Gemini 2.5 Flash vs Gemini 3.5 Flash Lite
google/gemini-2.5-flash · google/gemini-3-5-flash-lite
As of October 28, 2026, Gemini 2.5 Flash is the cheaper API on UberLLM: $0.0420 per million input tokens and $0.3500 per million output, versus $0.1500 / $1.25 for Gemini 3.5 Flash Lite — about 72% less on a blended 3:1 token mix. Both are reached through one OpenAI-compatible key and routed to the cheapest healthy seller, with no UberLLM fee added, so the price you see is the price you pay. Choose Gemini 2.5 Flash to cut cost; choose Gemini 3.5 Flash Lite when its capabilities fit your task better.
Gemini 2.5 Flash vs Gemini 3.5 Flash Lite, side by side
| Spec | Gemini 2.5 Flash | Gemini 3.5 Flash Lite |
|---|---|---|
| Price · input / 1M | $0.0420 | $0.1500 |
| Price · output / 1M | $0.3500 | $1.25 |
| Context length | 1,048,576 | 1,000,000 |
| Max output tokens | 65,535 | 65,536 |
| Input modalities | text, image | text, image, video, audio, file |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | Yes |
| Reasoning | — | Yes |
| Cheapest seller | UberLLM | UberLLM |
| % off list | 86% off | 50% off |
Live prices via UberLLM, routed to the cheapest healthy seller. The price shown has no UberLLM fee added. Updated October 28, 2026.
Gemini 2.5 Flash vs Gemini 3.5 Flash Lite — FAQ
Is Gemini 2.5 Flash or Gemini 3.5 Flash Lite cheaper?
Gemini 2.5 Flash is cheaper on a blended token mix, by about 72%. UberLLM routes every request to the cheapest healthy seller and bills the price shown, with no fee added.
What's the price difference between Gemini 2.5 Flash and Gemini 3.5 Flash Lite?
Gemini 2.5 Flash: $0.0420 in / $0.3500 out per 1M tokens. Gemini 3.5 Flash Lite: $0.1500 in / $1.25 out per 1M tokens. That's roughly a 72% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Gemini 2.5 Flash and Gemini 3.5 Flash Lite with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.