Lyria 3 Clip Preview

google/lyria-3-clip-preview-20260330

Lyria 3 Clip Preview is a Google model that accepts text and image inputs and generates text and audio outputs. It supports a context length of 1,048,576 tokens, has no per‑token pricing, does not support tools or reasoning, and its weights are not open. The model was released on 2026-03-30.

  • structured outputs

At a glance

providergoogle
releasedMar 30, 2026
context1.0M
input / M$0

Specifications

What the API gives you

Context window
1.0M tokens
Max output
66K tokens
Input price
$0 / 1M tokens
Output price
$0 / 1M tokens
Cache read
Modalities
text, image → text, audio
Knowledge cutoff
Released
Mar 30, 2026

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.

Benchmarks

No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.