APIMODELSAPIMODELS
All
Models/Suno Music (v5 & v6)
Suno

Suno Music API (v5 & v6)

suno-v5

Suno writes a full song from one line, with melody, arrangement, vocals and lyrics; it also sings your lyrics and makes instrumentals, sound effects and covers, with mv picking v5, v6 or older engines. Commercial-use rights follow Suno's terms, which we cannot grant. Call suno-v5 at $0.26 per call (2 songs); failed tasks are not charged.

Songs + VocalsAuto LyricsInstrumentalSound FXContinue / CoverVoice Persona
per song (2 variants)$0.26
sound effect$0.05
API Docs

Create Music

One submission returns 2 song variants · $0.26

Result

Your 2 song variants will appear here

Prompt to Full Song

Melody, vocals + lyrics from one line

2 Variants / Run

Pick the take you like

Custom or Auto Lyrics

[Verse]/[Chorus] or let it write

More Modes

Instrumental · SFX · Cover · Persona

TL;DR Suno Music (v5 & v6) is a Suno music generation model, callable via APIMODELS' unified API (model name `suno-v5`). Pricing: per song (2 variants): $0.26, sound effect: $0.05. One API key for all image / video / LLM / audio models.

About Suno Music (v5 & v6)

Suno Music (v5 & v6) is a Music Generation API provided by Suno. Suno turns a one-line idea into a full song — melody, arrangement, vocals and lyrics. Pick the engine with the `mv` parameter — chirp-v5 (default), chirp-v6 (Suno v6, same price), chirp-v5-5, chirp-v4-5 or chirp-v4 — without changing the model name. Inspiration mode writes the lyrics for you from a short description; Custom mode sings your own lyrics (with [Verse]/[Chorus] structure) in a style you pick; Instrumental mode makes vocal-free tracks. Beyond songs it also does sound effects, continue (extend a clip), cover, and voice personas (reuse a consistent singer). Each song submission returns 2 variants with cover art and the full lyrics. Async: submit, then poll for the finished mp3s. Billed per submission ($0.26 for a song, $0.05 for a sound effect); lyric generation and persona creation are free. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: per song (2 variants): $0.26, sound effect: $0.05.

Key Features

  • Prompt to Full Song -- Melody, vocals + lyrics from one line
  • 2 Variants / Run -- Pick the take you like
  • Custom or Auto Lyrics -- [Verse]/[Chorus] or let it write
  • More Modes -- Instrumental · SFX · Cover · Persona

Use Cases

Background Music for Video

Score short-form video, YouTube and ads with original tracks — no licensing, no clearance, no royalties to track.

Game & App Soundtracks

Generate looping themes, menu music and level tracks in a consistent style, and reuse one singer across a whole soundtrack via voice personas.

Brand Jingles & Ads

Turn a tagline into a sung hook in seconds. Every call returns 2 takes, so you pick rather than re-roll.

Podcast & Stream Assets

Intros, outros, stingers and sound effects from one endpoint — songs at $0.26 per call, sound effects at $0.05.

Why APIMODELS

  • Unified API -- One API key to access all models, no need to register on multiple platforms
  • Transparent Pricing -- Pay-as-you-go with per-call pricing published on every model page, ideal for indie developers and startups
  • Instant Access -- Start right after signup; pay by card, PayPal, Alipay or USDT
  • Full Documentation -- Detailed API docs with code examples in cURL, Python, and Node.js

Frequently Asked Questions

How much does Suno Music (v5 & v6) cost?

Suno Music (v5 & v6) is available through APIMODELS at: per song (2 variants): $0.26, sound effect: $0.05. Billing is pay-as-you-go — you only pay for what you generate.

What is the difference between APIMODELS and the official Suno API?

APIMODELS offers the same Suno Music (v5 & v6) model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.

How do I call the Suno API, and how many songs do I get?

Three steps: (1) sign up at apimodels.app and create an API key; (2) POST https://api.apimodels.app/v1/audio/generations with Authorization: Bearer YOUR_API_KEY and a body like {"model":"suno-v5","prompt":"warm solo piano, cinematic, calm","title":"Quiet Morning"} to get a taskId; (3) poll until it finishes and download the mp3 (results are kept 30 days — save your own copy). Every call returns 2 takes, each with cover art and the full lyrics, so you choose instead of re-rolling. Billing is $0.26 per call — $0.13 per song — sound effects $0.05, lyric generation and persona creation free. One exception: concat mode stitches an extended clip into a single finished track, still $0.26.

Which Suno modes are supported, and how do I trigger them?

One model name, routed by which fields you send — no separate endpoints. prompt only = inspiration (it writes the lyrics); lyrics + tags = custom (it sings yours, with [Verse]/[Chorus] structure tags); make_instrumental = instrumental; continue_clip_id = extend; cover_clip_id = cover; infill_clip_id = infill (rewrite a section); underpainting = add instrumentation; overpainting = add vocals; remaster; hum-to-song from an audio clip; concat_clip_id = stitch an extended clip into one song; persona_id = reuse the same singer; task "sound" = sound effects. Lyric generation and persona creation cost nothing.

Suno v4 vs v5 — do I need a different model name?

No. The version is the mv parameter on the request: chirp-v5 (default), chirp-v6, chirp-v5-5, chirp-v4-5, chirp-v4. The model field stays "suno-v5". For Suno v6 (the generation released in September 2026) send "mv": "chirp-v6" — it costs the same as v5, $0.26 per call for 2 songs. The v5 line is stronger on song structure and vocal realism and is the sensible default; the v4 line is rougher in a way some people prefer for certain genres. To compare, fix the prompt and change only mv — since each call returns 2 takes, an A/B is quick.

How is Suno different from a text-to-speech model?

They are different categories — do not shop for one the way you shop for the other. TTS (ElevenLabs, MiniMax Speech) reads existing text aloud; the output is narration, for voiceover and audiobooks. Suno generates music: from one description it writes melody, arrangement and harmony and sings the lyrics, and the output is a finished song. Narration → TTS. Background music, intro themes, brand jingles, game soundtracks → Suno. The same API key calls both.

Can I use the generated music commercially?

Output has no watermark and downloads as a standard mp3. But copyright and commercial-use rights follow Suno’s own terms, which we cannot grant on your behalf and make no representation about — confirm the upstream terms cover your use before shipping anything commercial. There is no technical restriction: it is a plain mp3 you can re-host wherever you like.

What can Suno Music (v5 & v6) do?

Suno Music (v5 & v6) supports: Songs + Vocals, Auto Lyrics, Instrumental, Sound FX, Continue / Cover, Voice Persona. See the APIMODELS docs for full parameters and call examples.

Can I use the Suno Music (v5 & v6) API from any country, including mainland China?

Yes. APIMODELS does not restrict access by country: the site and the API answer requests from anywhere, and apimodels.app and api.apimodels.app are reachable directly from mainland China without a proxy. You call Suno Music (v5 & v6) with one APIMODELS key, so you do not need a separate account with the model's developer.

What payment methods are supported? Can I pay with PayPal or crypto?

Yes to both. You can top up with a card (Visa, Mastercard and others, through Stripe), PayPal, Alipay, or USDT on TRON (TRC20) or BNB Smart Chain (BEP20). Card, PayPal and Alipay top-ups are credited immediately; USDT is credited once the transfer confirms on-chain. Auto top-up is optional, and a $50 top-up adds a $1 bonus ($3 on a $100 top-up). The balance is in USD and billed per use, with no subscription.

Related models