AI music negative prompt: why the API returns 400
Sume's music API rejects a non-empty negative_prompt with HTTP 400. What the error looks like and how to write exclusions in the prompt instead.

A negative prompt does not work on Sume's music API: a non-empty negative_prompt returns HTTP 400 with public_reason=negative_prompt_unsupported. The docs say Music 1.0 and Lyria do not support negative prompting, so omit the field, or send an empty string, and write what you want to avoid into the positive prompt.
From the Music 1.0 and Music Router docs, read 2026-09-29.
What does a working request look like?
Move each exclusion into the prompt as a clause. The example below excludes vocals and drums.
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: exclusions-001" \
-d '{
"prompt": "Ambient piano and pad, 60 BPM, A minor. A 1-minute track. No drums, no vocals, no spoken word."
}'Which other fields are rejected?
| Field | Result |
|---|---|
negative_prompt non-empty | HTTP 400, negative_prompt_unsupported |
negative_prompt omitted or "" | Accepted |
duration / duration_seconds | Rejected as unrecognized |
prompt over 5,000 characters | Outside the 1-5,000 limit |
Unknown model on the router | 400 model_not_found with catalog_url |
Do exclusions always work?
Not always. The docs call prompt directions creative guidance, not guaranteed settings, so listen to each take. If an unwanted element appears, restate the exclusion more plainly and generate again; each take is a billed generation.
Sources
Related posts
More in Developers
- AI music API webhook: get a callback when the track is ready
Submit a music job with mode webhook and a public HTTPS URL, verify the signed callback, and keep polling as a backup. Headers, events and retries.
- AI vendor risk assessment: questions and where to look
An AI vendor risk assessment adds training, model providers and spend to a SaaS review. The questions, and where Sume's public pages answer them.
- API sandbox environment: test a paid API without paying
An API sandbox is a separate test environment with fake or free results. Sume has none, so test with its spec, free checks and spend caps.
- API throttling vs rate limiting: what's the difference?
Rate limiting refuses requests over a quota with a 429; throttling slows or queues the excess instead. What each one means for your client.
Written by Sume