Gemini 3.1 Pro (Preview)
A preview Gemini Pro model with a 1,048,576-token input limit and a 200K-token pricing threshold.
Google describes it as
“Our 3rd generation Pro model, built for multimodal understanding, agentic capabilities, and vibe-coding.”
Last verified:
Key facts
- Context window
- 1,048,576
- Max output
- 65,536
- Input price
- $2.00
- Output price
- $12.00
- Max input
- 1,048,576
- Released
- Feb 19, 2026
- API model ID
- gemini-3.1-pro-preview
tokens
tokens
$4.00 above 200K tokens
$18.00 above 200K tokens
tokens
- Google's page lists an input token limit of 1,048,576; it does not use the term context window.
About Gemini 3.1 Pro (Preview)
Gemini 3.1 Pro is a preview model that Google describes as its third-generation Pro model, built for multimodal understanding, agentic capabilities and vibe-coding. It takes text, image, video, audio and PDF input and returns text. It is the one Gemini model here with a prompt-length price tier: $2 input and $12 output per million tokens up to 200K-token prompts, and $4 and $18 above.
API pricing
Per-token API prices from the provider's pricing page. Thresholds and processing modes are shown explicitly, not folded into one number.
| Rate | Prompts up to 200,000 tokens | Prompts over 200,000 tokens |
|---|---|---|
| Input | $2.00 | $4.00 |
| Cached input | $0.20 | $0.40 |
| Output | $12.00 | $18.00 |
| Cache storage, per 1M tokens per hour | $4.50 | $4.50 |
| Rate | Prompts up to 200,000 tokens | Prompts over 200,000 tokens |
|---|---|---|
| Input | $1.00 | $2.00 |
| Cached input | $0.20 | $0.40 |
| Output | $6.00 | $9.00 |
| Cache storage, per 1M tokens per hour | $4.50 | $4.50 |
| Rate | Prompts up to 200,000 tokens | Prompts over 200,000 tokens |
|---|---|---|
| Input | $3.60 | $7.20 |
| Cached input | $0.36 | $0.72 |
| Output | $21.60 | $32.40 |
| Cache storage, per 1M tokens per hour | $8.10 | $8.10 |
- Output prices include thinking tokens.
- Flex inference is priced the same as Batch.
- Search grounding is billed separately: 5,000 requests per month free (shared across Gemini 3 and newer models), then $14 per 1,000 requests, capped at 1,500 requests per day.
- Prompts above 200K tokens are billed at the higher rates.
- Batch cached-input pricing is listed as the same as Standard.
- No free tier for Standard, Batch or Flex.
Modalities and capabilities
What the provider documents for this model. “API tool” means it needs a provider tool or endpoint rather than being native to the model.
- Input modalities
- Text, Image, Video, Audio, PDF
- Output modalities
- Text
- ReasoningReasoning: ✓ Yes
Thinking is supported.
- Tool / function callingTool / function calling: ✓ Yes
- Structured outputsStructured outputs: ✓ Yes
- Web searchWeb search: ✓ Yes · API tool
Grounding with Google Search.
- Code executionCode execution: ✓ Yes · API tool
- Computer useComputer use: ? Not documented
Not listed on Google's model page.
- Image generationImage generation: ✕ No
Google lists image generation as not supported for this model.
- Prompt cachingPrompt caching: ✓ Yes
- Batch APIBatch API: ✓ Yes
Benchmarks
Individual named benchmarks only: there is no overall score. Vendor-reported results come from the model maker's own launch materials. Scores from different sources, versions or settings are not directly comparable.
No benchmark results are listed for this model yet.
Availability and API identifiers
| Surface | Identifier |
|---|---|
| Gemini APIA second code, gemini-3.1-pro-preview-customtools, serves the custom-tools variant. | gemini-3.1-pro-preview |
Limitations and caveats
API vs. apps. These limits and prices describe the Gemini API model. The Gemini app and Google AI plans can apply different limits and are billed through subscriptions, not per token.
- This is a preview model. Google deprecates preview models with at least two weeks' notice, so pricing, limits and availability can change.
- Google's page also lists a gemini-3.1-pro-preview-customtools endpoint that is better at prioritizing custom tools and warns of quality fluctuations when custom tools are not used.
- Computer use is not listed on this model's page. Google does not document a knowledge cutoff.
- File search is listed for this model in AI Studio only.
Sources
Last verified against these sources on Oct 31, 2026. Prices and limits change; follow the links for the live figure.
- Gemini API docs — Gemini 3.1 Pro (Preview)
Supports: status, context window, max input, max output, modalities, capabilities, pricing
OfficialChecked Oct 31, 2026
- Gemini API — Models
Supports: status
OfficialChecked Oct 31, 2026
- Gemini API — Pricing
Supports: pricing
OfficialChecked Oct 31, 2026
- Gemini API — Deprecations
Supports: release date
OfficialChecked Oct 31, 2026