GE
Gemini 2.5 Flash Native Audio - 2512
Release date: 2025-12-10Updated: 2025-12-19 15:04:00307
Parameters
Not disclosed
Context length
128K
Chinese support
Supported
Reasoning ability
Gemini 2.5 Flash Native Audio - 2512 is an AI model published by Google Deep Mind, released on 2025-12-10, for Audio model, and 128K context length.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Gemini 2.5 Flash Native Audio - 2512
Model basics
Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
8K tokens
Model type
Audio model
Modality (in / out)
Text, Audio, Video → Text, Audio, Video
Release date
2025-12-10
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini 2.5 Flash Native Audio - 2512
Open source & experience
Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Gemini 2.5 Flash Native Audio - 2512
Official resources
Paper
DataLearnerAI blog
No blog post yet
Gemini 2.5 Flash Native Audio - 2512
API details
API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $3.00/ 1M | $12.00/ 1M |
Gemini 2.5 Flash Native Audio - 2512
Benchmark Results
No benchmark data to show.
Compare with other models
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
Gemini 2.5 Flash Native Audio - 2512
Publisher
Google Deep Mind
View publisher details Gemini 2.5 Flash Native Audio - 2512
Model Overview
Gemini 2.5 Flash Native Audio - 2512 is an AI model published by Google Deep Mind, released on 2025-12-10, for Audio model, and 128K context length.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
