Gemini 3.7 Flash
by Vercel AI Gateway · family gemini-flash · listed Aug 2026RTV
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Current rates USD per 1M tokens
Input$0.75
Output$3.75
Cache read$0.075
Cache write—
Against the market
On the record
- Model id
google/gemini-3.7-flash- Context window
- 1M tokens
- Max output
- 66K tokens
- Input modalities
- text, image, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Mar 2026
- Released
- 2026-08-13
- Last updated
- 2026-08-13
Back of the envelope
≈
Also listed at
- Perplexity Agent$0.75 in · $3.75 out
- OpenCode$0.75 in · $3.75 out
- AI/ML API$0.75 in · $3.75 out
- Ofox$0.75 in · $3.75 out
- Cloudflare AI Gateway$0.75 in · $3.75 out
- Tempr Gateway$0.75 in · $3.75 out
- Merge Gateway$0.75 in · $3.75 out
- CrossModel$0.75 in · $3.75 out
- Vertex$0.75 in · $3.75 out
- GitHub Copilot$0.75 in · $3.75 out
- 302.AI$0.75 in · $3.75 out
- DevPass (LLM Gateway)$0.75 in · $3.75 out
- LLM Gateway$0.75 in · $3.75 out
- Kilo Gateway$0.75 in · $3.75 out
- NanoGPT$0.75 in · $3.75 out