Context
1M
Max output
66K
Serving providers
3
Cheapest input
$1.50 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisSpeed & latency
Output speed
188 t/s
tokens / second
Time to first token
18.79s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 18% | — | — | |||||||||||||||||
| APEX Agents | 47% | default | — | |||||||||||||||||
| ARC-AGI-2 | 72% | high | $0.850 | |||||||||||||||||
| ||||||||||||||||||||
| CritPt | 13% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval | 1348.8 | default | — | |||||||||||||||||
| GPQA Diamond | 92% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 41% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 76% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 40% | default | — | |||||||||||||||||
| Long-Context Reasoning | 71% | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 84% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | 22.7 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 53% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 46% | minimal | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 79% | default | — | |||||||||||||||||
| τ-bench Banking | 25% | default | — | |||||||||||||||||
| τ²-bench | 96% | medium | — | |||||||||||||||||
| ||||||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Vertex AICheapest | $1.50 | $9.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Vertex AICheapest | $1.50 | $9.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GoogleCheapest | $1.50 | $9.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$1,020
estimated / month
Model IDs
copy the exact identifier for your platformvertex_ai/gemini-3.5-flashgemini-3.5-flashgemini/gemini-3.5-flash
Frequently asked questions
Gemini 3.5 Flash pricing, context and availabilityHow much does Gemini 3.5 Flash cost?
Gemini 3.5 Flash costs $1.50 per 1M input tokens and $9.00 per 1M output tokens at its cheapest provider via Vertex AI.
What is the context window of Gemini 3.5 Flash?
Gemini 3.5 Flash accepts up to 1M tokens of context and can return up to 66K output tokens.
Which providers serve Gemini 3.5 Flash?
Gemini 3.5 Flash is available from 3 serving providers, each with its own pricing and model ID. Vertex AI is currently the cheapest.
What can Gemini 3.5 Flash do?
Gemini 3.5 Flash supports image input (vision), tool use, reasoning, audio input, prompt caching, structured output and web search.
Other Google models
compare pricing across the Google lineupGemini 2.5 Flash$0.15/1M · 8 providersGemma 3 27B$0.00/1M · 7 providersGemini 2.5 Pro$1.25/1M · 7 providersGemini 3 Flash Preview$0.50/1M · 5 providersGemini 3 Pro Preview$2.00/1M · 5 providersGemma 3 12B$0.05/1M · 4 providersGemini 2.0 Flash 001$0.10/1M · 4 providersGemini 3.1 Pro Preview$2.00/1M · 4 providers
Popular comparisons
head-to-head pages featuring Gemini 3.5 Flash
Gemini 3.5 Flash vs Claude Fable 5side-by-side pricing & benchmarks Gemini 3.5 Flash vs Claude Opus 4.8side-by-side pricing & benchmarks Gemini 3.5 Flash vs Claude Sonnet 5side-by-side pricing & benchmarks
Gemini 3.5 Flash vs DeepSeek V4 Proside-by-side pricing & benchmarks
Gemini 3.5 Flash vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI