Google DeepMind logoGoogle DeepMindText

Gemini 3.1 Pro

Gemini Pro preview for grounded multimodal reasoning and precise multi-step tool workflows.

Pricing

Public Core prices are current quotes, not a locked rate.

Model details
SpecificationsPriceBenchmark priceReference price · not a OneAster quoteDiscount
Input· Context≤ 200,000tokens
200 credits / 1M tokens200 credits / 1M tokens—
Output· Context≤ 200,000tokens
1,200 credits / 1M tokens1,200 credits / 1M tokens—
Input· Context> 200,000tokens
400 credits / 1M tokens200 credits / 1M tokens—
Output· Context> 200,000tokens
1,800 credits / 1M tokens1,200 credits / 1M tokens—
Context window
1,048,576 tokens
Maximum output
65,536 tokens

Playground

Restoring conversation…

About this model

Capabilities & specifications

Input
Text · Image · Audio · Video
Output
Text
Context window
1,048,576 tokens
Maximum output
65,536 tokens

Gemini 3.1 Pro Preview refines the Gemini Pro series for reliability, tool usage and software-engineering workflows. The documented API identifier remains gemini-3.1-pro-preview, with 1,048,576 input tokens and 65,536 output tokens.

  • Long context
Text chatReasoningCoding

Build with Gemini 3.1 Pro

Manage API keys
  • Bash, cURL and jq
  • Set ONEASTER_API_KEY to your OneAster API key.
bash
response=$(curl 'https://api.oneaster.ai/v1/chat/completions' \
  --fail-with-body --silent --show-error --max-time 60 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${ONEASTER_API_KEY:?Set ONEASTER_API_KEY}" \
  --data-binary @- <<< '{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024,
  "stream": false
}') && jq -r '.choices[0].message.content' <<< "$response"

Questions and answers

Where do Gemini 3.1 Pro specifications come from?

The references below identify the sources for this model’s capabilities. Confirm current access, request limits and pricing with your service provider before integration.

Where do Gemini 3.1 Pro specifications come from?

Things to consider

Review generated results before use. Available modes and request limits depend on the service you choose; check the linked documentation before integration.

Model information sources

  • Gemini 3.1 Pro reference