Input
- Official Google
- $0.1
- Here (−50%)
- $0.05
gemini-2.5-flash-lite
Gemini 2.5 Flash-Lite API — price per token
Gemini 2.5 Flash-Lite is the cheapest Gemini model — built for massive-volume, latency-sensitive work like classification, extraction and routing.
Pricing per 1M tokens
| Rate | Official Google | Here (−50%) |
|---|---|---|
| Input | $0.1 | $0.05 |
| Cached input | $0.01 | $0.005 |
| Output | $0.4 | $0.2 |
Cached input
- Official Google
- $0.01
- Here (−50%)
- $0.005
Output
- Official Google
- $0.4
- Here (−50%)
- $0.2
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1M tokens. Max output: 64K tokens.
Best for
- Classification, extraction and summarization at massive scale.
- Latency-sensitive chat and routing layers.
- Cheap pre-processing before a Flash or Pro call.
Good to know
- Cached input bills at 10% of input ($0.01 per 1M); caching is automatic on repeated prefixes.
- Pairs well with model routing: send bulk work to Flash-Lite, hard reasoning to 3.1 Pro Preview.
How to use Gemini 2.5 Flash-Lite
Create a free account, generate one key, and point any Gemini-compatible tool at https://gemini.api.apitoken.sale with model ID gemini-2.5-flash-lite — the native /v1beta/models/gemini-2.5-flash-lite:generateContent surface works, authenticated with x-goog-api-key. New accounts include $10 of API usage at official prices — enough to test the model before topping up.
Frequently asked questions
How much does the Gemini 2.5 Flash-Lite API cost?
Officially $0.10 per 1M input tokens and $0.40 per 1M output tokens, with cached input at $0.01. With the flat 50% apiToken.sale discount that is $0.05/$0.20 — the cheapest way to run Gemini.
What is Flash-Lite good for?
High-volume, low-latency work: classification, extraction, summarization, routing and simple chat. For complex reasoning, step up to 2.5 Flash or the Gemini 3 line.
What is the model ID?
gemini-2.5-flash-lite. It works on the same apiToken.sale key and balance as every other supported Claude, GPT and Gemini model.
Run Gemini 2.5 Flash-Lite on the native Gemini API at a flat 50% off — instant key, prepaid balance, card or crypto.