Gemini Omni Flash Preview
gemini-omni-flash-previewPricing
List prices at Google AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.50 | $9.00 |
What it costs a month
At Google AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,125
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,044
- Coding agent1,000 requests a day, 40K in / 2K out$2,340
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,760
Where to run it
2 hosts serve Gemini Omni Flash Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Google AI StudioLab API gemini-omni-flash-preview | $1.50 / $9.00 | gemini-omni-flash-preview | |
Vertex AICloud gemini-omni-flash-preview | $1.50 / $9.00 | gemini-omni-flash-preview |
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
- AudioImagesTextVideo
- Produces
- TextVideo
- Features
- Audio inputVideo input
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
- 11% less
- 56% less
- 75% less
Other frontier labs
- 11% less
- 41% less
- 94% less
- 50% less
Open-weight picks
- 33% less
- 41% less
- 49% less
- 80% less
Call it
Using Google AI Studio's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="gemini-omni-flash-preview", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-omni-flash-preview:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="gemini/gemini-omni-flash-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemini Omni Flash Preview cost?
On Google AI Studio, Gemini Omni Flash Preview costs $1.50 per million input tokens and $9.00 per million output tokens.
Which APIs offer Gemini Omni Flash Preview?
Gemini Omni Flash Preview runs on 2 APIs: Google AI Studio and Vertex AI.
What is Gemini Omni Flash Preview's context window?
131K tokens, with up to 66K tokens in one reply.
Is Gemini Omni Flash Preview being retired?
It has been retired: Vertex AI retired it on 6 Nov 2026.
What are cheaper alternatives to Gemini Omni Flash Preview?
Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (11% less), Grok 4.7 on xAI (11% less), GPT-6.1 Terra on OpenAI (41% less) and Qwen4 Max on Alibaba DashScope (33% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Gemini Omni Flash Preview's API model id?
Use gemini-omni-flash-preview with Google AI Studio.
Sources
Raw catalog entry for gemini-omni-flash-preview on Google AI Studio
{
"input_cost_per_audio_token": 0.0000015,
"input_cost_per_token": 0.0000015,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 0.000009,
"output_cost_per_token": 0.000009,
"output_cost_per_video_token": 0.0000175,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/deprecations",
"supported_endpoints": [
"/v1beta/interactions"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"video"
],
"supports_audio_input": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_video_input": true,
"supports_vision": true,
"tpm": 800000,
"deprecation_date": "2026-10-22",
"deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations",
"successor_model": "gemini/gemini-omni-1.2-flash"
}