Gemini 3 Flash Preview
by Venice AI · family gemini · listed Dec 2025RTV
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
Current rates USD per 1M tokens
Input$0.70
Output$3.75
Cache read$0.07
Cache write—
Against the market
On the record
- Model id
gemini-3-flash-preview- Context window
- 256K tokens
- Max output
- 66K tokens
- Input modalities
- text, image, video, audio, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Jan 2025
- Released
- 2025-12-19
- Last updated
- 2026-06-11
- Provider docs
- docs.venice.ai
Back of the envelope
≈
Also listed at
- QiHang$0.07 in · $0.43 out
- Requesty$0.50 in · $3.00 out
- 302.AI$0.50 in · $3.00 out
- Google$0.50 in · $3.00 out
- ZenMux$0.50 in · $3.00 out
- Merge Gateway$0.50 in · $3.00 out
- OrcaRouter$0.50 in · $3.00 out
- LLM Gateway$0.50 in · $3.00 out
- Abacus$0.50 in · $3.00 out
- Perplexity Agent$0.50 in · $3.00 out
- Kilo Gateway$0.50 in · $3.00 out
- FrogBot$0.50 in · $3.00 out
- OpenRouter$0.50 in · $3.00 out
- Jiekou.AI$0.50 in · $3.00 out
- AIHubMix$0.50 in · $3.00 out