Gemini 3 Flash
Gemini 3 Flash delivers Gemini 3's pro-grade reasoning at flash-level latency and cost, outperforming Gemini 2.5 Pro across most benchmarks with meaningful gains in token efficiency.
ReasoningTool UseFile InputVision (Image)Web Searchtiered-costImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'google/gemini-3-flash', prompt: 'Why is the sky blue?'})More models by Google
| Model |
|---|
| 1M | 1.8s | 196tps | $1.50/M | $7.50/M | Read:$0.15/M Write:— | $14/K + input costs | +3 |   | 07/21/2026 | |||
| 1M | 2.1s | 187tps | $1.50/M | $9/M | Read:$0.15/M Write:— | $14/K + input costs | +3 | | 05/19/2026 | |||
| 1M | 0.6s | 250tps | $0.25/M | $1.50/M | Read:$0.03/M Write:— | $14/K + input costs | +3 | | 03/03/2026 | |||
| 1M | 4.2s | 112tps | $2/M | $12/M | Read: $0.2/M Write: — | $14/K + input costs | +3 | | 02/19/2026 | |||
| 1M | 0.3s | 253tps | $0.10/M | $0.40/M | Read:$0.01/M Write:— | $35/K + input costs | +3 | | 06/17/2025 | |||
| 1M | 0.4s | 200tps | $0.30/M | $2.50/M | Read:$0.03/M Write:— | $35/K + input costs | +3 | | 03/20/2025 |