跳到正文
原文
Hacker News· AnneWodell·· 21 小时前精选AI 评分61

阶跃星辰（StepFun）Step 5 Preview 上线 OpenRouter，支持 1M 上下文

Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter

AI 导读

阶跃星辰（StepFun）的 Step 5 Preview 在 OpenRouter 上架，采用稀疏 MoE 架构（27B 激活 / 600B 总参数），支持 1M token 上下文。

推荐理由

原文给出了 1M 上下文、27B/600B MoE 架构与分层定价，读者可据此判断它在大上下文与长链路任务上的可用边界。

正文

Skip to content

Image 1: OpenRouter

Search⌘K

ModelsBenchmarksChatRankingsAppsOriPricingDocs

BenchmarksChatPricingDocs

Sign Up

Sign Up *

Image 2: Favicon for StepFun

StepFun: Step 5 Preview

stepfun/step-5-preview

CompareAPI Try this model

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.

It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

Show more

Modalities

In / Out Price

$1 / $2.70 per 1M

Context

1.0M

Released

Oct 8, 2026

Image 3: Favicon for StepFun

StepFun: Step 5 Preview

CompareAPI Try this model

ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Reasoning effort All Latency / throughput P50

Provider Input/M Output/M Cache read/M Latency Throughput Uptime
Image 4: Favicon for StepFun StepFun $1.00 $2.70 $0.05 3.50 s 106 tps 100.00%

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Weighted Avg Input Price

$0.09582

/M tokens

Weighted Avg Output Price

$2.70

/M tokens

Step 5 Preview — Price history

Effective Listed

Input Output

Reset

3D 1W 1M 3M 1Y All

Chart visibility Provider Effective in /M Effective out /M Cache hit rate Token share 1d

| | Image 5: Favicon for StepFun StepFun | $0.0958 | $2.70 | 95.2% | 100.0% | | --- |

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

106 tok/s

P50, best across providers

Latency

3.50 s

P50, best provider

All locations

Reasoning effort All 3 days

Throughput

P99

Avg 302 tok/s

P95

Avg 264 tok/s

P90

Avg 247 tok/s

P75

Avg 206 tok/s

P50

Avg 153 tok/s

Latency

P50

Avg 1.54 s

P75

Avg 2.02 s

P90

Avg 2.83 s

P95

Avg 6.49 s

P99

Avg 17.90 s

E2E latency

P50

Avg 6.89 s

P75

Avg 12.74 s

P90

Avg 50.16 s

P95

Avg 79.64 s

P99

Avg 144.25 s

Tool call error rate

StepFun

Avg 0.66 %

Structured output error rate

StepFun

Avg 7.87 %

Cache hit rate

StepFun

Avg 92.90 %

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

99.94%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.43%

Availability over the last 3 days

Oct 5, 4 PM - Oct 8, 4 PM

Availability 99.43%

Mon Tue Wed Now

Availability over the last 24 hours

OpenRouter Availability

99.73%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Image 6: Favicon for https://openclaw.ai/

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

54.4B tokens

Image 7: Favicon for https://nousresearch.com

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

3.27B tokens

Image 8: Favicon for https://kilocode.ai/

Kilo Code

Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.

475M tokens

Image 9: Favicon for https://portal.nousresearch.com/api-docs

Nous Research API

Nous Research is an AI research team focused on advancing open-source AI.

156M tokens

Image 10: Favicon for https://claude.ai/apple-touch-icon.png

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

118M tokens

Activity

Token volume and request traffic to this model over time.

Tokens

Not enough data to display yet.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

1

Get your API key

Create an API key from your OpenRouter dashboard and set it as an environment variable:

Get API Key

Copy Copied!

shell

export OPENROUTER_API_KEY=sk-or-v1-...

2

Make your first request

Use stepfun/step-5-preview with the OpenRouter API:

OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in your request to enable reasoning, and access the reasoning_details array in the response to see the model's internal reasoning before the final answer. When continuing a conversation, preserve the complete reasoning_details when passing messages back to the model so it can continue reasoning from where it left off. Learn more about reasoning tokens.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

TypeScript SDK Python TypeScript (fetch)cURL Python (OpenAI)TypeScript (OpenAI)

Copy Copied!

typescript

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

// Stream the response to get reasoning tokens in usage
const stream = await openrouter.chat.send({
  chatRequest: {
    model: "stepfun/step-5-preview",
    messages: [
      {
        role: "user",
        content: "How many r's are in the word 'strawberry'?"
      }
    ],
    stream: true
  }
});

let response = "";
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    response += content;
    process.stdout.write(content);
  }

  // Usage information comes in the final chunk
  if (chunk.usage) {
    console.log("\nReasoning tokens:", chunk.usage.completionTokensDetails?.reasoningTokens);
  }
}

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

Copy Copied!

shell

curl -N https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
  "model": "stepfun/step-5-preview",
  "stream": true,
  "messages": [
    {"role": "user", "content": "Hello"}
  ]
}'

Endpoint

Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.

POSThttps://openrouter.ai/api/v1/chat/completions

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modelstepfun/step-5-preview

Creates a streaming or non-streaming response using the OpenAI Responses API format.

Docs

POSThttps://openrouter.ai/api/v1/responses

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modelstepfun/step-5-preview

Creates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.

Docs

POSThttps://openrouter.ai/api/v1/messages

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modelstepfun/step-5-preview

Parameters

Name Type Default Description
reasoning map — Controls reasoning behavior for models that support thinking tokens, including whether reasoning is enabled, the reasoning effort, maximum reasoning tokens, and whether reasoning is excluded from the response.
temperature float 1 This setting influences the variety in the model's responses.
max_tokens integer — This sets the upper limit for the number of tokens the model can generate in response.
tools array — Tool calling parameter, following OpenAI's tool calling request shape.
top_p float 1 This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P.
stop array — Stop generation immediately if the model encounter any token specified in the stop array.
frequency_penalty float 0 This setting aims to control the repetition of tokens based on how often they appear in the input.
logprobs boolean — Whether to return log probabilities of the output tokens or not.
top_logprobs integer — An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
response_format map — Forces the model to produce specific output format.

Frequently asked questions

What is Step 5 Preview?

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

How much does Step 5 Preview cost?

Step 5 Preview costs $1.00/M input tokens and $2.70/M output tokens, with separate rates for Cache Read at $0.05/M tokens.

What is the context length of Step 5 Preview?

Step 5 Preview has a 1,000,000 token context window. It supports up to 64,000 completion tokens.

Does Step 5 Preview support tool calling and structured outputs?

Yes. Step 5 Preview accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Step 5 Preview support?

Step 5 Preview accepts text, images, and video as input and returns text.

What other text models does StepFun have?

Step 3.7 Flash and Step 3.5 Flash are other text models from StepFun.

When was Step 5 Preview released?

Step 5 Preview was released on October 8, 2026.

Explore more models

AI Models with Vision: Multimodal LLMs for Image Understanding CollectionAI Model Rankings Ranking

More models fromstepfun

Step 3.7 Flash Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks. Text 262K context$0.20 / $1.15

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. Text 262K context$0.10 / $0.30

Previous slide Next slide

Image 11: OpenRouterImage 12: OpenRouter

© 2026 OpenRouter, Inc

Product

Company

Developer

Connect

Join the OpenRouter newsletter Model usage data, product updates, and research reports. One email each week.

Subscribe

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.

Playground

Open in Chat

Sign in to try this model

Responses are AI-generated. Verify before relying on them.

Playground

Open in Chat

Sign in to try this model

Responses are AI-generated. Verify before relying on them.

CompareAPI Try

API

Your key, drop-in code and the LLMs.txt for stepfun/step-5-preview.

Copy LLMs.txtView docs

12:20

End-to-End Latency percentiles on OpenRouter

Reset All locations

Close

Throughput percentiles on OpenRouter

Reset All locations

Close

Step 5 Preview — Price history

Close

Latency percentiles on OpenRouter

Reset All locations

Close

Cache Hit Rate by Provider

Reset

Close

Structured Output Error Rate by Provider

Reset

Close

Tool Call Error Rate by Provider

Reset

Close

来源：Hacker News · openrouter.ai

#模型发布#Agent