Gemini 3.8 Live Extended Thinking API Pricing

Gemini 3.8 Live Extended Thinking pricing by provider

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

Other Gemini 3.8 Live Extended Thinking prices on Google AI Studio

What Gemini 3.8 Live Extended Thinking 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 3.8 Live Extended Thinking features

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

• Function calling
• Structured output
• Image input
• Audio input
• Audio output
• Reasoning
• Web search

Use Gemini 3.8 Live Extended Thinking with LiteLLM

Call Gemini 3.8 Live Extended Thinking through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/realtime. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="gemini-3.8-live-extended-thinking",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: gemini-3.8-live-extended-thinking
    litellm_params:
      model: gemini-3.8-live-extended-thinking
      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 sk-1234" \
  -d '{
    "model": "gemini-3.8-live-extended-thinking",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gemini 3.8 Live Extended Thinking FAQ

More Google models

• Gemini 3.8 Live$0.75 / $4.50 per 1M tokens
• Gemini 3.5 Live Translate Preview$3.50 / $21 per 1M tokens
• Gemini 3.1 Flash Live Preview$0.75 / $4.50 per 1M tokens
• Gemini 3.8 Flash Cyber$1.50 / $7.50 per 1M tokens
• Gemini 3.8 Flash Lite TTS$0.50 per 1M input tokens
• Gemini 3.8 Flash TTS$0.50 per 1M input tokens
• Gemini 3 Flash Preview Search$0.50 / $3 per 1M tokens
• Gemini 3.8 Flash$0.75 / $3.75 per 1M tokens