You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

suno-v5.5 is a music generation model based on text descriptions: a track with vocals or an instrumental in a specified genre, mood, and structure. It is suitable for background music for videos and podcasts, jingles and commercials, demo sketches, as well as personal sound experiments.

The output is a finished audio track that you can download and insert into your project. You define the genre, tempo, mood, vocal character, and structure via description; the model handles the arrangement itself. We do not specify exact bitrate or duration figures — rely on the results of your generation.

A separate reasoning mode is not noted in our data: this is a music generator, not a text model, and you should not expect step-by-step reasoning from it. The quality of the result here depends on how accurately you describe the genre, mood, and structure of the track.

Function calling and structured JSON output are not noted in our data for this model. If your scenario requires tools and strict answers, connect a text model via the unified OpenAI-compatible BotHub API, and leave the music to suno-v5.5 — you won't have to rewrite the integration.

Accepting files other than text is not noted in our data, so expect to work based on text descriptions. Describe the genre, instruments, tempo, mood, and structure of the composition: the more specific the request, the closer the result will be to what you intended. The model's context is 4095 tokens.

We do not separately claim the language capabilities of the model itself, so we won't make any promises — check it with your own request. However, BotHub itself is fully in Russian: access from Russia without a VPN or foreign card, payment with Russian cards, and pay-as-you-go.