Skip to content
Model infoModelsSnapshot: 15 Oct 2026

StepFun / Step

Step 5 Preview

Multimodal reasoning and coding model with a published 1M-token context and three reasoning-effort levels.

Language models (LLMs)
previewClosed weightsText generationReasoningCodingVisionVideo understanding
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
13 of 20 specification fields collected
Input token limit1MSee specification notes below
Maximum output64KSee specification notes below
Input billingSee ratesStepFun China
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
1MSource for Context / input limit (opens in a new tab)
Maximum output
64KSource for Maximum output (opens in a new tab)
Input modalities
Text, Image, VideoSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
SupportedSource for Reasoning (opens in a new tab)
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
SupportedSource for Structured output (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
SupportedSource for Context caching (opens in a new tab)

The regional pricing table explicitly publishes cached-input rates.

Maximum input tokens
1MSource for Maximum input tokens (opens in a new tab)
Supported reasoning efforts
low, medium, highSource for Supported reasoning efforts (opens in a new tab)
Input image limits
Up to 60 JPG/JPEG, PNG, WebP or static GIF images by URL or Base64.Source for Input image limits (opens in a new tab)
Input video limits
URL, Base64 or stepfile references; MP4, QuickTime or Matroska. URL MP4 must be under 128 MB; under 5 minutes is a recommendation, not a hard duration ceiling.Source for Input video limits (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

StepFun China

Provider source (opens in a new tab)
API model ID
step-5-preview
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
China platform (.com); deployment geography and data residency are not established by the hostname.
API endpoint URL
POST https://api.stepfun.com/v1/chat/completionsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text and vision tokensInput1CN¥7.001 million tokens
Text and vision tokensCached input2CN¥0.351 million tokens
Text and vision tokensOutput1CN¥20.001 million tokens

Rate conditions

  1. Regional pay-as-you-go rate as reviewed on 2026-10-12. Input, cached input and output are distinct charges; no currency conversion. Subscription allowances are separate.
  2. CNY 0.35 per million cached input tokens applies as of 2026-10-12. Standard rate becomes CNY 0.70 on 2026-10-14 at 00:30 Beijing; users who called the pay-as-you-go API before then retain 0.35. Step Plan is excluded from this change.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

StepFun International

Provider source (opens in a new tab)
API model ID
step-5-preview
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
International platform (.ai); deployment geography and data residency require account-specific confirmation.
API endpoint URL
POST https://api.stepfun.ai/v1/chat/completionsSource for API endpoint URL (opens in a new tab)
INPUT / 1M TOKENS$1.00
OUTPUT / 1M TOKENS$2.70

Regional pay-as-you-go rate as reviewed on 2026-10-12. Input, cached input and output are distinct charges; no currency conversion. Subscription allowances are separate. Cached input price: $0.10 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text and vision tokensInput1$1.001 million tokens
Text and vision tokensCached input1$0.101 million tokens
Text and vision tokensOutput1$2.701 million tokens

Rate conditions

  1. Regional pay-as-you-go rate as reviewed on 2026-10-12. Input, cached input and output are distinct charges; no currency conversion. Subscription allowances are separate.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

StepFun China

step-5-preview
Documented
Support evidence (opens in a new tab)
How it works
Automatic matching prompt prefixesSource for How it works (opens in a new tab)
Minimum reusable input
256-token blocks; guide says automatic above 256 tokens and no hits below 256.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
LRU eviction; lifetime varies with traffic. No fixed TTL is promised.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Keep repeated content at the start of the prompt; identical images, videos and tool history can participate.Source for How to enable it (opens in a new tab)
Usage fields
response.usage.cached_tokensSource for Usage fields (opens in a new tab)
Billing rules
CNY 0.35 per million cached input tokens applies as of 2026-10-12. Standard rate becomes CNY 0.70 on 2026-10-14 at 00:30 Beijing; users who called the pay-as-you-go API before then retain 0.35. Step Plan is excluded from this change.Source for Billing rules (opens in a new tab)
Limits & data boundaries
No manual cache clearing or guaranteed cache hits.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cached input1Text and vision tokensCN¥0.35 / 1 million tokensPricing evidence (opens in a new tab)

Rate conditions

  1. CNY 0.35 per million cached input tokens applies as of 2026-10-12. Standard rate becomes CNY 0.70 on 2026-10-14 at 00:30 Beijing; users who called the pay-as-you-go API before then retain 0.35. Step Plan is excluded from this change.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

StepFun International

step-5-preview
Documented
Support evidence (opens in a new tab)
How it works
Automatic matching prompt prefixesSource for How it works (opens in a new tab)
Minimum reusable input
256-token blocks; guide says automatic above 256 tokens and no hits below 256.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
LRU eviction; lifetime varies with traffic. No fixed TTL is promised.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Keep repeated content at the start of the prompt; identical images, videos and tool history can participate.Source for How to enable it (opens in a new tab)
Usage fields
response.usage.cached_tokensSource for Usage fields (opens in a new tab)
Billing rules
Cache-miss input includes writing to cache; hits use the model’s cached-input rate.Source for Billing rules (opens in a new tab)
Limits & data boundaries
No manual cache clearing or guaranteed cache hits.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.10 / 1M tokensPricing evidence (opens in a new tab)
Cached input1Text and vision tokens$0.10 / 1 million tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Regional pay-as-you-go rate as reviewed on 2026-10-12. Input, cached input and output are distinct charges; no currency conversion. Subscription allowances are separate.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this named native commercial service from official model/API documentation and comparison with StepFun’s public model repositories. No release of weights for this exact named service was found in the reviewed inventory. Public Step 3/3.5/3.7, Step-Audio Mini/R1/R1.1, Step1X and StepVideo releases are excluded; this does not assert that every StepFun model is closed.

Classification evidence (opens in a new tab)

Sources reviewed