Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. StepFun

Step 5 Preview

Step 5 Preview is StepFun's 600B sparse MoE frontier model for production-scale agents, activating 27B parameters per token. It is built for software engineering, long-horizon tool use, research, professional knowledge work, and finance, with native text, image, and video understanding and a 1M-token context window.

  • Reasoning
  • Vision
  • Video Input
  • Tool Calling
  • Parallel Tool Calls
  • Structured Output

Added Sep 20, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$1.00
Output
$2.70
Cache read
$0.05
Compare provider prices

Specifications

Context window
1M
Max output
65.5K
Parameters
600B / 27B
Total / active

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto
Recommended
$1.00$2.70$0.05N/AN/A
DeepInfra
DeepInfra
FP8
US
$1.05$2.84$0.0525N/AN/A
Novita
Novita
US
$1.05$2.84$0.105N/AN/A
Uomi
Uomi
BF16
GLB
$1.10$2.98N/AN/AN/A
Privacy:ZDR, prompts not retained

Related text models

Compare Step 5 Preview with similar models from the same provider or model family.

Step 3.7 Flash Thinking

stepfun/step-3.7-flash:thinking

Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding.

Step 3.5 Flash

stepfun-ai/step-3.5-flash

StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.

Tencent Hy4 Flash

tencent/hy4-flash

Tencent Hy4 Flash is the smaller, faster and cheaper version of Hy4. It accepts text and images and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. It suits coding, automatic tool calling, structured output and high-volume work. Reasoning is on by default and can be turned off.

DeepSeek V4.1 Flash 1017 Abliterated CSF (jcartu)

jcartu/deepseek-v4.1-flash-1017-abliterated-lossless-csf

This model is based on DeepSeek-V4.1-Flash-1017-lossless-CSF by Local Inference Lab, Inc., a non-profit organization, available at https://huggingface.co/local-inference-lab/DeepSeek-V4.1-Flash-1017-lossless-CSF. DeepSeek-V4.1-Flash-1017-lossless-CSF is licensed under the Local Inference Lab License, Version 1.0. jcartu’s CSF derivative of DeepSeek V4.1 Flash 1017 applies norm-preserving abliteration to 132 dense tensors. It accepts text, supports tool calling and structured JSON output, and offers none, low, high and max reasoning effort. Input and output share a 1,048,576-token context window, with up to 943,718 output tokens. This offering uses jcartu/DeepSeek-V4.1-Flash-1017-abliterated-lossless-CSF.

SuperGemma4 26B Uncensored

jiunsong/supergemma4-26b-uncensored

SuperGemma4 26B Uncensored is Jiunsong’s tuned Gemma 4 mixture-of-experts model for conversation, writing and coding, with 26B total parameters and about 4B active per token. It accepts text and one image, supports function calling and JSON-schema output, and offers a 256,000-token context window with up to 8,192 output tokens.

GPT 6.2 Astra

openai/gpt-6.2-astra

GPT-6.2 Astra is OpenAI’s flagship reasoning model for complex coding, scientific research, and professional work. It accepts text and images and supports tool calling, structured outputs, and reasoning from low through max.