Gemini 3.8 Flash (fast)

PRICE / USD

$0.75

Per 1 million output tokens · input billed separately

Input / 1M tokens

$0.75

Output / 1M tokens

$3.75

Cached input / 1M tokens

$0.075

Cache write / 1M tokens

Not verified

These rates end December 31, 2026. Input/output then become $1.50/$7.50 per MTok. Cache storage is extra; output includes thinking tokens.

SPEED & CAPABILITIES

236.5 tokens/s

Google API · Gemini 3.8 Flash · High reasoning. Artificial Analysis reports a rolling 72-hour median of output speed after the first token, not total response time. Checked 2026-10-05; speed varies with workload and serving conditions.

Artificial Analysis · performance methodology v2.2.0 ↗ · Checked 2026-10-05. (fast) means median output above 150 tokens/s in these settings.

Model score

41

Our own output-speed measurement

Not measured

Context window

1,000,000

API model ID

gemini-3.8-flash

Artificial Analysis tested Gemini 3.8 Flash · high. This mostly English, text-based index is not a guarantee of performance on your workload. Artificial Analysis · Gemini 3.8 Flash · high ↗

The Flash name alone is not used as evidence of measured speed.

Suggested starting role: everyday coding. The official model description emphasizes software engineering and autonomous agents. Consider it for implementation workflows; the current introductory token rates expire separately. This is editorial guidance, not a benchmark score.