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)
Most capable Gemini model
2M token context window
Native multimodal (text + vision + audio + video)
Advanced reasoning and coding
Thinking/reasoning mode
Function calling & structured output

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window
2M
tokens
Max Output
66K
tokens
Training Cutoff
February 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

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

1Most capable Gemini model - best for complex tasks
2Leverage the 2M context window for large document analysis
3Preview model - may have breaking changes
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