Context
1M
Max output
66K
Serving providers
2
Cheapest input
$2.00 /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 AnalysisHeadline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 9% | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 91% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 40% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 70% | default | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 92% | default | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 76% | default | — | |||||||||||||
| ||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 90% | default | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 80% | default | — | |||||||||||||
| Omniscience | 15.3 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.6 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.1 | low | — | |||||||||||||
| ||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 56% | — | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 42% | default | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 87% | default | — | |||||||||||||
| ||||||||||||||||
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.devLong context (>200K)
$4.00 / $18.00
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $2.00 to $2.50 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 | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ReplicateCheapest | $2.00 | $12.00 | 1 | ||||||||||||||||
Standardreplicate/google/gemini-3-pro
| |||||||||||||||||||
| Databricks | $2.50 | $15.00 | 1 | ||||||||||||||||
Standarddatabricks/databricks-gemini-3-pro
| |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$1,360
estimated / month
Model IDs
copy the exact identifier for your platformreplicate/google/gemini-3-prodatabricks/databricks-gemini-3-pro
Frequently asked questions
Gemini 3 Pro pricing, context and availabilityHow much does Gemini 3 Pro cost?
Gemini 3 Pro costs $2.00 per 1M input tokens from Replicate, and $12.00 per 1M output tokens from Replicate. Across 2 serving providers, input prices range from $2.00 to $2.50 per 1M tokens.
What is the context window of Gemini 3 Pro?
Gemini 3 Pro accepts up to 1M tokens of context and can return up to 66K output tokens.
Which providers serve Gemini 3 Pro?
Gemini 3 Pro is available from 2 serving providers, each with its own pricing and model ID. Replicate is currently the cheapest.
What can Gemini 3 Pro do?
Gemini 3 Pro supports image input (vision), tool use, audio input and prompt caching.
Other Google models
compare pricing across the Google lineupPopular comparisons
head-to-head pages featuring Gemini 3 Pro
Gemini 3 Pro vs Claude Opus 4.5
Gemini 3 Pro vs GPT-5 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