GoogleMediumUltra

Gemini 3.1 Pro Preview

Google's latest and most capable Gemini model in preview. Features dynamic pricing that adjusts based on context length, with enhanced pricing for inputs over 200K tokens.

500 credits

per request

Dynamic pricing (standard / long-context >200K)

Advanced reasoning and analysis

1,048,576 token context window

65,536 max output tokens

Multimodal input: text, image, audio, video, PDF

Function calling, structured outputs, thinking, search grounding, code execution, caching, Batch API

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window

1.0M

tokens

Max Output

66K

tokens

Training Cutoff

January 2025

Compatible SDK

OpenAI, Google AI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	2,000	$2.00
Output Tokens	12,000	$12.00

* 1 credit ≈ $0.001 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the current state of quantum error correction research and identify the most promising approaches for achieving fault-tolerant quantum computing by 2030."
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Array of message objects (OpenAI format). Supports text, image, video, audio, and PDF inputs.
`temperature`	float	No	1	Sampling temperature (0-2). Lower values produce more deterministic outputs.
`top_p`	float	No	0.95	Nucleus sampling parameter (0-1).
`max_tokens`	integer	No	-	Maximum output tokens. Max: 65,536. Context window (input + output): 1,048,576 tokens.
`stop`	string \| array	No	-	Up to 4 sequences where the model stops generating.
`response_format`	object	No	-	Output format constraint. Use `{ type: 'json_object' }` for structured JSON output.
`presence_penalty`	float	No	0	Penalty (-2.0 to 2.0) for repeating tokens.
`frequency_penalty`	float	No	0	Penalty (-2.0 to 2.0) by token frequency.
`seed`	integer	No	-	Seed for deterministic sampling (best-effort).
`stream`	boolean	No	false	Enable Server-Sent Events streaming.

Examples

Research Analysis

In-depth analysis with Gemini 3.1 Pro

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the current state of quantum error correction research and identify the most promising approaches for achieving fault-tolerant quantum computing by 2030."
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}'