Specification

Family: Gemini
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Context window: 131.1K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Max output: 8.19K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Knowledge cutoff: Jan 2025
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Modalities: audio, text, video
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Input modalities: audio, video, text
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Output modalities: audio, text
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
API model id: gemini-2.5-flash-native-audio-preview-12-2025
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Official page: ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Capabilities: Audio generation, Function calling, Live API, Search grounding, Thinking
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Latest update: 2025-09
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Versions: {"preview":["gemini-2.5-flash-native-audio-preview-12-2025"]}
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

17

Source tiers

T117

Freshest observation

2 h ago

Conflicts

None

Modalities

Modalities: audiotextvideo
Input: audiovideotext
Output: audiotext

Capabilities

Tool calling
Yes
Google AI for Developers (Gemini API docs) · T1
Structured output
No
Google AI for Developers (Gemini API docs) · T1
Reasoning
Yes
Google AI for Developers (Gemini API docs) · T1
Vision
Unavailable
Audio
Yes
Google AI for Developers (Gemini API docs) · T1
Fine-tuning available
Unavailable

Context window: 131.1K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Max output: 8.19K tokens
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh
Knowledge cutoff: Jan 2025
Source:Google AI for Developers (Gemini API docs)T1observed 2 h agohigh

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

Current prices per 1M tokens
Provider	Input / 1M	Output / 1M	Cached in	Batch in / out	Context	Observed	Source
Google Gemini APIgemini-2.5-flash-native-audio-preview-12-2025	$0.50	$2	—	—	—	2 h ago	ai.google.devT1

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Available through 1

Google Gemini API

Price history

Input price · USD / 1M tokens

Output price · USD / 1M tokens

Google Gemini API

No hardware estimate available

Estimates need a parameter count; this model has none recorded from a source.

No lineage recorded

Lineage comes from explicit `derived_from`, `fine_tuned_from`, `distilled_from` and `quantized_from` relations stated by sources.

Papers 0

No papers linked yet.

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

22 claims · 17 properties

Familyfamily1

Claim history for Family
Value	Valid from → to	Status	Source	Confidence	Extractor
Gemini	11 Sept 2026 20:51 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Context windowcontext_length1

Claim history for Context window
Value	Valid from → to	Status	Source	Confidence	Extractor
131.1K tokens	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Max outputmax_output_tokens1

Claim history for Max output
Value	Valid from → to	Status	Source	Confidence	Extractor
8.19K tokens	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
Value	Valid from → to	Status	Source	Confidence	Extractor
Jan 2025	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Modalitiesmodalities1

Claim history for Modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
audio, text, video	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
audio, video, text	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
audio, text	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

API model idapi_model_id1

Claim history for API model id
Value	Valid from → to	Status	Source	Confidence	Extractor
gemini-2.5-flash-native-audio-preview-12-2025	11 Sept 2026 20:51 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Audioaudio1

Claim history for Audio
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Capabilitiescapabilities1

Claim history for Capabilities
Value	Valid from → to	Status	Source	Confidence	Extractor
Audio generation, Function calling, Live API, Search grounding, Thinking	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Descriptiondescription6

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
Our flagship Live API model for low-latency, bidirectional voice and video agents with native audio reasoning.	11 Sept 2026 20:59 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic
Optimized for real-time conversational agents with sub-second native audio streaming.	11 Sept 2026 20:59 UTC → 11 Sept 2026 20:59 UTC	superseded	Google AI for Developers (Gemini API docs)T1	high	deterministic
Our flagship Live API model for low-latency, bidirectional voice and video agents with native audio reasoning.	11 Sept 2026 20:53 UTC → 11 Sept 2026 20:59 UTC	superseded	Google AI for Developers (Gemini API docs)T1	high	deterministic
Optimized for real-time conversational agents with sub-second native audio streaming.	11 Sept 2026 20:53 UTC → 11 Sept 2026 20:53 UTC	superseded	Google AI for Developers (Gemini API docs)T1	high	deterministic
Our flagship Live API model for low-latency, bidirectional voice and video agents with native audio reasoning.	11 Sept 2026 20:51 UTC → 11 Sept 2026 20:53 UTC	superseded	Google AI for Developers (Gemini API docs)T1	high	deterministic
Optimized for real-time conversational agents with sub-second native audio streaming.	11 Sept 2026 20:51 UTC → 11 Sept 2026 20:51 UTC	superseded	Google AI for Developers (Gemini API docs)T1	high	deterministic

Latest updatelatest_update1

Claim history for Latest update
Value	Valid from → to	Status	Source	Confidence	Extractor
2025-09	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Reasoningreasoning1

Claim history for Reasoning
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Structured outputstructured_output1

Claim history for Structured output
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Tool callingtool_calling1

Claim history for Tool calling
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

Versionsversions1

Claim history for Versions
Value	Valid from → to	Status	Source	Confidence	Extractor
{"preview":["gemini-2.5-flash-native-audio-preview-12-2025"]}	11 Sept 2026 20:55 UTC → current	current	Google AI for Developers (Gemini API docs)T1	high	deterministic

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 →

11 Sept 2026
New modelModelGemini 2.5 Flash Native Audio (Live API)Google
New model: Gemini 2.5 Flash Native Audio (Live API) (Google)
google
ai.google.dev
11 Sept 2026
Listed by providerModelGemini 2.5 Flash Native Audio (Live API)Google
Google Gemini API lists Gemini 2.5 Flash Native Audio (Live API) at $0.5 in / $2 out per 1M tokens
google
ai.google.dev

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Google AI for Developers (Gemini API docs)	ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025	model_page	T1· Official	2 h ago	2
Google AI for Developers (Gemini API docs)	ai.google.dev/gemini-api/docs/models	model_docs	T1· Official	2 h ago	3
Google AI for Developers (Gemini API docs)	ai.google.dev/gemini-api/docs/pricing	pricing	T1· Official	2 h ago	3

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