Suno v4.5 API
AI AudioSuno v4.5 is OmniaKey's first live music route: describe a style and let the model write the words, or send your own lyrics with a style tag, and one finished song comes back through the same asynchronous media API as images and video.
- Per successful call$0.30
- OperationsText to music
- Last verified2026-09-15
- View tool pricing and billing rules
Your result will appear here once you run the model.
01
Where it fits
Suno v4.5 is OmniaKey's first live music route: describe a style and let the model write the words, or send your own lyrics with a style tag, and one finished song comes back through the same asynchronous media API as images and video.
Use Suno v4.5 for demos, background tracks, jingles and lyric drafts at $0.30 per generation. Each generation returns one finished song and bills once whether or not you send lyrics.
02
What it does
Text to music
suno-v4.5
Turn a style description and optional lyrics into a finished song.
03
Call it
Media models run asynchronously. Create a task, poll it until it finishes, then download the signed asset URL.
# 1. Create the job. 202 Accepted; the body carries the task id,
# the pre-charged price, and a poll_url. Reuse one Idempotency-Key
# across retries so a timeout never starts a second paid job.
curl --fail-with-body https://api.omniakey.com/v1/media/tasks \
-H "Authorization: Bearer $OMNIAKEY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: suno-v4.5-001" \
-d '{
"model": "suno-v4.5",
"type": "audio",
"operation": "generate",
"input": {"prompt": "a paper boat on a quiet lake at sunset"},
"parameters": {"title": "Paper Boats"}
}'
# 2. Description mode sends input.prompt alone and lets the model write
# the words. Custom lyrics mode adds input.lyrics plus the style:
# {"prompt": "indie folk", "lyrics": "[Verse] ..."} —
# parameters.style (or .tags) overrides the style, and
# parameters.instrumental: true drops the vocal entirely.
# 3. Poll GET /v1/media/tasks/{id} until status is
# succeeded | failed | canceled. Progress carries percent and stage.
curl --fail-with-body https://api.omniakey.com/v1/media/tasks/TASK_ID \
-H "Authorization: Bearer $OMNIAKEY_API_KEY"
# 4. Download assets[0].url before expires_at, or poll again for a
# fresh signed URL. Failed and canceled jobs are refunded.
curl -sS -o out.mp3 "$(jq -r '.assets[0].url' result.json)"04
Pricing
Music jobs are billed per successful generation, not per token. Failed or canceled jobs are refunded automatically.
$0.30per call
Frequently asked questions
How do I call Suno v4.5 on OmniaKey?
POST to /v1/media/tasks with the model id, type "audio", and operation "generate". Send input.prompt for description mode, or add input.lyrics to sing your own words. Reuse one Idempotency-Key across retries so a timeout never starts a second paid job.
What does Suno v4.5 cost?
Suno v4.5 bills $0.30 per call per successful generation. Creation pre-charges that amount from your prepaid balance, and failed or canceled jobs are refunded automatically.
Why does the API return a task id instead of the song?
Music renders take from about thirty seconds to a few minutes, so OmniaKey runs every audio route through one asynchronous lifecycle. Poll GET /v1/media/tasks/{id} until the status is succeeded, then read the signed asset URL.