How much does Lyria 3 Pro Preview cost on Zeplik?

Input tokens cost 0 credits per million and output tokens 0 credits per million (1 credit = $0.10; the raw provider rates are $0 and $0 per million). New accounts start with free credits.

How long can a conversation with Lyria 3 Pro Preview be?

Lyria 3 Pro Preview has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.

Does Lyria 3 Pro Preview support images and tools?

Lyria 3 Pro Preview accepts image input and does not support tool calling.

Lyria 3 Pro Preview

General purposeVision

Google · Released March 2026

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API.

It is part of Google's Gemini and Gemma catalog: Pro tiers lead on capability, Flash tiers on speed and price, Nano Banana covers image generation, and Gemma models are open weight.

Facts and pricing

Provider: Google
Context window: 1.0M tokens
Input price: 0 credits / 1M tokens ($0 raw)
Output price: 0 credits / 1M tokens ($0 raw)
Vision (image input): Yes
Tool calling: No
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Zeplik composes music

Zeplik composes music with Lyria 2, a different version in the same family. Lyria 3 Pro Preview itself is not one of the engines Zeplik runs.

Open the Zeplik music tool with Lyria 2

What Lyria 3 Pro Preview is best for

Balanced everyday work: writing, questions, brainstorming and summarization
Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
Working with images: screenshots, charts, photos and scanned documents alongside text

Example prompts

Prompts that suit a general purpose model like Lyria 3 Pro Preview:

Help me outline a talk about what I learned this year
Compare these two paragraphs and tell me which is clearer and why
Draft a polite reply declining this invitation
Explain this concept with a concrete everyday analogy

Google family

Model	Context	Input cr/M	Output cr/M	Released
Gemini 4 Argon	1.0M	24.0	120	October 2026
Nano Banana 2.1	66K	18.0	90.0	October 2026
Gemini 3.8 Flash	1.0M	9.0	45.0	September 2026
Gemini 3.8 Flash (batch)	1.0M	4.5	22.5	September 2026
Gemini 3.7 Flash (batch)	1.0M	4.5	22.5	August 2026
Gemini 3.7 Flash	1.0M	9.0	45.0	August 2026
Gemini 3.6 Flash (batch)	1.0M	4.5	22.5	July 2026
Gemini 3.6 Flash	1.0M	9.0	45.0	July 2026
Gemini 3.5 Flash Lite (batch)	1.0M	1.8	15.0	July 2026
Gemini 3.5 Flash Lite	1.0M	3.6	30.0	July 2026

All 40 Google models

Model comparisons

Frequently asked questions

What is Lyria 3 Pro Preview?: Lyria 3 Pro Preview is an AI model by Google. Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API.
How much does Lyria 3 Pro Preview cost on Zeplik?: Input tokens cost 0 credits per million and output tokens 0 credits per million (1 credit = $0.10; the raw provider rates are $0 and $0 per million). New accounts start with free credits.
How long can a conversation with Lyria 3 Pro Preview be?: Lyria 3 Pro Preview has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
Does Lyria 3 Pro Preview support images and tools?: Lyria 3 Pro Preview accepts image input and does not support tool calling.

Related models

Gemini 4 ArgonFast and light

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.

1.0M ctx120 cr/M outOctober 2026

Nano Banana 2.1Fast and light

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

66K ctx90.0 cr/M outOctober 2026

Gemini 3.8 FlashFast and light

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

1.0M ctx45.0 cr/M outSeptember 2026

Gemini 3.8 Flash (batch)Fast and light

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

1.0M ctx22.5 cr/M outSeptember 2026

Gemini 3.7 Flash (batch)Fast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

1.0M ctx22.5 cr/M outAugust 2026

Gemini 3.7 FlashFast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

1.0M ctx45.0 cr/M outAugust 2026