Binder / Google / Lyria 3 Pro Preview Google
Lyria 3 Pro Preview CTX 1.05M
Text to speech · Vision
Text Image Input Free
Text Audio Output Free
Music generation model for full-length songs from text or images with vocals and structure
MODELDEX AI TRADING CARD EVERY MODEL · DEALT AS A CARD
Flip card Drag to turn Card front showing
Google · Audio · Preview
Lyria 3 Pro Preview Music generation model for full-length songs from text or images with vocals and structure
lyria-3-pro-previewCopy ID
Type Audio
Quality Not rated yet
Context window 1,048,576 tokens
Max output 65,536 tokens
Input price Free
Output price Free
Cache read —
Cache write —
Released Mar 25, 2026
Knowledge cutoff —
Takes in Text, Image
Puts out Text, Audio
Reasoning No
Tool calling No
Structured output No
File attachments Yes
Access Free
License Proprietary
Rarity Common
Set number 839/1040 Weights aren’t public. Use is governed by Google’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: ai.google.dev.
How good is it? Public leaderboard scores for Lyria 3 Pro Preview, refreshed daily from Epoch AI and LMArena.
No public leaderboard lists Lyria 3 Pro Preview yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.
Where to run it 3 providers sell Lyria 3 Pro Preview through an API. Prices are per million tokens, cheapest first.
Free to try 3 providers Google, Kilo Gateway, OpenRouter From the lab Google Free in · Free out API providers From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.
More from Google Google
Gemini 4 Argon CTX 1.05M
Reasoning · Vision · Tools
Text Image Audio Video PDF Input $2/M
Text Output $10/M
Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents
Google
embeddinggemma-2 SIZE 744M
Embedding
Text Downloads 160K/mo
– Likes 2.6K
Embedding model from Google, 744M parameters.
Google
Gemini 3.8 Flash CTX 1.05M
Reasoning · Vision · Tools
Text Image Audio Video PDF Input $0.75/M
Text Output $3.75/M
Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows
Google
timesfm-3.0-pytorch SIZE 331M
Forecasting
Time-series forecasting model from Google, 331M parameters.
Google
Gemini 3.7 Flash CTX 1.05M
Reasoning · Vision · Tools
Text Image Audio Video PDF Input $0.75/M
Text Output $3.75/M
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Google
Gemini 3.6 Flash CTX 1.05M
Reasoning · Vision · Tools
Text Image Audio Video PDF Input $0.75/M
Text Output $3.75/M
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Google
Gemini 3.5 Flash Lite CTX 1.05M
Reasoning · Vision · Tools
Text Image Audio Video PDF Input $0.30/M
Text Output $2.50/M
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Google
Nano Banana 2 Lite CTX 66K
Image generation
Text Image Input $0.25/M
Text Image Output $30/M
Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing