GoogleFastHigh

Gemini 3.1 Flash Image Preview

Gemini 3.1 Flash with native image generation capabilities. Can generate images directly in chat responses alongside text. Features separate pricing for text and image output tokens.

500 credits

per request

Native image generation in chat

131,072 token context window

32,768 max output tokens

Multimodal input: text, image, PDF

Output modalities: image + text

Resolutions 0.5K / 1K (default) / 2K / 4K

Aspect ratios up to 1:8 and 8:1

Image search grounding, thinking, 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

131K

tokens

Max Output

33K

tokens

Training Cutoff

January 2025

Compatible SDK

OpenAI, Google AI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Image Generation

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	500	$0.50
Output Tokens	3,000	$3.00
🖼Image Output Tokens	60,000	$60.00

* 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-flash-image-preview",
  "messages": [
    {
      "role": "user",
      "content": "Explain the concept of neural style transfer in simple terms."
    }
  ],
  "max_tokens": 1000,
  "temperature": 0.7
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Array of message objects (OpenAI format)
`temperature`	float	No	1	Sampling temperature (0-2)
`top_p`	float	No	0.95	Nucleus sampling parameter
`max_tokens`	integer	No	-	Maximum output tokens. Max: 32,768. Context window (input + output): 131,072 tokens.
`stream`	boolean	No	false	Enable Server-Sent Events streaming

Examples

Text Chat

Standard text conversation

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-flash-image-preview",
  "messages": [
    {
      "role": "user",
      "content": "Explain the concept of neural style transfer in simple terms."
    }
  ],
  "max_tokens": 1000,
  "temperature": 0.7
}'

Image Generation

Generate an image through natural language conversation

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-flash-image-preview",
  "messages": [
    {
      "role": "user",
      "content": "Generate an image of a serene Japanese garden with a koi pond, cherry blossoms, and a small wooden bridge at sunset."
    }
  ],
  "max_tokens": 4096
}'