Skip to content

AI model API catalog

125 model families from 19 providers on one API key. Compare inputs and live prices, then run a model in the playground or from code.

Layout

5,000

prompt characters

Suno

Suno V5.5

A single sentence describing the song's theme or mood. Output: Two alternative complete songs automatically generated, including melody, lyrics, and vocals. v5.5 delivers Suno's highest-ever audio quality in vocal realism, instrument separation, and dynamic range, capable of handling nuanced emotional expression and complex style mashups. Significantly lowers the creative barrier – no music background required to quickly produce professional-grade music.

  • Text to music
Loading price…
2 variants

5,000

prompt characters

Suno

Suno V5

A single sentence describing the song content. Output: Two complete songs automatically generated. The core upgrade of v5 is studio-grade audio quality – vocal realism is significantly improved, mix soundstage and instrument separation reach professional levels, and the "electronic/robotic" artifacts are largely eliminated. Suitable for high-quality background music production, content creator soundtracks, and quick demo generation.

  • Text to music
Loading price…
2 variants

5,000

prompt characters

Suno

Suno V4.5

Input a single sentence describing the song (style/mood/scene). The model automatically generates two alternative complete tracks. Compared to previous versions, v4.5 significantly expands the range of supported music styles and intelligently handles complex style mashups. Vocal expression is fuller, covering emotional range from whispers to powerful hooks. Low cost per generation, suitable for batch production.

  • Text to music
Loading price…
2 variants

3,000

prompt characters

ByteDance

Doubao Seed Audio 1.0

Generate audio from text with optional voice or reference media.

  • Text to audio
Loading price…
1 variant

Music and audio APIs

4 music and audio model families from 2 providers: songs from a description or your own lyrics, lyrics drafts and speech from text. Each request is an asynchronous job through POST /api/v1/jobs.

Compare every priceRead the quickstart

Questions about choosing a model

How do I call these models?

Image, video and music models are asynchronous: POST /api/v1/jobs with a model ID and an input object, then poll GET /api/v1/jobs/{id} until the task succeeds. LLMs are synchronous through POST /api/v1/chat/completions, which works with any OpenAI SDK. The quickstart has a request you can copy.

How am I charged?

From prepaid credits, with no subscription. A task's price is reserved when it is accepted and charged only when it succeeds; a failed task returns the reservation. LLMs are charged per token from the usage the model reports. Every rate is on the pricing page.

What is a model variant?

One model page can hold several model IDs: tiers such as Pro and Standard, tasks such as text to video and image to video, or a lower-priced channel. Each variant has its own model ID, input schema and price; pick one on the model page.

Which models turn my own lyrics into a song?

Suno V5.5, Suno V5 and Suno V4.5. Send the lyrics and the style tags as separate fields.

Why does a model say Price not set yet?

No price is configured for it yet, so it cannot run: the API answers MODEL_PRICE_UNAVAILABLE. The page and its schema stay available for reference.