Gemini 2.5 Flash Lite
by Qiniu · family gemini-flash-lite · listed Jun 2025TV
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
gemini-2.5-flash-lite- Context window
- 1.0M tokens
- Max output
- 64K tokens
- Input modalities
- text, image, audio, video
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Jan 2025
- Released
- 2025-06-17
- Last updated
- 2025-06-17
- Provider docs
- developer.qiniu.com/aitokenapi
Also listed at
- Poe$0.07 in · $0.28 out
- Jiekou.AI$0.095 in · $0.38 out
- Vercel AI Gateway$0.10 in · $0.40 out
- Kilo Gateway$0.10 in · $0.40 out
- AIHubMix$0.10 in · $0.40 out
- Helicone$0.10 in · $0.40 out
- Ofox$0.10 in · $0.40 out
- OpenRouter$0.10 in · $0.40 out
- Google$0.10 in · $0.40 out
- Cloudflare AI Gateway$0.10 in · $0.40 out
- OrcaRouter$0.10 in · $0.40 out
- Vertex$0.10 in · $0.40 out
- LLMTR$0.10 in · $0.10 out
- NEAR AI Cloud$0.10 in · $0.40 out
- Impossibl$0.10 in · $0.40 out