Skip to main content
Core.Today
|
GoogleMediumUltra

Gemini 3 Flash

Google's most advanced reasoning model with state-of-the-art multimodal understanding, PhD-level reasoning, and leading coding performance.

500 credits
per request
PhD-level reasoning ability
Native multimodal (text + vision + audio + video)
Thinking/reasoning mode
1M token context window
Breakthrough mathematics capabilities

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window
1M
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 Tokens3.6$0.00
Output Tokens21.6$0.02

* 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-flash",
  "messages": [
    {
      "role": "user",
      "content": "A researcher has 5 compounds. Compound A reacts with B to form C. C reacts with D only in the presence of a catalyst E. If only 3g of E is available and each reaction consumes 1g of catalyst, what is the maximum yield of the final product if we start with 10g each of A, B, and D?"
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects (OpenAI format)
temperaturefloatNo1Sampling temperature (0-2)
top_pfloatNo0.95Nucleus sampling parameter
max_tokensintegerNo-Maximum output tokens

Examples

Advanced Reasoning

Solve a complex multi-step reasoning problem

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-flash",
  "messages": [
    {
      "role": "user",
      "content": "A researcher has 5 compounds. Compound A reacts with B to form C. C reacts with D only in the presence of a catalyst E. If only 3g of E is available and each reaction consumes 1g of catalyst, what is the maximum yield of the final product if we start with 10g each of A, B, and D?"
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}'

Code Review

Review and improve code with expert-level 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-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Provide detailed code review with severity levels and concrete fixes."
    },
    {
      "role": "user",
      "content": "Review this Python function for performance issues and security vulnerabilities, and suggest improvements."
    }
  ],
  "max_tokens": 2000,
  "temperature": 0.3
}'

Tips & Best Practices

1Use thinking_level 'high' for complex math, logic, and multi-step reasoning
2Lower temperature (0.2-0.5) for factual, analytical, and coding tasks
3Leverage the 1M context window for processing entire codebases or long documents
4Combine vision and text inputs for diagram analysis or document understanding

Use Cases

Complex reasoning tasks
Research and analysis
Code generation and review
Multimodal content understanding
Scientific problem solving

Model Info

ProviderGoogle
Version3.0
CategoryLLM
Price500 credits

API Endpoint

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