Gemini Omni 1.2 Flash API Pricing

Gemini Omni 1.2 Flash pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Gemini Omni 1.2 Flash costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

Gemini Omni 1.2 Flash cost calculator

At Google AI Studio's price ($1.50 input, $9.00 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $60.00 a day, about $1,800 a month. Change the numbers for your workload, or compare it with other models.

Gemini Omni 1.2 Flash features

Input: text, image, video. Output: text, video, audio.

• Image input
• Audio input
• Audio output
• Video input
• Reasoning

Use Gemini Omni 1.2 Flash with LiteLLM

Call Gemini Omni 1.2 Flash through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="gemini/gemini-omni-1.2-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: gemini-omni-1.2-flash
    litellm_params:
      model: gemini/gemini-omni-1.2-flash
      api_key: os.environ/GEMINI_API_KEY

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "gemini-omni-1.2-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gemini Omni 1.2 Flash FAQ

More Google models

• Gemini Omni 1.1 Flash Preview$1.50 / $9 per 1M tokens
• Gemini Omni 1.1 Flash$1.50 / $9 per 1M tokens
• Gemini Omni Flash Preview$1.50 / $9 per 1M tokens
• Gemini 4 Argon$2 / $10 per 1M tokens
• Gemini 4 Argon Cyber Permissive$4 / $20 per 1M tokens
• Gemma 4 12B IT$0.30 / $2 per 1M tokens
• Gemini 3.8 Flash Cyber$1.50 / $7.50 per 1M tokens
• Lyria Realtime Exp$0.08 per generation