Gemini 3.1 Pro Preview Custom Tools

Preview

Separate endpoint tuned to prioritize custom tools.

Access details: Gemini API

The model ID to use in API requests.

gemini-3.1-pro-preview-customtools

Updated Sep 23, 2026

Sources & notes

Capabilities & limits

Context window: 1M
Maximum output: 64K
Image input: Supported
Tool calling: Supported
Structured output: Supported

Pricing

USD / 1M tokens

Input: $2.00
Output: $12.00

Standard rates per million tokens. Discounts and long-context rates, where offered, are on Google's pricing page.

Full rate card 7 rates

All prices in USD.

Short-context input

$2.00 per 1M tokens

prompt <= 200K tokens

Long-context input

$4.00 per 1M tokens

prompt > 200K tokens

Short-context output

$12.00 per 1M tokens

prompt <= 200K tokens
includes thinking tokens

Long-context output

$18.00 per 1M tokens

prompt > 200K tokens
includes thinking tokens

Cached input (short context)

$0.20 per 1M tokens

prompt <= 200K tokens

Cached input (long context)

$0.40 per 1M tokens

prompt > 200K tokens

Cache storage

$4.50 per 1M tokens per hour

context caching storage

Paid tier only; no free tier in the API. The gemini-3.1-pro-preview-customtools endpoint is priced the same. Batch and Flex: $1.00 / $2.00 input and $6.00 / $9.00 output (<= / > 200K). Priority: $3.60 / $7.20 input and $21.60 / $32.40 output, cached $0.36 / $0.72, storage $8.10. Grounding with Google Search: 5,000 free requests per month shared across Gemini 3.x models, then $14 per 1,000.

Price history

Sep 23, 2026

Input $2.00 per million tokens

Sep 23, 2026

Output $12.00 per million tokens

Technical details

Parameters: Not published
Active parameters: Not published
Architecture: Based on Gemini 3 Pro, a sparse mixture-of-experts (MoE) transformer with native multimodal support
Training / knowledge cutoff: January 2025
Input modalities: Text, image, video, audio, PDF
Output modalities: Text

Release & lifecycle

First available: Feb 19, 2026
unknown: As of Sep 13, 2026
preview: As of Sep 23, 2026