acestep-v15-xl-sft

deepinfra/ACE-Step/acestep-v15-xl-sft

ACE-Step 1.5 XL SFT (April 2026): the highest-quality variant of the open ACE-Step 1.5 music model, a 4B diffusion transformer that generates full songs with vocals from a style prompt and lyrics in 50+ languages, with guidance control; outputs usable commercially.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/inference" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Idempotency-Key: $AUDIOLAB_REQUEST_ID" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/ACE-Step/acestep-v15-xl-sft",
  "prompt": "A mountain lake at sunrise."
}'

Input Price: $0.051 / minute
Output Price: —
Input: Text
Output: Audio

Capabilities

Explore what acestep-v15-xl-sft supports, then use the API section for a request tailored to this model.

Model Information

Provider: DeepInfra
Product: Music Generation
Release Date: Apr 2, 2026
Data Policy: Not specified
Region: US
Input: Text
Output: Audio

Provider Documentation

Playground

Try acestep-v15-xl-sft by DeepInfra. Requests use the selected workspace’s credits and API pricing.

acestep-v15-xl-sft

This model uses a dedicated input format. Explore its API example or open the supported playground.

View API reference

Providers

Compare available endpoints, pricing, and context limits for acestep-v15-xl-sft.

Provider	Context	Output	Input Price	Output Price	Endpoint
DeepInfra	Not specified	Audio	$0.051 / minute	—	`ACE-Step/acestep-v15-xl-sft`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max units	30
Path	/v1/inference
Native	{"task":"text2music","duration":30,"response_format":"mp3","negative_prompt":"","instrumental":true,"pricingBasis":"published-units-v1"}

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/inference" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Idempotency-Key: $AUDIOLAB_REQUEST_ID" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/ACE-Step/acestep-v15-xl-sft",
  "prompt": "A mountain lake at sunrise."
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepinfra/ACE-Step/acestep-v15-xl-sft` — Required model identifier.
`prompt`	View Accepted Values
`lyrics`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max units	30
Path	/v1/inference
Native	{"task":"text2music","duration":30,"response_format":"mp3","negative_prompt":"","instrumental":true,"pricingBasis":"published-units-v1"}

Similar Models

Explore more music generation and compare their capabilities.

Model	Context	Input Price	Output Price
ElevenLabs Music v2.5ElevenLabs	Not specified	$0.1275 / minute	—
Lyria 3.5Google Cloud	Not specified	$0.068 / song	—
ElevenLabs Music v2ElevenLabs	Not specified	$0.1275 / minute	—
Lyria 3 ClipGoogle Cloud	Not specified	$0.034 / song	—
ElevenLabs Music v1ElevenLabs	Not specified	$0.1275 / minute	—

View All Music Generation