Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Google / Gemini

Gemini 2.5 Flash live preview

Speech generation model offered through the Gemini API.

Speech & voice
previewClosed weightsSpeech generationReasoningAgents
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
23 of 27 specification fields collected
Input token limit131.1K131,072 tokens
Maximum output8.2K8,192 tokens
Input billingSee ratesGoogle Gemini API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Input token limit
131,072 tokensSource for Input token limit (opens in a new tab)

Provider input-token limit.

Maximum output
8,192 tokensSource for Maximum output (opens in a new tab)
Input modalities
Audio, Video, TextSource for Input modalities (opens in a new tab)

Audio, video, text

Output modalities
Audio, TextSource for Output modalities (opens in a new tab)

Audio and text

Reasoning
SupportedSource for Reasoning (opens in a new tab)

Supported

Tool calling
SupportedSource for Tool calling (opens in a new tab)

Supported

Structured output
Not supportedSource for Structured output (opens in a new tab)

Not supported

Streaming
SupportedSource for Streaming (opens in a new tab)

Live API support. This does not infer SSE support for other endpoints.

Batch processing
Not supportedSource for Batch processing (opens in a new tab)

Not supported

Fine-tuning
Not collected
Knowledge cutoff
January 2025Source for Knowledge cutoff (opens in a new tab)
Release date
2025-12-12Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Audio generation
SupportedSource for Audio generation (opens in a new tab)

Supported

Context caching
Not supportedSource for Context caching (opens in a new tab)

Not supported

Code execution
Not supportedSource for Code execution (opens in a new tab)

Not supported

File search
SupportedSource for File search (opens in a new tab)

Not Supported

Google Maps grounding
Not supportedSource for Google Maps grounding (opens in a new tab)

Not supported

Image generation
Not supportedSource for Image generation (opens in a new tab)

Not supported

Live API
SupportedSource for Live API (opens in a new tab)

Supported

Search grounding
SupportedSource for Search grounding (opens in a new tab)

Supported

URL context
Not supportedSource for URL context (opens in a new tab)

Not supported

Flex inference
Not supportedSource for Flex inference (opens in a new tab)

Not supported

Priority inference
Not supportedSource for Priority inference (opens in a new tab)

Not supported

Model card updated
September 2025Source for Model card updated (opens in a new tab)

Card update month, not a release date.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Google Gemini API

Provider source (opens in a new tab)
API model ID
gemini-2.5-flash-native-audio-preview-12-2025
Access
Existing-user access restriction documented for the listed Gemini 2.5 models. Account, tier and region requirements also apply.
Regions
See Google supported-region and account requirements; region-specific availability not yet collected.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text tokensInput1$0.501M text tokens
Audio/video tokensInput1$3.001M audio/video tokens
Text tokensOutput1$2.001M text tokens
Audio tokensOutput1$12.001M audio tokens

Rate conditions

  1. Standard paid-tier native-audio rate; input and output modalities are billed separately.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Google-documented proprietary hosted release in the Gemini API model catalog. No public weights identified for this release in the reviewed documentation; public-weight Gemma models are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Gemini API release12 Dec 2025Source (opens in a new tab)
Earliest possible Gemini API shutdown17 Nov 2026Source (opens in a new tab)

Sources reviewed