Skip to content
AI Atlas
ModelActive

Lyria 3

Googlefamily · CLIPai.google.dev/gemini-api/docs/models/lyria-3-cli

Optimized for generating short musical clips, loops, and previews up to 30 seconds.

Open in Graph
data quality59

Updated 5 h ago · first seen 11 Sept 2026

model_01M293V7W809MQTRMAF26EN9PR

Overview

Identity

Canonical model
Yesidentity confidence: highOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
None recordedofficial_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
google/lyria-3-clip-previewlyria-3-clip-previewIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

API model id

Source:Google AI for Developers (Gemini API docs)T1observed 15 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
imagetext
Input
textimage
Output
audiotext

Capabilities

  • Tool calling

    No

    Google AI for Developers (Gemini API docs) · T1

  • Structured output

    No

    Google AI for Developers (Gemini API docs) · T1

  • Reasoning

    No

    Google AI for Developers (Gemini API docs) · T1

  • Vision

    Yes

    Google AI for Developers (Gemini API docs) · T1

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:Google AI for Developers (Gemini API docs)T1observed 15 h agohigh

Max output

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Providers & Pricing3

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MOutput / 1MPer image / requestNative unitsStatusObservedSource
Google Gemini APIcheapest outputgoogle/lyria-3-clip-preview1.05Mout 65.5K——active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRoutergoogle/lyria-3-clip-preview1.05Mout 65.5K——active2 h agosince 12 Sept 2026openrouter.aiT2
Google Gemini APIlyria-3-clip-preview———— / $0.04per_request={"lyria 3 clip preview (30s)":["$0.04 per song"],"lyria 3 pro preview (full song)":["$0.08 per song"]}active1 h agosince 11 Sept 2026ai.google.devT1

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Lyria 3$0$0.20$0.40$0.60$0.80$1Sept 26Sept 26Sept 26Sept 26Sept 26Google Gemini API: first observed → $0 · 11 Sept 2026OpenRouter: first observed → $0 · 12 Sept 2026
  • Google Gemini API
  • OpenRouter
  • OpenRouterfirst observed $012 Sept 2026
  • Google Gemini APIfirst observed $011 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Lyria 3$0$0.20$0.40$0.60$0.80$1Sept 26Sept 26Sept 26Sept 26Sept 26Google Gemini API: first observed → $0 · 11 Sept 2026OpenRouter: first observed → $0 · 12 Sept 2026
  • Google Gemini API
  • OpenRouter
  • OpenRouterfirst observed $012 Sept 2026
  • Google Gemini APIfirst observed $011 Sept 2026

Versions & Artifacts0

Version history

Context windowfirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline2

Full timeline →
  • Listed by providerModelLyria 3Google

    OpenRouter lists Lyria 3 at $0 in / $0 out per 1M tokens

    openrouter
    openrouter.ai
  • Capabilities changedModelLyria 3Google

    Lyria 3: capabilities changed from ["Audio generation"] to ["audio_output"]

    CapabilitiesAudio generation→audio_outputgoogle
    ai.google.dev

Change history47

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 1 Jul 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Lyria 3 was not yet in AI Atlas on 1 Jul 2026

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
47 claims · 21 properties25 conflicting

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
CLIP → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
30 Mar 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Context windowcontext_length8conflicting claims

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
131.1K tokens → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
65.5K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities8conflicting claims

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
audio, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Input modalitiesmodalities_input5conflicting claims

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
text, image → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
lyria-3-clip-preview → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://ai.google.dev/gemini-api/docs/models/lyria-3-clip-preview → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Capabilitiescapabilities2

Claim history for Capabilities
ValueValid from → toStatusSourceConfidenceExtractor
audio_output → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic
Audio generation → supersededGoogle AI for Developers (Gemini API docs)T1highdeterministic

Capabilities rawcapabilities_raw1

Claim history for Capabilities raw
ValueValid from → toStatusSourceConfidenceExtractor
Audio generation → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Optimized for generating short musical clips, loops, and previews up to 30 seconds. → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Latest updatelatest_update1

Claim history for Latest update
ValueValid from → toStatusSourceConfidenceExtractor
2026-03 → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
google/lyria-3-clip-preview → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
30 Mar 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Structured outputstructured_output8conflicting claims

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
Yes → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
No → currentcurrentGoogle AI for Developers (Gemini API docs)T1conflicteddeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
max_tokens, response_format, seed, temperature, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Versionsversions1

Claim history for Versions
ValueValid from → toStatusSourceConfidenceExtractor
{"preview":["lyria-3-clip-preview","lyria-3-pro-preview"]} → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

21

Source tiers

T1T215 / 6

Freshest observation

5 h ago

Conflicts

25 flagged

Source documents 5

Source documents
SourceDocumentTypeTierLast observedSnapshots
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview model_pageT1· Official1 h ago23
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/models/lyria-3-clip-preview model_pageT1· Official1 h ago23
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/pricing pricingT1· Official1 h ago25
Google AI for Developers (Gemini API docs)ai.google.dev/gemini-api/docs/models model_docsT1· Official1 h ago25
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago11

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (59/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →