🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
G

Gemini 3.8 Flash

GoogleModel IDgemini-3.8-flash
G

Gemini 3.8 Flash

GoogleModel IDgemini-3.8-flash

Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, complex enterprise workflows, multimodal reasoning, and reliable multi-step tool use. It supports a 1M-token context window, advanced thinking, function calling, structured outputs, search grounding, code execution, file search, URL context, and computer use.

ModeText / Image / File / Audio / Video → Text
Input price$0.75 / 1M tokens
Output price$3.75 / 1M tokens
Context length1048576 tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Google
Input modality
Text / Image / File / Audio / Video
Output modality
Text
Max output
65536 tokens

Pricing

ProviderBilling typePrice summary
G
Gemini-Balanced
Per token
Input price$0.75per 1M tokens
Completion price$3.75per 1M tokens
Cache read price$0.075per 1M tokens
Cache write price$0.075per 1M tokens
G
Gemini-Custom
Per token
Input price$0.75per 1M tokens
Completion price$3.75per 1M tokens
Cache read price$0.075per 1M tokens
Cache write price$0.075per 1M tokens

Integration

Code Example

curl http://127.0.0.1:4179/v1beta/models/gemini-3.8-flash:generateContent \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
google-generate-content

Supported Parameters

ParameterTypeDefaultDescription
stringmediumControls the model's reasoning depth. Supported values: low, medium, and high. Default: medium.
integer-Maximum number of output tokens. Gemini 3.8 Flash supports up to 65,536 output tokens.
booleanfalseWhether to stream the response incrementally.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.