qwen
Gemini 3.5 Flash Lite vs Qwen3.6 27B
64.0 overall · $0.915 / 1M
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite
reasoningtool callingimage inputvideo inputfile inputaudio inputprompt caching
Gemini 3.5 Flash Lite costs $0.300 per 1M input tokens and $2.50 per 1M output tokens with a 1.0M-token context window.
A reasoning, tool-calling model from google, released Jul 21, 2026. On LiveBench it scores 63.9 overall — #54 of 55 benchmarked models — and ranks highest in instruction following (#29).
- Input / 1M
- $0.300
- Output / 1M
- $2.50
- Context
- 1.0M
- LiveBench overall
- 63.9 · #54
Specs and pricing
| Input price USD per 1M prompt tokens | $0.300 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $2.50 |
| Blended price 3:1 input:output — #153 most expensive of 343 listed models | $0.850 |
| Cached input read Blank means not priced separately — not free | $0.030 |
| Cache write | $0.083 |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Input modalities | text, image, video, file, audio |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jul 21, 2026 |
Also listed as google/gemini-3.5-flash-lite:batch ($0.425 blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with Gemini 3.5 Flash Lite's rank among the 55 benchmarked models listed here. Run: gemini-3.5-flash-lite-high.
Language#50 of 55
71.8
$0.0114 measured per point
What Gemini 3.5 Flash Lite costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $252.56/mo |
| RAG assistant 8K in / 600 out × 100K requests | $282.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $288.80/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $474.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $865.00/mo |
Compare Gemini 3.5 Flash Lite with
The benchmarked models closest to it on overall score.
deepseek
Gemini 3.5 Flash Lite vs DeepSeek V4 Flash 0423
65.5 overall · $0.061 / 1M
x-ai
Gemini 3.5 Flash Lite vs SpaceXAI: Grok 4.3
62.2 overall · $1.56 / 1M
openai
Gemini 3.5 Flash Lite vs GPT-5.4 Mini
66.4 overall · $1.69 / 1M
minimax
Gemini 3.5 Flash Lite vs MiniMax M3
67.3 overall · $0.525 / 1M
nvidia
Gemini 3.5 Flash Lite vs Nemotron 3 Ultra
67.4 overall · $1.05 / 1M
Gemini 3.5 Flash Lite FAQ
How much does Gemini 3.5 Flash Lite cost?
Gemini 3.5 Flash Lite lists at $0.300 per 1M input tokens and $2.50 per 1M output tokens, with cached input reads at $0.030 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $282.00 at list price.
What is the context window of Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite accepts up to 1,048,576 tokens of context and can return up to 65,536 output tokens per response.
Does Gemini 3.5 Flash Lite support tool calling?
Yes — Gemini 3.5 Flash Lite supports tool (function) calling and exposes extended reasoning. It accepts text, image, video, file, audio input.
How does Gemini 3.5 Flash Lite score on benchmarks?
On LiveBench release 2026-06-25 (run: gemini-3.5-flash-lite-high), Gemini 3.5 Flash Lite scores 63.9 overall, ranking #54 of 55 benchmarked models.
What is the API model ID for Gemini 3.5 Flash Lite?
On OpenRouter the model ID is "google/gemini-3.5-flash-lite". It was listed on Jul 21, 2026.
More from google
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.