Effort levels by model › Gemini 3.8 Flash
Gemini 3.8 Flash reasoning effort levels: intelligence, cost and speed
How much smarter Gemini 3.8 Flash gets at each reasoning effort, what each level costs per task, and how fast it answers. Benchmarks from Artificial Analysis.
| Effort | Intelligence Index | Gain vs. previous | Cost per task | Output tokens/s |
|---|---|---|---|---|
| medium Best intelligence per dollar | 30 | — | $6.26 | — |
| high | 31 | +1 | $7.77 | 135 |
API: $0.75 / $3.75 per 1M input / output tokens.
Source: Artificial Analysis LLM Leaderboard, checked 2026-11-02.