---
title: "StepFun models: release history and timeline"
description: "Shanghai-based AI company that develops the Step series of language, multimodal, image, video, and audio foundation models, many of them released as open weights."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/stepfun"
markdown_url: "https://theaiengineering.com/releases/stepfun.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-09-20"
citation: "The AI Engineering Editors. \"StepFun models: release history and timeline.\" The AI Engineering, updated Sep 20, 2026. https://theaiengineering.com/releases/stepfun"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# StepFun models: release history and timeline

Shanghai-based AI company that develops the Step series of language, multimodal, image, video, and audio foundation models, many of them released as open weights.

- Headquarters: Shanghai, China
- Website: https://www.stepfun.com

22 releases from 1 lab, 17 with open weights. Dates are the labs' official announcement dates.

## September 2026

### Step 5 Preview

Step 5 Preview is StepFun's flagship model for agentic work, aimed at software engineering and professional knowledge work with particular strength in finance. It launched through StepFun products and API, with open weights following on October 15, 2026.

- Date: 2026-09-20
- Lab: StepFun
- Type: LLM
- Weights: Open weights
- Modalities: text, image, video → text
- Context window: 1,000,000 tokens
- Parameters: MoE: 600B total, 27B active
- License: StepFun Model License 1.0
- Available at launch: API, Consumer app, Open weights
- Permalink: https://theaiengineering.com/releases/2026/09#step-5-preview

Highlights:

- Sparse mixture-of-experts model with 600B total and 27B active parameters
- 1M-token context window; accepts text, image, and video input
- API model ID step-5-preview with low, medium, and high reasoning effort
- BF16 and FP8 weights on Hugging Face under the StepFun Model License 1.0

Source: [阶跃发布旗舰模型 Step 5 Preview：向前一步，智能效率的新一代“帕累托前沿”](https://www.stepfun.com/news/step-5-preview)

### StepAudio 3

StepAudio 3 is StepFun's speech and audio model family, comprising StepAudio 3 Realtime, ASR, TTS, Gen, and Music for full-duplex voice interaction, speech recognition, speech synthesis, multi-element audio generation, and music creation.

- Date: 2026-09-15
- Lab: StepFun
- Type: Speech
- Weights: Proprietary
- Modalities: text, audio → text, audio
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2026/09#stepaudio-3

Highlights:

- StepAudio 3 Realtime supports native full-duplex conversation with asynchronous tool calls
- StepAudio 3 Gen produces voices, sound effects, ambience, and background music from text descriptions and reference audio
- StepAudio 3 Music supports song creation, a cappella accompaniment, and covers, with ABC notation control
- All five models launched on the StepFun open platform

Source: [阶跃发布语音大模型StepAudio 3，拿下多个全球第一！](https://www.stepfun.com/news/stepaudio-3)

## May 2026

### Step 3.7 Flash

Step 3.7 Flash is a sparse mixture-of-experts vision-language model that builds on Step 3.5 Flash, adding native visual input for agent workflows that combine perception, search, coding, and reasoning at high throughput.

- Date: 2026-05-29
- Lab: StepFun
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Context window: 256,000 tokens
- Parameters: MoE: 198B total, about 11B active
- License: Apache-2.0
- Available at launch: API, Open weights
- Permalink: https://theaiengineering.com/releases/2026/05#step-3-7-flash

Highlights:

- 196B-parameter language backbone plus a 1.8B-parameter vision encoder
- Activates about 11B parameters per token with a 256K context window
- Three selectable reasoning levels: low, medium, and high
- Weights released under Apache-2.0

Source: [Step 3.7 Flash: A high-efficiency Flash model for Real-World Agents](https://static.stepfun.com/blog/step-3.7-flash/)

### StepAudio 2.5 Realtime

StepAudio 2.5 Realtime is StepFun's real-time voice conversation model, focused on understanding and expressing paralinguistic cues, user-defined personas set through the API, and stable role-play behavior.

- Date: 2026-05-08
- Lab: StepFun
- Type: Speech
- Weights: Proprietary
- Modalities: text, audio → text, audio
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2026/05#stepaudio-2-5-realtime

Highlights:

- Interprets tone, pace, pauses, sighs, and laughter in user speech
- Personality, background, preferences, and conversational boundaries can be set through the API
- Trained on more than 10,000 native personas expanded into a million-scale persona feature set

Source: [StepAudio 2.5 Realtime 上线！真人级实时语音对话能力，千万人设任你打造](https://www.stepfun.com/news/stepaudio-2-5-realtime)

## April 2026

### Step Image Edit 2

Step Image Edit 2 is a lightweight 3.5B-parameter StepFun model for image generation and editing, supporting Chinese and English text rendering, local edits, subject consistency, and style transfer with fast response times.

- Date: 2026-04-29
- Lab: StepFun
- Type: Image
- Weights: Proprietary
- Modalities: text, image → image
- Parameters: 3.5B
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2026/04#step-image-edit-2

Highlights:

- Generates or edits an image in about 0.5 to 2 seconds
- Launched on the StepFun open platform and Step Plan
- StepFun retired the model and its image APIs on October 10, 2026

Source: [阶跃 Step Image Edit 2 上线！小身材、大能力、快响应](https://www.stepfun.com/news/step-image-edit-2)

### StepAudio 2.5 ASR

StepAudio 2.5 ASR is StepFun's speech recognition model that brings Step 3.5 Flash's multi-token prediction to transcription and reuses a 32K language model context to transcribe up to 30 minutes of audio in one pass.

- Date: 2026-04-24
- Lab: StepFun
- Type: Speech
- Weights: Proprietary
- Modalities: audio → text
- Context window: 32,000 tokens
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2026/04#stepaudio-2-5-asr

Highlights:

- ASR plus MTP-5 architecture with peak inference of 500 tokens per second
- Transcribes up to 30 minutes of audio in a single request without slicing
- Launched on the StepFun open platform and Step Plan

Source: [阶跃 StepAudio 2.5 ASR 上线！500TPS 极速推理，30分钟语音“秒级转写”](https://www.stepfun.com/news/stepaudio-2-5-asr)

### StepAudio 2.5 TTS

StepAudio 2.5 TTS is StepFun's speech generation model with passage-level and in-text control over emotion, tone, rhythm, and pauses, plus zero-shot voice cloning with adjustable emotion and speaking style.

- Date: 2026-04-16
- Lab: StepFun
- Type: Speech
- Weights: Proprietary
- Modalities: text, audio → audio
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2026/04#stepaudio-2-5-tts

Highlights:

- Global context control sets the emotional tone, character state, and scene for a whole passage
- Controls can be given as natural-language instructions
- Launched on the StepFun open platform and Step Plan

Source: [阶跃 StepAudio 2.5 TTS 上线！人人都能是配音导演](https://www.stepfun.com/news/stepaudio-2-5-tts)

## February 2026

### Step 3.5 Flash

Step 3.5 Flash is StepFun's open-weight sparse mixture-of-experts reasoning model built for fast agentic and coding work, using three-way multi-token prediction and hybrid sliding-window attention for efficient long-context inference.

- Date: 2026-02-02
- Lab: StepFun
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Context window: 256,000 tokens
- Parameters: MoE: 196B total, 11B active
- License: Apache-2.0
- Available at launch: API, Open weights
- Permalink: https://theaiengineering.com/releases/2026/02#step-3-5-flash

Highlights:

- 196B total parameters with about 11B activated per token
- 256K context window using a 3:1 sliding-window to full-attention layer ratio
- 3-way multi-token prediction (MTP-3) for faster decoding
- Weights on Hugging Face and ModelScope under Apache-2.0; pre-training and mid-training checkpoints followed on March 4, 2026

Source: [阶跃星辰 Step 3.5 Flash 上线！更快更强更稳的 Agent 大脑，开源！](https://www.stepfun.com/news/step-3-5-flash-launch)

## January 2026

### Step-Audio R1.1

Step-Audio R1.1 (Realtime) is an upgrade to Step-Audio-R1 for interactive spoken dialogue, designed to reason while speaking so that real-time voice conversations keep low latency without giving up reasoning ability.

- Date: 2026-01-14
- Lab: StepFun
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → text, audio
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/01#step-audio-r1-1

Highlights:

- Dual-brain design separates high-level reasoning from speech generation
- Grounds reasoning in acoustic representations rather than transcripts alone
- Inference code and weights released on Hugging Face and ModelScope

Source: [GitHub - stepfun-ai/Step-Audio-R1](https://github.com/stepfun-ai/Step-Audio-R1)

### Step3-VL-10B

Step3-VL-10B is a compact open-weight multimodal foundation model from StepFun that targets visual perception, complex reasoning, and human-centric alignment at a 10B-parameter scale.

- Date: 2026-01-13
- Lab: StepFun
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Parameters: 10B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/01#step3-vl-10b

Highlights:

- 10B-parameter vision-language model with a base checkpoint also released
- Optional PaCoRe parallel reasoning mode aggregates 16 parallel rollouts
- FP8 weights and official vLLM support followed the initial release

Source: [stepfun-ai/Step3-VL-10B · Hugging Face](https://huggingface.co/stepfun-ai/Step3-VL-10B)

## December 2025

### NextStep-1.1

NextStep-1.1 is an updated version of StepFun's autoregressive text-to-image model that improves output quality through extended training and a flow-based reinforcement learning post-training stage.

- Date: 2025-12-24
- Lab: StepFun
- Type: Image
- Weights: Open weights
- Modalities: text → image
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#nextstep-1-1

Highlights:

- Builds on NextStep-1's autoregressive generation with continuous image tokens
- Adds flow-based reinforcement learning post-training
- Checkpoints hosted on Hugging Face under Apache-2.0

Source: [GitHub - stepfun-ai/NextStep-1](https://github.com/stepfun-ai/NextStep-1)

## November 2025

### Step1X-Edit v1.2

Step1X-Edit v1.2, described in its paper as ReasonEdit-S, is a version of StepFun's open image editing model with native reasoning-based editing, following a v1.2 preview released in September 2025.

- Date: 2025-11-26
- Lab: StepFun
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/11#step1x-edit-v1-2

Highlights:

- Adds native reasoning edit ability to the Step1X-Edit line
- A step1x-edit-v1p2-preview checkpoint was released on September 8, 2025
- Weights on Hugging Face under Apache-2.0

Source: [GitHub - stepfun-ai/Step1X-Edit](https://github.com/stepfun-ai/Step1X-Edit)

### Step-Audio-R1

Step-Audio-R1 is StepFun's audio reasoning model, applying chain-of-thought reasoning to audio understanding tasks. StepFun published the technical report and demo on November 19, 2025, and released the weights on November 27.

- Date: 2025-11-19
- Lab: StepFun
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → text
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/11#step-audio-r1

Highlights:

- Technical report and demo page released November 19, 2025
- Inference code and weights released November 27, 2025 on Hugging Face and ModelScope
- Repository code released under Apache-2.0

Source: [GitHub - stepfun-ai/Step-Audio-R1](https://github.com/stepfun-ai/Step-Audio-R1)

### Step-Audio-EditX

Step-Audio-EditX is a 3B-parameter LLM-based audio editing model trained with reinforcement learning to edit emotion, speaking style, and paralinguistic features of speech, alongside zero-shot text-to-speech.

- Date: 2025-11-06
- Lab: StepFun
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → audio
- Parameters: 3B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/11#step-audio-editx

Highlights:

- Technical report released November 6, 2025; weights followed on November 12
- Later updates added polyphonic pronunciation control plus Japanese and Korean support
- Repository released under Apache-2.0

Source: [GitHub - stepfun-ai/Step-Audio-EditX](https://github.com/stepfun-ai/Step-Audio-EditX)

## August 2025

### Step-Audio 2 mini

Step-Audio 2 mini is the open-weight member of StepFun's Step-Audio 2 family, an end-to-end multimodal model for audio understanding and speech conversation. A base version shipped alongside it, and a Think variant followed in September.

- Date: 2025-08-29
- Lab: StepFun
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → text, audio
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#step-audio-2-mini

Highlights:

- Step-Audio 2 technical report was published July 23, 2025
- Step-Audio 2 mini and Step-Audio 2 mini Base released August 29, 2025
- Step-Audio 2 mini Think added September 15, 2025
- Released under Apache-2.0

Source: [GitHub - stepfun-ai/Step-Audio2](https://github.com/stepfun-ai/Step-Audio2)

### NextStep-1

NextStep-1 is a 14B-parameter autoregressive image generation model that works directly with continuous image tokens rather than discrete ones, released with text-to-image and image editing checkpoints.

- Date: 2025-08-14
- Lab: StepFun
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- Parameters: 14B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#nextstep-1

Highlights:

- Released as NextStep-1-Large-Pretrain, NextStep-1-Large, and NextStep-1-Large-Edit
- Autoregressive generation over continuous image tokens
- Weights on Hugging Face under Apache-2.0

Source: [GitHub - stepfun-ai/NextStep-1](https://github.com/stepfun-ai/NextStep-1)

## July 2025

### Step 3

Step 3 is StepFun's multimodal reasoning model built on a mixture-of-experts architecture and co-designed with Multi-Matrix Factorization Attention and Attention-FFN Disaggregation to reduce decoding costs.

- Date: 2025-07-25
- Lab: StepFun
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image → text
- Context window: 65,536 tokens
- Parameters: MoE: 321B total, 38B active
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/07#step-3

Highlights:

- 321B total parameters (316B language model) with 38B active per token
- Maximum context length of 65,536 tokens
- Model weights were uploaded to Hugging Face on July 31, 2025 under Apache-2.0

Source: [stepfun-ai/step3 · Hugging Face](https://huggingface.co/stepfun-ai/step3)

## May 2025

### Step1X-3D

Step1X-3D is an open framework for generating textured 3D assets, pairing a geometry generation model with a texture synthesis model, released with training code and a curated 3D dataset.

- Date: 2025-05-13
- Lab: StepFun
- Type: Image
- Weights: Open weights
- Modalities: image → 3d
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/05#step1x-3d

Highlights:

- 1.3B-parameter geometry model and 3.5B-parameter texture model
- Training code and 800K curated 3D asset IDs released
- Weights on Hugging Face under Apache-2.0

Source: [GitHub - stepfun-ai/Step1X-3D](https://github.com/stepfun-ai/Step1X-3D)

## April 2025

### Step1X-Edit

Step1X-Edit is StepFun's open-source general image editing model that follows natural-language editing instructions, released with inference code, weights, a technical report, and the GEdit-Bench evaluation benchmark.

- Date: 2025-04-25
- Lab: StepFun
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/04#step1x-edit

Highlights:

- Released with the GEdit-Bench image editing benchmark
- Updated v1.1 weights followed on July 9, 2025
- Weights on Hugging Face and ModelScope under Apache-2.0

Source: [GitHub - stepfun-ai/Step1X-Edit](https://github.com/stepfun-ai/Step1X-Edit)

## March 2025

### Step-Video-TI2V

Step-Video-TI2V is a 30B-parameter text-driven image-to-video model built on Step-Video-T2V, generating videos of up to 102 frames from an input image and text prompt.

- Date: 2025-03-17
- Lab: StepFun
- Type: Video
- Weights: Open weights
- Modalities: text, image → video
- Parameters: 30B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/03#step-video-ti2v

Highlights:

- Generates videos up to 102 frames
- Released with the Step-Video-TI2V-Eval benchmark and ComfyUI integration
- Weights on Hugging Face under MIT

Source: [GitHub - stepfun-ai/Step-Video-TI2V](https://github.com/stepfun-ai/Step-Video-TI2V)

## February 2025

### Step-Audio

Step-Audio is StepFun's open speech interaction family, led by the 130B-parameter Step-Audio-Chat model that unifies speech understanding and generation, released with a 3B text-to-speech model and an audio tokenizer.

- Date: 2025-02-17
- Lab: StepFun
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → text, audio
- Parameters: 130B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/02#step-audio

Highlights:

- Step-Audio-Chat is a 130B-parameter unified speech model
- Step-Audio-TTS-3B and Step-Audio-Tokenizer released alongside
- Released with the StepEval-Audio-360 multi-turn benchmark

Source: [GitHub - stepfun-ai/Step-Audio](https://github.com/stepfun-ai/Step-Audio)

### Step-Video-T2V

Step-Video-T2V is StepFun's 30B-parameter open text-to-video model, capable of generating videos of up to 204 frames, released alongside a faster Turbo variant and a technical report.

- Date: 2025-02-17
- Lab: StepFun
- Type: Video
- Weights: Open weights
- Modalities: text → video
- Parameters: 30B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/02#step-video-t2v

Highlights:

- Generates videos up to 204 frames
- Step-Video-T2V-Turbo released the same day
- Weights on Hugging Face under MIT

Source: [GitHub - stepfun-ai/Step-Video-T2V](https://github.com/stepfun-ai/Step-Video-T2V)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "StepFun models: release history and timeline." The AI Engineering, updated Sep 20, 2026. https://theaiengineering.com/releases/stepfun

HTML link:

```html
<a href="https://theaiengineering.com/releases/stepfun">StepFun models: release history and timeline</a> (The AI Engineering)
```

- Title: StepFun models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-09-20
- URL: https://theaiengineering.com/releases/stepfun
- Markdown: https://theaiengineering.com/releases/stepfun.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
