StepAudio 3 Chat API

Audio and text conversation model that reasons before answering, with function calling and JSON output.

StepFun Text Generation 256K context Released Sep 9, 2026 International Proprietary Endpoint

About StepAudio 3 Chat

Audio and text conversation model that reasons before answering, with function calling and JSON output.

Text output is exposed through Chat Completions, Responses, Messages, and Gemini-compatible generateContent. Linkup web search is available through web_search_linkup for text prompts and adds $0.013 per call when invoked.

Also known as StepFun StepAudio 3 Chat

reasoning audio in function calling structured output multimodal

StepAudio 3 Chat specs

Model ID
stepaudio-3-chat
Author
StepFun
Category
Text Generation
Released
Sep 9, 2026
Context window
256K tokens
Max output
131,072 tokens
Input
TextAudio
Output
Text
Structured output
JSON Mode
Region
International
Endpoints
POST/v1/chat/completions
Alternate model IDs
stepaudio-3-chat-previewstepfun/stepaudio-3-chat

StepAudio 3 Chat API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Input
per 1M prompt tokens
$1.50
Output
per 1M generated tokens
$3.50
Implicit cache read
per 1M cached input tokens
$0.30
Web Search (Linkup)
per call when invoked
$0.013
Compare on the full pricing page

How to call the StepAudio 3 Chat API

StepAudio 3 Chat serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id stepaudio-3-chat. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepaudio-3-chat",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="stepaudio-3-chat",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full StepAudio 3 Chat API reference

StepAudio 3 Chat API parameters

Request parameters supported by the StepAudio 3 Chat API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
temperaturenumber0.50 to 2Sampling temperature.
top_pnumber0.90.01 to 1Nucleus sampling probability mass.
max_tokensinteger40961 to 131072Maximum output tokens. Reasoning tokens count toward this limit, so a small budget can be spent entirely on thinking and return an empty answer. Leave unset for a...
stoparray--Stop sequences.
frequency_penaltynumber0-2 to 2Penalty for repeated tokens.
modalitiesarray["text"]-Response modalities. Text output is currently exposed.
response_formatobject--OpenAI-compatible response format. Use {"type":"json_object"} for JSON object mode.
reasoning_formatenumgeneralgeneral, deepseek-styleFormat of the reasoning trace returned alongside the answer.
toolsarray--OpenAI-compatible function tools.
tool_choicestring--OpenAI-compatible tool choice.
web_search_linkupbooleanfalse-Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.
disable_formattingbooleanfalse-Return the answer without the Sources list that web search adds.

Good to know

Accepts text and audio input and replies with text. The model reasons before answering and returns its reasoning alongside the answer, and those reasoning tokens bill as output tokens. Because reasoning consumes the output budget, a small max_tokens can be spent entirely on thinking and return an empty answer; leave max_tokens unset for a sensible default, or allow at least a few thousand tokens. Function calling and JSON object output are supported. Linkup web search is available for text prompts. This model is in preview and its capabilities may change.

StepAudio 3 Chat API: common questions

How much does the StepAudio 3 Chat API cost?

On EmpirioLabs, StepAudio 3 Chat is billed pay as you go: Input $1.50 per 1M prompt tokens; Output $3.50 per 1M generated tokens; Implicit cache read $0.30 per 1M cached input tokens; Web Search (Linkup) $0.013 per call when invoked. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does StepAudio 3 Chat support?

StepAudio 3 Chat takes Text, Audio as input and returns Text.

What is the context window of StepAudio 3 Chat?

StepAudio 3 Chat supports a 256K-token context window with up to 131,072 output tokens per response.

Is the StepAudio 3 Chat API OpenAI-compatible?

Yes. StepAudio 3 Chat serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to stepaudio-3-chat.

What is the model ID for StepAudio 3 Chat?

Send stepaudio-3-chat as the model in your request. The alternate IDs stepaudio-3-chat-preview, stepfun/stepaudio-3-chat also work.

When was StepAudio 3 Chat released?

StepFun released StepAudio 3 Chat on Sep 9, 2026.

Where is StepAudio 3 Chat served from?

StepAudio 3 Chat on EmpirioLabs is served from International.

Can I try StepAudio 3 Chat in the browser before integrating?

Yes. The EmpirioLabs playground runs StepAudio 3 Chat in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a StepAudio 3 Chat API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare StepAudio 3 Chat with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.