Sume Music Router vs Music 1.0: same $0.125, different model ids
Both Sume music routes charge a fixed $0.125 per generation. Music Router adds a model field (sume/music-auto, lyria-3.5, lyria-3-pro); Music 1.0 is retiring.
Music Router and Music 1.0 cost the same on Sume: a fixed $0.125 per audio generation, regardless of prompt or image input. The difference is the interface. Music Router has an optional model field with three routable ids (sume/music-auto, lyria-3.5, lyria-3-pro); Music 1.0 has none. Sume's docs say Music 1.0's retirement is gradual and recommend the router for new integrations.
The comparison
Facts below come from the Sume docs and catalog.
| Item | Music Router | Music 1.0 |
|---|---|---|
| Invoke URL | POST /v1/music-router/generate | POST /v1/music-1.0/generate |
| Model id | sume/music-router | sume/music-1.0 |
| Engine choice | model: sume/music-auto, lyria-3.5 or lyria-3-pro | Runs on Google Lyria 3.5 |
| Price | $0.125 per audio | $0.125 per audio |
| Prompt length | 1 to 5,000 characters | Text prompt, optional image |
| Duration field | Rejected (control length in the prompt) | No duration parameter |
| Status | Recommended for new integrations | Routes work; resolves through the router |
What the retirement means in practice
Every Music 1.0 request already resolves through the Music Router (sume/music-auto), and the job keeps model sume/music-1.0. So switching does not change cost or, by default, the engine; it gives you the option to pin lyria-3.5 or lyria-3-pro and a catalog at GET /v1/music-router/models.
An unknown model id fails with 400 model_not_found and a catalog_url, which is a useful error to handle in a client that pins an id.
A request that works
Length is not a field. Ask for it in the prompt, for example 'A 30-second track', or with section markers such as [0:00-0:30] Intro. Sume rejects duration and duration_seconds, and it does not support a non-empty negative_prompt, so put exclusions in the positive prompt. The Music Router docs and Music 1.0 docs show the full request.
Sources
More in Comparisons
- Sume POST /v1/images (sume/auto) vs Image 1.0: which for new code
Sume's docs say Image 1.0 is retiring and is an alias for Image Router Auto. New code should use POST /v1/images. The field differences.
- Sume TTS 1.0 vs TTS Router: same $0.0475 per 1,000 characters
Sume's catalog prices TTS 1.0 and TTS Router identically: $0.0475 per 1,000 characters, 20,000-character maximum. They differ in how you pick the model.
- Sume TTS is a job, not a stream: cost and fit for a voice agent reply
A 45-second spoken reply is about 675 characters: $0.0320625 on Sume TTS, $0.010125 on MAI-Voice-2.1-Flash. Sume returns a finished file, not a live stream.
- Switching Fabric to H3 Max Lip Sync: 6 s, 12 s and 20 s clips compared
Fabric and H3 Max Lip Sync share a body on Sume, so switching is a URL change. At 6 s H3 768p is $0.60 vs Fabric 720p $1.125; at 20 s H3 Max is not eligible.
Written by Sume