Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / GOOGLE
Google's full-song music generation model for high-fidelity MP3 audio and optional lyrics, with structural coherence across verses, choruses and bridges.
PRIMARY-SOURCE VERIFIED
Google documents a 131,072-token context window. Input modalities: text + image. Output: audio + text. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
$0.08 per generated full song (Standard paid API).
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
Google Gemini API publishes $0.08 per generated full song, billed per request (Standard paid tier); no free API tier. This is NOT a token or per-second price.
Native music generation model ID: lyria-3.5. Supports text and image prompts; output includes 44.1kHz stereo MP3 audio and lyrics.
Song length can be a couple of minutes and is guided by the prompt. There is no separate publicly specified generative max_output token count applicable to finished audio.
Music generation is its own task filter; it does not participate in generative text token pricing estimates.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Lyria 3.5 since 2026-10-12.
VERIFIED CHANGE HISTORY
Baseline verified: 131,072 context · Not published max output · $0.08 per generated full song (Standard paid API)
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 77b0ad167e15…