Context
1M
Max output
66K
Serving providers
2
Cheapest input
$0.50 /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. A Vercel reseller quote is the price Vercel lists for serving this model, not the maker list price, so it moves when Vercel re-routes.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
201 t/s
tokens / second
Time to first token
0.91s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| APEX Agents | 28% | reasoning: true | — | |||||||||||||
| CritPt | 9% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 90% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 37% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 78% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 91% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 78% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||
| ||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 89% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 80% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | 10.1 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.5 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||
| ||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 51% | — | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 39% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| τ-bench Banking | 21% | reasoning: true | — | |||||||||||||
| τ²-bench | 80% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
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 detail
cost beyond the standard rate · source: models.devAudio
$1.00 / n/a
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.50 to $0.625 per 1M tokens across 2 providers, so the dearest route costs 25% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VercelRouted quoteVercel reseller quote | $0.50 | $3.00 | 1 | ||||||||||||||||
Standardgoogle/gemini-3-flash
| |||||||||||||||||||
| Databricks | $0.625 | $3.75 | 1 | ||||||||||||||||
Standarddatabricks/databricks-gemini-3-flash
| |||||||||||||||||||
| Vercel (flex)Vercel reseller quote | $0.25 | $1.50 | 1 | ||||||||||||||||
Flexgoogle/gemini-3-flash
| |||||||||||||||||||
| Vercel (long context, from 200K tokens)Vercel reseller quote | $0.50 | $3.00 | 1 | ||||||||||||||||
Long contextgoogle/gemini-3-flash
| |||||||||||||||||||
| Vercel (priority)Vercel reseller quote | $0.90 | $5.40 | 1 | ||||||||||||||||
Prioritygoogle/gemini-3-flash
| |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$340
estimated / month
Model IDs
copy the exact identifier for your platformgoogle/gemini-3-flashgoogle/gemini-3-flashgoogle/gemini-3-flashdatabricks/databricks-gemini-3-flashgoogle/gemini-3-flash
Frequently asked questions
Gemini 3 Flash pricing, context and availabilityHow much does Gemini 3 Flash cost?
Gemini 3 Flash costs $0.50 per 1M input tokens as a Vercel reseller quote, and $3.00 per 1M output tokens as a Vercel reseller quote. A Vercel reseller quote is the price Vercel lists for serving this model, not the maker list price, so it moves when Vercel re-routes. Across 2 serving providers, input prices range from $0.50 to $0.625 per 1M tokens.
What is the context window of Gemini 3 Flash?
Gemini 3 Flash accepts up to 1M tokens of context and can return up to 66K output tokens.
Which providers serve Gemini 3 Flash?
Gemini 3 Flash is available from 2 serving providers, each with its own pricing and model ID. Vercel is currently the cheapest, as a routed quote.
What can Gemini 3 Flash do?
Gemini 3 Flash supports image input (vision), tool use, audio input and prompt caching.
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