Suno v6-wild: is there a less predictable setting on Sume?

Suno v6-wild is a paid model that is less predictable. Sume's music request has no seed, temperature or guidance field, so variety comes from the prompt.

4 min readSume
All posts

Sume has no "wild" switch: the music request takes a prompt and an optional image, with no seed, temperature, guidance or duration parameter. To get less predictable results, write a more unusual brief and vary its axes between requests. Sume does not list Suno models; omitted model routes to sume/music-auto, which is Lyria 3.5 today.

Sume details are from the Music 1.0 docs and Music Router docs, read 2026-09-30.

What does Suno say v6-wild is?

Suno's release notes (dated 2026-09-09) describe three models and who can use them.

Suno v6 models, from the Suno release notes read 2026-09-30.
ModelSuno's description
v6"reliable, precise and consistently delivers polished music across every genre and style"
v6-wild"less predictable and more varied, producing unexpected, textured and ambitious results"
v6-mini"faster, more efficient version available to everyone"

Which knobs does Sume expose?

The Music Router accepts prompt (1-5000 characters), optional image_url, optional model, and the usual communication fields. duration and duration_seconds are rejected, and a non-empty negative_prompt returns 400. Routable ids are sume/music-auto, lyria-3.5 and lyria-3-pro, listed by GET /v1/music-router/models.

How do I ask for something less conventional?

The docs give seven prompt axes: emotion, genre lineage, tempo as a number, key and mode, two to four textured instruments, an arc with one named moment, and era or production. Choose unexpected combinations, and for contrasting scenes vary genre family, tempo (at least 12 BPM apart) and lead instrument. The docs call these creative directions, not guaranteed settings, so listen to the result.

curl -X POST https://api.sume.com/v1/music-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: music-odd-001" \
  -d '{
    "prompt": "Gugak fusion with a 142 BPM half-time 808, E phrygian. Gayageum plucks through tape wow, a bowed saw answers at 0:12, breakdown to claps at 0:20. Instrumental, no vocals."
  }'

How do I submit the job and fetch the track?

A music request takes mode async, sync, subscribe or webhook. With sync or subscribe, wait_timeout_seconds is 0 to 30; with webhook, webhook_url must be a public HTTPS callback. Send an Idempotency-Key on the submit, then poll GET /v1/jobs/{job_id}/status and read GET /v1/jobs/{job_id}/result. The audio is the entry in result.artifacts[] where type is audio, hosted on media.sume.com; raw provider URLs are not public outputs. The docs list no field that trades predictability for variety.

The prompt is 1 to 5000 characters. Put exclusions in the positive prompt ("Instrumental, no vocals"), because a non-empty negative_prompt is refused. Full field list: Music Router docs.

Sources

Related posts

More in Models

All Models posts

Written by Sume