impulse

Gemini 2.5 Flash Native Audio Preview

Frontier labRealtimePreview
API id gemini-2.5-flash-native-audio-preview-12-2025
Google AI Studio (2025-12 only) retires it on 31 Mar 2027 (in 132 days). 1 host keeps serving it.
Input / 1M
$0.50
at Google AI Studio
Output / 1M
$2.00
at Google AI Studio
Context window
131K
tokens
Max output
8K
tokens per reply
Hosts
1
4 listings
Released
-
date not published

Pricing

List prices at Google AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.50$2.00

What it costs a month

At Google AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$300
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$312
  • Coding agent1,000 requests a day, 40K in / 2K out$720
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,680
Use your own numbers

Where to run it

1 host serve Gemini 2.5 Flash Native Audio Preview. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
2025-09
gemini-2.5-flash-native-audio-preview-09-2025
$0.50 / $2.00
Show 3 more listings: regions, snapshots and variants
Google AI Studio
2025-09
gemini-2.5-flash-native-audio-preview-09-2025
$0.50 / $2.00
2025-12
gemini-2.5-flash-native-audio-preview-12-2025
$0.50 / $2.00
Retires 31 Mar 2027
2025-12
gemini-2.5-flash-native-audio-preview-12-2025
$0.50 / $2.00
Retires 31 Mar 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioTextImages
Produces
AudioText
Features
Audio inputAudio outputBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Google AI Studio.

Smaller Google models

No cheaper Google model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Google AI Studio's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-2.5-flash-native-audio-preview-12-2025", contents="Hello")
print(response.text)

Quick answers

How much does Gemini 2.5 Flash Native Audio Preview cost?

On Google AI Studio, Gemini 2.5 Flash Native Audio Preview costs $0.50 per million input tokens and $2.00 per million output tokens.

Which APIs offer Gemini 2.5 Flash Native Audio Preview?

Gemini 2.5 Flash Native Audio Preview runs on 1 API: Google AI Studio.

What is Gemini 2.5 Flash Native Audio Preview's context window?

131K tokens, with up to 8K tokens in one reply.

Is Gemini 2.5 Flash Native Audio Preview being retired?

Google AI Studio (2025-12 only) retires it on 31 Mar 2027. 1 host keeps serving it.

What is Gemini 2.5 Flash Native Audio Preview's API model id?

Use gemini-2.5-flash-native-audio-preview-12-2025 with Google AI Studio.

Sources

Raw catalog entry for gemini-2.5-flash-native-audio-preview-12-2025 on Google AI Studio
{
  "deprecation_date": "2027-03-31",
  "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations",
  "successor_model": "gemini/gemini-3.8-live",
  "input_cost_per_audio_token": 0.000003,
  "input_cost_per_token": 5e-7,
  "litellm_provider": "gemini",
  "max_input_tokens": 131072,
  "max_output_tokens": 8192,
  "mode": "realtime",
  "output_cost_per_audio_token": 0.000012,
  "output_cost_per_token": 0.000002,
  "source": "https://ai.google.dev/gemini-api/docs/pricing",
  "supported_endpoints": [
    "/v1/realtime"
  ],
  "supported_modalities": [
    "text",
    "audio"
  ],
  "supported_output_modalities": [
    "text",
    "audio"
  ],
  "supports_audio_input": true,
  "supports_audio_output": true,
  "gemini_native_audio": true,
  "input_cost_per_video_token": 0.000003,
  "supports_function_calling": true,
  "supports_response_schema": false,
  "supports_vision": true,
  "supports_web_search": true
}