StepFun Models & API

Compare the StepFun models available on TokenHub, including Step 3.7 Flash and Step 3.7. Review pricing, context, capabilities, and model IDs, then call StepFun, Step, and StepFun AI through one OpenAI-compatible API workflow.

View StepFun Models Get API key

StepFun Models & API Pricing

Compare current StepFun API pricing, input and output token costs, context windows, endpoints, and model IDs. The catalog may include Step 3.7 Flash and Step 3.7; availability follows the live TokenHub model list.

API PricingSpecifications

Compare input, output, and cache-read prices for the available StepFun models. Open a model page to confirm the current billing unit and model ID.

Model NameInput/ M tokensOutput/ M tokensCache Read/ M tokens

StepFun

Step 3.7 Flashstep-3.7-flash

$0.2$1.15$0.04

Compare context windows, maximum output, reasoning, tool calling, endpoints, and release dates across Step 3.7 Flash and Step 3.7.

Model NameModalitiesContextMax outputReasoningTool callingEndpointReleased

StepFun

Step 3.7 Flashstep-3.7-flash

256K

✓

OpenAI / Responses / Anthropic

May 29, 2026

Catalog data

Pricing, model availability, context windows, and endpoint support reflect the current TokenHub catalog. Confirm the model detail page before a production release because specifications and availability can change.

Last updated: 2026-08-25

Get Started With the StepFun API

Create a TokenHub API key, copy a published StepFun model ID, and call it with OpenAI Chat Completions, Responses, or Claude Messages. Existing OpenAI SDK projects can usually switch by changing the API key, Base URL, and model ID.

01Create a TokenHub API key
02Choose an available StepFun model
03Choose an API protocol
04Copy the published StepFun model ID
05Send your first request

Get API key Read API docs

Choose an API protocol

OpenAI ChatPOST /v1/chat/completionsOpenAI ResponsesPOST /v1/responsesClaude MessagesPOST /v1/messages

OpenAI SDK · TypeScriptOpenAI SDK · PythoncURLTypeScript fetchPython requests

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: process.env.TOKENHUB_API_KEY,
  baseURL: "https://us-api.tokenhub.com/v1",
})

const result = await client.chat.completions.create({
  "model": "step-3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain why low latency matters for an AI product in one sentence."
    }
  ]
})
console.log(result.choices[0]?.message?.content)

import json
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("TOKENHUB_API_KEY"),
    base_url="https://us-api.tokenhub.com/v1",
)

request = json.loads("{\"model\":\"step-3.7-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}")
result = client.chat.completions.create(**request)
print(result.choices[0].message.content)

curl 'https://us-api.tokenhub.com/v1/chat/completions' \
  -X 'POST' \
  -H "Authorization: Bearer $TOKENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "step-3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain why low latency matters for an AI product in one sentence."
    }
  ]
}'

const response = await fetch("https://us-api.tokenhub.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "step-3.7-flash",
    "messages": [
      {
        "role": "user",
        "content": "Explain why low latency matters for an AI product in one sentence."
      }
    ]
  }),
})
const data = await response.json()
console.log(data)

import os
import requests

response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/chat/completions",
    headers={
        "Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=__import__("json").loads("{\"model\":\"step-3.7-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}"),
)
response.raise_for_status()
print(response.json())

OpenAI SDK · TypeScriptOpenAI SDK · PythoncURLTypeScript fetchPython requests

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: process.env.TOKENHUB_API_KEY,
  baseURL: "https://us-api.tokenhub.com/v1",
})

const result = await client.responses.create({
  "model": "step-3.7-flash",
  "input": "Explain why low latency matters for an AI product in one sentence."
})
console.log(result.output_text)

import json
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("TOKENHUB_API_KEY"),
    base_url="https://us-api.tokenhub.com/v1",
)

request = json.loads("{\"model\":\"step-3.7-flash\",\"input\":\"Explain why low latency matters for an AI product in one sentence.\"}")
result = client.responses.create(**request)
print(result.output_text)

curl 'https://us-api.tokenhub.com/v1/responses' \
  -X 'POST' \
  -H "Authorization: Bearer $TOKENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "step-3.7-flash",
  "input": "Explain why low latency matters for an AI product in one sentence."
}'

const response = await fetch("https://us-api.tokenhub.com/v1/responses", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "step-3.7-flash",
    "input": "Explain why low latency matters for an AI product in one sentence."
  }),
})
const data = await response.json()
console.log(data)

import os
import requests

response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/responses",
    headers={
        "Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=__import__("json").loads("{\"model\":\"step-3.7-flash\",\"input\":\"Explain why low latency matters for an AI product in one sentence.\"}"),
)
response.raise_for_status()
print(response.json())

cURLTypeScript fetchPython requests

curl 'https://us-api.tokenhub.com/v1/messages' \
  -X 'POST' \
  -H "Authorization: Bearer $TOKENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "step-3.7-flash",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain why low latency matters for an AI product in one sentence."
    }
  ]
}'

const response = await fetch("https://us-api.tokenhub.com/v1/messages", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "step-3.7-flash",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Explain why low latency matters for an AI product in one sentence."
      }
    ]
  }),
})
const data = await response.json()
console.log(data)

import os
import requests

response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/messages",
    headers={
        "Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=__import__("json").loads("{\"model\":\"step-3.7-flash\",\"max_tokens\":1024,\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}"),
)
response.raise_for_status()
print(response.json())

Which StepFun Model Should You Choose?

Use this StepFun model selection guide for fast text generation, reasoning, coding, agent workflows, and general assistants. Compare price, context, reasoning, tool calling, and endpoint support before shipping.

API workload	Start with	When it fits	Verify before launch
High-volume StepFun API calls	Step 3.7 Flash	Fast iteration, chat, extraction, summarization, and batch workloads using StepFun.	StepFun API pricing, throughput, and output-token cost
StepFun reasoning and coding	Step 3.7 Flash	Multi-step analysis, code generation, debugging, and agent tasks where answer quality matters.	Reasoning support, tool calling, latency, and total request cost
General StepFun applications	Step 3.7 Flash	Everyday assistants, content generation, information extraction, and product features.	Task accuracy, endpoint support, and production price
Long-context StepFun workloads	Step 3.7 Flash	Documents, codebases, research, and conversations where input length is the constraint.	Context window, input-token price, maximum output, and streaming
Quality-first StepFun workloads	Step 3.7 Flash	Production outputs where capability matters more than the lowest unit cost.	Task quality, latency, and the price difference versus a faster model

Choose and Compare StepFun Models

Use the live catalog to compare StepFun API price, model specifications, context limits, and supported endpoints.

StepFun API PricingCompare input, output, cache-read, or per-request pricing for available StepFun models.StepFun Model SpecificationsReview context, maximum output, reasoning, tool calling, endpoints, and release dates.Choose a StepFun ModelMatch StepFun models to fast text generation, reasoning, coding, agent workflows, and general assistants.

Integrate StepFun

Use TokenHub to connect StepFun to the development tools already in your workflow.

Cursor integrationConfigure Cursor to call StepFun through your TokenHub API key.OpenClaw integrationConnect OpenClaw to StepFun with an OpenAI-compatible API.Claude Code integrationUse StepFun in Claude Code with the TokenHub endpoint and API key.Cline integrationSet up Cline to use StepFun models for your coding workflow.Codex integrationUse StepFun in Codex with your TokenHub API key and OpenAI-compatible endpoint.OpenCode integrationConfigure OpenCode to call StepFun through the TokenHub endpoint.

View all integrations

StepFun API FAQ

What are StepFun, Step, and StepFun AI?

StepFun, Step, and StepFun AI are names and search terms associated with this model family. TokenHub uses the published provider and model IDs shown in the live catalog.

Which StepFun models are available on TokenHub?

The live list above shows current availability. Relevant model searches include Step 3.7 Flash and Step 3.7, but only models displayed in the TokenHub catalog can be called through this page.

How do I get a StepFun API key?

StepFun API and StepFun API key searches lead to the same TokenHub workflow: create an API key, select a published StepFun model ID, and use the TokenHub Base URL in your application.

How is StepFun API pricing calculated?

Pricing depends on the selected model and billing type. Compare input, output, cache, or per-request prices in the table and confirm the model detail page before production use.

Can I use the OpenAI SDK with StepFun?

Yes. Use the TokenHub Base URL, API key, and published StepFun model ID with the OpenAI Python or Node.js SDK. Endpoint support is shown for each model.

Which StepFun model should I use?

Choose based on the workload: fast text generation, reasoning, coding, agent workflows, and general assistants. Compare actual price, context, reasoning, tool calling, and output limits in the live catalog.

Start Building With StepFun

Choose a StepFun model, copy its model ID, create a TokenHub API key, and send your first request through one compatible API workflow.

View StepFun Models Get API key