Stepaudio 3 Chat
stepaudio-3-chatPricing
List prices at EmpirioLabs AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.50 | $3.50 | |
| Cached input 80% off input | $0.30 | 80% off input |
What it costs a month
At EmpirioLabs AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$605
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$558
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,002
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,440
Where to run it
1 host serve Stepaudio 3 Chat. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud stepaudio-3-chat | $1.50 / $3.50 | stepaudio-3-chat |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextAudio
- Produces
- Text
- Features
- Audio inputPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than EmpirioLabs AI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 16% less
- 25% less
- 38% less
- 90% less
Open-weight picks
- 14% less
- 57% less
- 60% less
- 66% less
Model line
Newer and older versions, at each lab's own price.
- UndatedStepaudio 3 ChatLatest$1.50 / $3.50
- UndatedStepaudio 2.5 Chat$1.50 / $3.50
Call it
Using EmpirioLabs AI's API.
from litellm import completion
response = completion(
model="empiriolabs/stepaudio-3-chat",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Stepaudio 3 Chat cost?
On EmpirioLabs AI, Stepaudio 3 Chat costs $1.50 per million input tokens and $3.50 per million output tokens. Cached input costs $0.30 per million tokens.
Which APIs offer Stepaudio 3 Chat?
Stepaudio 3 Chat runs on 1 API: EmpirioLabs AI.
What is Stepaudio 3 Chat's context window?
262K tokens, with up to 131K tokens in one reply.
Is Stepaudio 3 Chat being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Stepaudio 3 Chat?
No. Stepaudio 3 Chat is the newest model in its line.
What are cheaper alternatives to Stepaudio 3 Chat?
Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (16% less), Gemini 3.8 Flash on Google AI Studio (25% less) and Inkling on DeepInfra (14% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Stepaudio 3 Chat's API model id?
Use stepaudio-3-chat with EmpirioLabs AI.
Sources
Raw catalog entry for stepaudio-3-chat on EmpirioLabs AI
{
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 262144,
"max_output_tokens": 131072,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.0000035,
"cache_read_input_token_cost": 3e-7,
"supports_system_messages": true,
"supports_reasoning": true,
"supports_prompt_caching": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_audio_input": true,
"source": "https://empiriolabs.ai/models/stepaudio-3-chat"
}