Scheduled for retirement on Jul 21, 2027. Still available at the prices below until then.
Context
1M
Max output
66K
Serving providers
6
Cheapest input
$0.30 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
416 t/s
tokens / second
Time to first token
8.13s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.3 | default | — | |||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1139.9 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 84% | default | — | |||||||||||||||||
| Harvey Lab | 0 | default | — | |||||||||||||||||
| Humanity's Last Exam | 19% | default | — | |||||||||||||||||
| Long-Context Reasoning | 76% | default | — | |||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||
| MMMU-Pro | 79% | default | — | |||||||||||||||||
| Omniscience | 5.2 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.7 | default | — | |||||||||||||||||
| SciCode | 41% | default | — | |||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 54% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 18% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.30 to $0.375 per 1M tokens across 6 providers, so the dearest route costs 25% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aihubmix | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardaihubmix/gemini-3.5-flash-lite
| ||||||||||||||||||||
| GoogleCheapest | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgemini/gemini-3.5-flash-lite
| ||||||||||||||||||||
| OpenRouter | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgoogle/gemini-3.5-flash-lite
| ||||||||||||||||||||
| VercelVercel reseller quote | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgoogle/gemini-3.5-flash-lite
| ||||||||||||||||||||
| Vertex AI Language Models | $0.30 | $2.50 | 1 | |||||||||||||||||
Standardgemini-3.5-flash-lite
| ||||||||||||||||||||
| Databricks | $0.375 | $3.13 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gemini-3-5-flash-lite
| ||||||||||||||||||||
| OpenRouter (batch) | $0.15 | $1.25 | 1 | |||||||||||||||||
Batchgoogle/gemini-3.5-flash-lite:batch
| ||||||||||||||||||||
| Vercel (flex)Vercel reseller quote | $0.15 | $1.25 | 1 | |||||||||||||||||
Flexgoogle/gemini-3.5-flash-lite
| ||||||||||||||||||||
| Vercel is dearest at $0.54 / $4.50 | ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$260
estimated / month
Model IDs
copy the exact identifier for your platformgoogle/gemini-3.5-flash-lite:batchgoogle/gemini-3.5-flash-litegemini-3.5-flash-litegemini/gemini-3.5-flash-litegoogle/gemini-3.5-flash-litegoogle/gemini-3.5-flash-liteaihubmix/gemini-3.5-flash-litedatabricks/databricks-gemini-3-5-flash-litegoogle/gemini-3.5-flash-lite
Frequently asked questions
Gemini 3.5 Flash Lite pricing, context and availabilityIs Gemini 3.5 Flash Lite still available?
Yes. Gemini 3.5 Flash Lite is scheduled for retirement on 2027-07-21.
How much does Gemini 3.5 Flash Lite cost?
Gemini 3.5 Flash Lite costs $0.30 per 1M input tokens from Google, and $2.50 per 1M output tokens from Aihubmix. Across 6 serving providers, input prices range from $0.30 to $0.375 per 1M tokens.
What is the context window of Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite accepts up to 1M tokens of context and can return up to 66K output tokens.
Which providers serve Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite is available from 6 serving providers, each with its own pricing and model ID. Google is currently the cheapest.
What can Gemini 3.5 Flash Lite do?
Gemini 3.5 Flash Lite supports image input (vision), tool use, reasoning, audio input, prompt caching, structured output and web search.
Other Google models
compare pricing across the Google lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI