Skip to main content
Core.Today
|
GoogleMediumUltra

Gemini 3 Pro Preview

Google's most powerful Gemini model in preview. Features breakthrough reasoning, coding, and multimodal capabilities with the largest context window.

4 credits
per 1K tokens (avg)
1,048,576 token context window
65,536 max output tokens
Multimodal input: text, image, video, audio, PDF
Advanced reasoning and coding
Thinking, structured outputs, function calling
Search grounding, code execution, caching, Batch API
Deprecated โ€” migrate to gemini-3.1-pro-preview (shut down 2026-03-09)

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

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 TypeCreditsUSD Equivalent
Input Tokens4,000$4.00
Output Tokens24,000$24.00

* 1 credit โ‰ˆ $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-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the architectural differences between transformer and state-space models, and discuss their implications for future AI system design."
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.7
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects (OpenAI format)
temperaturefloatNo1Sampling temperature (0-2)
max_tokensintegerNo-Maximum output tokens. Max: 65,536. Context window (input + output): 1,048,576 tokens.

Examples

Complex Analysis

Leverage Gemini 3 Pro for deep analysis

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-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the architectural differences between transformer and state-space models, and discuss their implications for future AI system design."
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.7
}'

Tips & Best Practices

1Deprecated โ€” shut down 2026-03-09. Migrate to gemini-3.1-pro-preview
2Max output tokens: 65,536 โ€” set max_tokens up to this limit
3Context window 1,048,576 tokens (not 2M; updated to match Google docs)
4Use lower temperature for analytical and coding tasks

Use Cases

Complex research and analysis
Large codebase understanding
Multi-document reasoning
Scientific problem solving
Enterprise applications

Model Info

ProviderGoogle
Version3.0-preview
CategoryLLM
Price4 credits

API Endpoint

POST /llm/gemini/v1beta/openai/chat/completions
Try in PlaygroundBack to Docs