gemini-3.1-flash-lite
by SAP AI Core · family gemini-flash-lite · listed May 2026RTV
Low-latency Gemini model for high-volume multimodal and agent workloads
Current rates USD per 1M tokens
Input$0.25
Output$1.50
Cache read$0.025
Cache write—
Against the market
On the record
- Model id
gemini-3.1-flash-lite- Context window
- 1.0M 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
- 2026-05-07
- Last updated
- 2026-05-07
- Provider docs
- help.sap.com/docs/sap-ai-core
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.125 in · $0.75 out
- OpenRouter$0.25 in · $1.50 out
- AIHubMix$0.25 in · $1.50 out
- DevPass (LLM Gateway)$0.25 in · $1.50 out
- Google$0.25 in · $1.50 out
- Eden AI$0.25 in · $1.50 out
- 302.AI$0.25 in · $1.50 out
- Vertex$0.25 in · $1.50 out
- Ofox$0.25 in · $1.50 out
- LLM Gateway$0.25 in · $1.50 out
- CommandCode$0.25 in · $1.50 out
- Cloudflare AI Gateway$0.25 in · $1.50 out
- OrcaRouter$0.25 in · $1.50 out
- Impossibl$0.25 in · $1.50 out
- Tempr Gateway$0.25 in · $1.50 out