ModelBench
Google logo
Models/Google

Google: Lyria 3 Pro Preview

Music generation model for full-length songs from text or images with vocals and structure

Source-linked lyria Closed weights Released 2026-03-25
API record Report
InputT
OutputT
Input priceNot listed
Output priceNot listed
Context131.072K
Max output8.192K
Providers3
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Lyria 3 Pro Preview
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Google lyria-3-pro-preview 1.04858M 65.536K — — — Not listed Docs ↗
OpenRouter google/lyria-3-pro-preview 1.04858M 65.536K — — — Not listed Docs ↗
Kilo Gateway google/lyria-3-pro-preview 1.04858M 65.536K — — — Not listed Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
× Tool calling No
× Structured output No
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
Google
Model family
lyria
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-03-25
Model ID
google/lyria-3-pro-preview
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Max Output Tokens65536 → 8192
Context Length1048576 → 131072
Max Output Tokens8192 → 65536
Context Length131072 → 1048576
Max Output Tokens65536 → 8192
Context Length1048576 → 131072
Max Output Tokens8192 → 65536
Context Length131072 → 1048576
Max Output Tokens65536 → 8192
Context Length1048576 → 131072
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/google/lyria-3-pro-preview
curl
curl "https://model.kyssta.lol/api/v1/models/google/lyria-3-pro-preview"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Lyria 3 Pro Preview?

Music generation model for full-length songs from text or images with vocals and structure. It is published by Google and catalogued here from Models.dev.

What is the context length of Lyria 3 Pro Preview?

Lyria 3 Pro Preview accepts up to 131.072K tokens of context and returns up to 8.192K output tokens.

Does Lyria 3 Pro Preview support tool calling and structured output?

Provider catalogs list support for image input.

Which providers serve Lyria 3 Pro Preview?

3 providers list this model: Google, OpenRouter, Kilo Gateway.

Are the weights for Lyria 3 Pro Preview open?

No. This model is served through hosted APIs only.

When was Lyria 3 Pro Preview released?

The catalog records a release date of 2026-03-25, last verified Sep 11, 2026.

More models from Google

View all →
Nano Banana Pro

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

65.536K ctx $2/M in Gemini 3.7 Flash

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

1.04858M ctx $0.75/M in Google: Gemini 3.5 Flash (batch)

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

1.04858M ctx $0.75/M in Google: Gemini 2.5 Pro (batch)

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

1.04858M ctx $0.625/M in