flash

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.

stepfun/step-3.5-flash

Organization: StepFun (China)
Family: —
Providers: 9
Context: 256,000
Output limit: 256,000
Knowledge: 2025-01
Release: 2026-01-29
Updated: 2026-02-13
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

9 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Eden AI	deepinfra/stepfun-ai/Step-3.5-Flash	262,144	256,000	$0.09 / $0.30	Yes	Yes	Yes	View
EmpirioLabs AI	step-3-5-flash	256,000	131,072	$0.10 / $0.30	Yes	Yes	Yes	View
Hugging Face	stepfun-ai/Step-3.5-Flash	262,144	256,000	$0.10 / $0.30	Yes	Yes	—	View
Kilo Gateway	stepfun/step-3.5-flash	262,144	65,536	$0.10 / $0.30	Yes	Yes	No	View
NanoGPT	stepfun-ai/step-3.5-flash	262,144	65,536	$0.10 / $0.30	Yes	No	No	View
SiliconFlowvia OpenRouter	stepfun/step-3.5-flash fp8	262,144	65,536	$0.10 / $0.30	Yes	Yes	No	View
StepFun Step Plan (China)	step-3.5-flash	256,000	256,000	— / —	Yes	Yes	—	View
StepFun Step Plan (Global)	step-3.5-flash	256,000	256,000	— / —	Yes	Yes	—	View
Vercel AI Gateway	stepfun/step-3.5-flash	262,114	262,114	$0.09 / $0.30	Yes	Yes	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.09Per 1M input tokens

Output from$0.30Per 1M output tokens

Available offers9Across 9 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration

InputOutput

SiliconFlowsiliconflow/fp8

$0.10$0.30

stepfun/step-3.5-flashObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.10
Output: $0.30

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
SiliconFlowsiliconflow/fp8	$0.10	$0.30	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

SiliconFlowsiliconflow/fp8

1,314.5–11,073.67 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
SiliconFlowsiliconflow/fp8	1,314.5 ms	1,900.25 ms	2,924.9 ms	11,073.67 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

SiliconFlowsiliconflow/fp8

68–103.25 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
SiliconFlowsiliconflow/fp8	68 t/s	78.25 t/s	90.5 t/s	103.25 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 1 endpoint

Endpoint5 minutes30 minutes24 hours

SiliconFlowsiliconflow/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

99.72%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

stepfun/step-3.5-flashObserved Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 65,536
Tokenizer: Other
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-01-29

Base URLhttps://openrouter.ai/api/v1

Model IDstepfun/step-3.5-flash

Version IDstepfun/step-3.5-flash

Weights IDstepfun-ai/Step-3.5-Flash

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
max_tokens
reasoning
temperature
tool_choice
tools
top_k
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Step 3.5 Flash cost?

Listed rates start at $0.09 per million input tokens and $0.30 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Step 3.5 Flash?

There are 9 cataloged offers across 9 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 256,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · ce3d5dbd62c1
Sep 12, 2026 · 74a6f543ed39