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
StepAudio 3 Chat and StepAudio 2.5 Chat side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
StepFun Text GenerationStepAudio 3 Chat and StepAudio 2.5 Chat are both StepFun models in the Text Generation category, available through the EmpirioLabs API.
| Spec | StepAudio 3 Chat | StepAudio 2.5 Chat |
|---|---|---|
| Model ID | stepaudio-3-chat | stepaudio-2-5-chat |
| Author | StepFun | StepFun |
| Released | Sep 9, 2026 | - |
| Context window | 256K tokens | 256K tokens |
| Max output | 131,072 tokens | 131,072 tokens |
| Input | Text Audio | Text Audio |
| Output | Text | Text |
| Structured output | JSON Mode | JSON Mode |
| Region | International | International |
| Endpoints | POST /v1/chat/completions | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/stepaudio-2-5-chat:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | StepAudio 3 Chat | StepAudio 2.5 Chat |
|---|---|---|
| temperature | 0 to 2 Default: 0.5 | 0 to 2 Default: 0.5 |
| top_p | 0.01 to 1 Default: 0.9 | 0.01 to 1 Default: 0.9 |
| max_tokens | 1 to 131072 Default: 4096 | 1 to 131072 Default: 4096 |
| stop | array | array |
| frequency_penalty | -2 to 2 Default: 0 | -2 to 2 Default: 0 |
| modalities | array Default: ["text"] | array Default: ["text"] |
| response_format | object | object |
| reasoning_format | general, deepseek-style Default: general | - |
| tools | array | array |
| tool_choice | string | string |
| web_search_linkup | boolean Default: false | boolean Default: false |
| disable_formatting | boolean Default: false | boolean Default: false |
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.
Accepts text or base64 audio input and returns text. Linkup web search is available for text prompts.
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. Both models are called through the same endpoint. Set model to stepaudio-3-chat or stepaudio-2-5-chat. Get an API key from the EmpirioLabs dashboard.
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."}
]
}'Both models have a context window of 256K tokens. Capabilities listed only for StepAudio 3 Chat: reasoning, audio in, function calling, structured output. Capabilities listed only for StepAudio 2.5 Chat: audio input, speech understanding, prompt cache, web search. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Both models list the same rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.