Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key
Get API key

StepFun · Step · Flagship

Step 5 Preview

Discount −30%New

StepFun's sparse frontier model for production agents, software engineering and long tool use.

Model id

step-5-preview
Get an API keyTry in Chat

Price per 1M tokens

Input
Regular rate $1.00now $0.70
Output
Regular rate $2.70now $1.89
Cached input
$0.1086% below input

30% below the market rate.

Added here 18 Oct 2026 — read the changelog for what changed and why.

Output is 2.7× the input rate. $1 covers about 607 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using Step 5 Preview

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "step-5-preview",
    "stream": true,
    "messages": [{"role": "user", "content": "Compare these five articles on SQLite in production and summarise where they disagree."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="step-5-preview",
    messages=[{"role": "user", "content": "Compare these five articles on SQLite in production and summarise where they disagree."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "step-5-preview",
  messages: [{ role: "user", content: "Compare these five articles on SQLite in production and summarise where they disagree." }],
  stream: true,
});

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

More: quickstart · API reference · try it in Chat first

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

Step line-up

Step 5 Preview or StepAudio 3 Chat Preview or Gemini 4 Argon?

Of the 2 Step models on this site, Step 5 Preview is the top of the line-up and StepAudio 3 Chat Preview the step down. Gemini 4 Argon from Google is the closest-priced flagship-tier model from another vendor. Each comparison lists the published rates and limits, then what favours each side.

Step 5 PreviewvsStepAudio 3 Chat Preview

Pick Step 5 Preview when

  • the task needs a higher tier: this catalogue places Step 5 Preview in the flagship tier and StepAudio 3 Chat Preview in the fast tier.
  • you rely on Tools, Vision, Structured output and Prompt caching, which StepAudio 3 Chat Preview does not list.
  • the work is agents, software engineering and research, which this catalogue lists for Step 5 Preview and not for StepAudio 3 Chat Preview.

Pick StepAudio 3 Chat Preview instead when

  • a free model covers the work until the promotion ends.
  • your workload looks like voice-style chat, reasoning replies and preview trials, labels the catalogue gives StepAudio 3 Chat Preview only.

Step 5 PreviewvsGemini 4 Argon

Per 1M tokensStep 5 PreviewGemini 4 Argon
Input$0.7033% more$0.525
Output$1.8928% less$2.63
Cached input$0.10the same$0.10
Context1Mthe same1M
Max output64kthe same64k

Pick Step 5 Preview when

  • cost per request decides it: Step 5 Preview charges output 28% less than Gemini 4 Argon.
  • the work is research, which this catalogue lists for Step 5 Preview and not for Gemini 4 Argon.

Pick Gemini 4 Argon instead when

  • the job runs well enough on the lower rates: input at 25% less.
  • your workload looks like maths and science, a label the catalogue gives Gemini 4 Argon only.

Use cases

What Step 5 Preview is listed for, and what it costs

The catalogue lists Step 5 Preview for agents, software engineering and research. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.

Model your own traffic

  1. Agents

    One step of a tool-using agent: 20,000 tokens of instructions, tool results and history, 15,000 of them cached, and 1,000 tokens of tool calls and notes out.

    “Check the order status for each customer in this list and draft a reply to the late ones.”

    Same request on StepAudio 3 Chat Preview $0 and Gemini 4 Argon $0.00675.

    $0.00689

    per agent step, about 1,451 per $10

    $0.0092 at the market rate

    0.005 × $0.70 + 0.015 × $0.10 + 0.001 × $1.89

  2. Software engineering

    Implementing a function or endpoint: 8,000 tokens of context in, 2,000 tokens of code out.

    “Write a TypeScript endpoint that returns paginated orders for the signed-in user.”

    Same request on StepAudio 3 Chat Preview $0 and Gemini 4 Argon $0.00945.

    $0.00938

    per task, about 1,066 per $10

    $0.0134 at the market rate

    0.008 × $0.70 + 0.002 × $1.89

  3. Research

    A research question with search results attached: 25,000 tokens in, a 1,500-token summary out.

    Break broad questions into focused sub-questions for better answers.

    “Compare these five articles on SQLite in production and summarise where they disagree.”

    Same request on StepAudio 3 Chat Preview $0 and Gemini 4 Argon $0.017062.

    $0.020336

    per summary, about 491 per $10

    $0.02905 at the market rate

    0.025 × $0.70 + 0.0015 × $1.89

Overview

When Step 5 Preview fits

Step 5 Preview is a flagship model from StepFun, available here under the exact model id “step-5-preview”. It heads the Step line-up here, above StepAudio 3 Chat Preview. StepFun has not published a release date we can cite; it has been available here since 18 Oct 2026.

StepFun documents tools, vision, reasoning, structured output and prompt caching for it, and it reads images as well as text.

It costs $0.70 per million input tokens and $1.89 per million output tokens, so output is 2.7× the input rate. That is 30% below the market rate of $1 input and $2.70 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 27% of the bill for agents, 40% for software engineering and 14% for research, so trimming the context you send saves more than capping the answer. With a 3:1 input-to-output mix it ranks 13th lowest-cost of the 27 models on this site.

Cached input bills at $0.10 per million tokens, 86% below the standard input rate. In the agents example, 15k of the 20k input tokens come from cache, which brings one agent step from $0.01589 down to $0.00689.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Similar models

Same tier, other vendors

Same key, same balance. Switching is a change to the model field.

Compare side by sideAll models

Use Step 5 Preview with any balance.

Step 5 Preview is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Create an accountSee pricing

Step 5 Preview is developed by StepFun. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by StepFun.