Gemini 3.8 Live Extended Thinking pricing
Source: litellm · updated 2026-10-28
Short answer: Gemini 3.8 Live Extended Thinking costs $0.750 per million input tokens and $4.50 per million output tokens. That is a 3:1 blended rate of $1.69 per million tokens, ranking it #437 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.750 |
| Output, per 1M tokens | $4.50 |
| Output รท input multiple | 6.00× |
| 3:1 blended, per 1M tokens | $1.69 |
| Context window | 131,072 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.750 | $1.12 | $1.88 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $7.50 | $11.25 | $18.75 | ||||
| 100M in / 25M out | $75.00 | $112 | $188 |
Other gemini models
| Model | Input | Output |
|---|---|---|
| Gemini 2.5 Flash Lite Preview | $0.100 | $0.400 |
| Gemini 2.5 Flash Preview | $0.300 | $2.50 |
| Gemini Robotics Er 1.5 Preview | $0.300 | $2.50 |
| Gemini Flash Lite Latest | $0.300 | $2.50 |
| Gemini Exp 1206 | $0.300 | $2.50 |
Cheaper alternatives
Next cheaper option: GPT-3.5 Turbo Instruct at $1.50 per 1M input tokens. Next step up: Sakana Namazu at $0.950 per 1M input tokens.