Step 5 Preview

by Stepfun
stepfun/step-5-preview

Step 5 Preview is a text and image and video-input model by Stepfun, available through the AgentSky API as stepfun/step-5-preview at $1.1605 per million input tokens and $3.13335 per million output tokens, with a 1M context window.

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).

  1. Get an API key

  2. Send a request

    curl https://gateway.agentsky.dev/v1/chat/completions \
      -H "authorization: Bearer $AGENTSKY_API_KEY" \
      -H "content-type: application/json" \
      -d '{"model":"stepfun/step-5-preview","messages":[{"role":"user","content":"In one sentence, what can you help me with?"}],"max_tokens":128}'
  3. Run it here, no terminal needed

    Billed to your balance: under $0.01.
  4. Or hand it to your agent

    Use Step 5 Preview through AgentSky.
    Model id: stepfun/step-5-preview
    OpenAI-compatible base URL: https://gateway.agentsky.dev/v1 · Anthropic base URL: https://gateway.agentsky.dev
    Docs: https://agentsky.dev/models/stepfun/step-5-preview.md
    Key: <your AgentSky API key>

This model is available through the API. It is not currently offered as an agent’s reasoning model.

Pricing

USD per million tokens, using your plan when signed in.
MeterPer 1M tokens
InputPrice: $1.1605
OutputPrice: $3.13335
Cache readPrice: $0.11605
Cache writePrice: $1.1605

Every response carries its own cost. Balance and per-call records: /v1/credits and /v1/generation.

Use it

Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "stepfun/step-5-preview",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response

Questions