Skip to content

StepFun · Chat

Step 5 Preview

StepFun 🇨🇳ChatStep familyOpen weights. One of its sources says the weights are publicly available.
From Empiriolabs's listing:
Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.
llminfo IQ
132.7
Max context
1M
Listings
37

Evidence and sources

International API storefront (platform.stepfun.ai) is Singapore-based; principal operating entity 上海阶跃星辰智能科技股份有限公司 (Shanghai).

🤗 stepfun-ai/Step-5-Previewllminfo IQ 132.7, ranked among chat models. From 119 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 115.2, 95% interval 108–123. From 8 benchmark families across 4 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (43.2). Costs more per task than its benchmark results predict. From 23 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 20 Sep 2026Maker HQ: CN (source)
All rankings: #9 on OpenRouter this week #145 on OpenRouter this month #269 on OpenRouter today #325 on NanoGPT recentlySources: StepFun API data, EmpirioLabs data, Models.dev data, llminfo researchPrimary data from StepFun API from EmpirioLabs: primary mode, description from Models.dev: weights availability from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 StepFunstep-5-previewSources: Models.dev data, StepFun API data1M$1.0461cache read $0.1046$2.989——
 Opencode Gostep-5-preview-free · freeSource: Models.dev data1M$0.00$0.00——
 Ezkielynastep-5-previewSource: Models.dev data1M$0.4579cache read $0.0458$1.236——
 Runinfrastepfun-ai/Step-5-PreviewSource: Models.dev data1M$0.90cache read $0.09$2.43——
 Eden AIInference by DeepInfradeepinfra/stepfun-ai/Step-5-PreviewSource: Models.dev data1M$1.00cache read $0.10$2.70——
 Kilostepfun/step-5-previewSources: Kilo AI Gateway data, Models.dev data1M$1.00cache read $0.10$2.70——
 Llmgatewaystep-5-previewSource: LLMGateway data1M$1.00cache read $0.10$2.70——
 NanoGPTstepfun/step-5-previewSources: Models.dev data, NanoGPT1M$1.00cache read $0.05$2.70——
 Nous Portalstepfun/step-5-previewSource: Nous Portal Inference Gateway data262K$1.00cache read $0.10$2.70——
 OpenRouterInference by Featherless AIstepfun/step-5-preview · fp4Source: OpenRouter data docs262K$1.00cache read $0.10$2.70282,516ms
Show all 30 listings

Showing 10 of 30: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aihubmix, Aimlapi, Commandcode, DeepInfra, Empiriolabs, Gmicloud, Kenari, Llmgateway Providers, Novita AI, Ppio, Vercel, Wavespeed, Zenmux.

7 listings without a price are hidden.

Included in plans

MiniStepFunSubscription$6.99/moPlan page
PlusStepFunSubscription$9.99/moPlan page
ProStepFunSubscription$29/moPlan page
MaxStepFunSubscription$99/moPlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO53 related benchmarks · 53 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 49 more benchmarksHide 49 benchmarks
BenchmarkScore
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled

Coding

Arena ELOSource: LMArena data · Nov 2026
ValsSource: Vals AI

Agentic

Arena AgentSource: LMArena data

Science

General

Instruction following

Math

Reasoning

OCR

Other

SuperCLUESource: SuperCLUE data

Data credits: LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark

Around the web

  • stepfun-ai (StepFun)
    #### stepfun-ai/Step-3.7-Flash-GGUF ### spaces 13 Sort: Recently updated #### Step-Audio-EditX Try out Step-Audio-EditX #### StepAudio …#### stepfun-ai/Step-3.7-Flash-GGUF ### spaces 13 Sort: Recently updated #### Step-Audio-EditX Try out Step-Audio-EditX #### StepAudio 3 Music Studio Create songs, arrange vocals, and remix music wit…

    huggingface.co

    Model card
  • stepfun-ai · GitHub
    StepFun's flagship model for agentic work 89 2. Step-3.7-Flash Step-3.7-Flash Public A high-efficiency Flash model …StepFun's flagship model for agentic work 89 2. Step-3.7-Flash Step-3.7-Flash Public A high-efficiency Flash model for real-world agents. 348 29 3. Step-3.5-Flash Step-3.5-Flash Public Fast, Sharp & …

    github.com

    Repository
  • stepfun-ai (StepFun)

    #### stepfun-ai/Step-Audio-R1.1 #### stepfun-ai/Step-Audio-EditX #### stepfun-ai/Step-Audio-2-mini #### stepfun-ai/Step-3.5-Flash-GGUF-Q8\_0 #### stepfun-ai/Step-3.5-Flash-GGUF-Q4\_K\_S #### stepfun-…

    huggingface.co

    Model card
  • StepFun releases “trillion” and “multi-mode” large models
    On July 4, at the 2024 World Artificial Intelligence Conference, StepFun released three new Step …On July 4, at the 2024 World Artificial Intelligence Conference, StepFun released three new Step series general large models: STEP-2 trillion parameters language large model official version, STEP-1.…

    medium.com

  • StepFun: Step 3.5 Flash Coding Benchmark | Kilo Code
    Architecture and implementation specifications Specifications Model ID : stepfun/step-3.5-flash Created : January 29, 2026 Tokenizer …Architecture and implementation specifications Specifications Model ID : stepfun/step-3.5-flash Created : January 29, 2026 Tokenizer : Other Input Modalities : Text Context Window : 262,144 tokens Ma…

    kilo.ai

  • StepFun — AI Model API | LLM Reference
    StepFun is a Chinese AI company providing API access to its Step series of large …StepFun is a Chinese AI company providing API access to its Step series of large language and multimodal models. ## Available Models(8) View all → All models available asServerless · Model · Input (p…

    llmreference.com

  • StepFun AI Review 2026: Models, Pricing & Which to Pick | MyClaw.ai
    ## StepFun at a Glance StepFun (阶跃星辰) builds Step-series models, an OpenAI-compatible Open Platform API, …## StepFun at a Glance StepFun (阶跃星辰) builds Step-series models, an OpenAI-compatible Open Platform API, and consumer 阶跃 AI apps — separate from MyClaw. In 2026 you mainly choose multimodal agents on…

    myclaw.ai

  • Step 3.5 Flash - API Pricing & Benchmarks | OpenRouter
    ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs …ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models # StepFun: Step 3.5 Flash stepfun/step-3.5-flash:free Model weights Step 3.5 Flash is StepFu…

    openrouter.ai

  • stepfun/step-3.7-flash | ZenMux AI Model Routing
    224.93Mtokens Step 5 Preview is StepFun's next-generation flagship foundation model for real-world tasks, with a …224.93Mtokens Step 5 Preview is StepFun's next-generation flagship foundation model for real-world tasks, with a focus on coding and professional knowledge work. It natively supports text, image, and…

    zenmux.ai

  • StepFun - Intelligence, Performance & Price Analysis | Artificial Analysis
    ## Key definitions Average cost per task in the index. Costs are split by input, …## Key definitions Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available. ## Frequently …

    artificialanalysis.ai

Also known as: deepinfra/stepfun-ai/step-5-preview, empiriolabs/step-5-preview, gmi/stepfun-ai/step-5-preview, nvidia_nim/stepfun-ai/step-5-preview, opencode_go/step-5-preview, step-5-preview-free, step-5-preview-high, stepfun-ai/step-5-preview, stepfun/step-5-preview, tencent/step-5-preview

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works