Model Information

Display Name: Gemini 3.8 Flash

API Model ID: google/gemini-3.8-flash

Category: Image To Text

Description: Gemini 3.8 Flash is Google's newest Flash-tier model — a natively multimodal model with a 1M-token context window and tunable thinking levels, built for high-throughput production workloads that still need real reasoning. **Key Features:** - 1,048,576-token context window - Up to 65K output tokens - Multimodal input: text, images, audio, video and PDFs - Tunable thinking levels (low / medium / high) - Function/tool calling and structured outputs (JSON schema) - Context caching for cheaper repeated prompts - Streaming support **Best For:** - High-volume production workloads at flash pricing - Multimodal analysis: documents, screenshots, audio and video - Agentic and tool-using workflows - Long-context reading over repository- or book-scale inputs

Context Window: 1,048,576 tokens

Max Output: 65,536 tokens

How to Use This Model

To use Gemini 3.8 Flash via the HInow.ai API, use the model ID: google/gemini-3.8-flash

API Request Example (Chat/Text)

POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "google/gemini-3.8-flash",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)

POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "google/gemini-3.8-flash",
  "prompt": "Your image description here"
}
              

Pricing

• input: $1.65
• output: $8.25
• cached: $0.165

Available Parameters

• temperature: Controls randomness (0-2). Default: 1 (Options: 0, 0.3, 0.5, 0.7, 1.0, 1.5, 2.0)
• top_p: Nucleus sampling (0-1). Default: 0.95 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
• max_tokens: Max tokens to generate (1-65536) (Options: 256, 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536)
• thinking: Reasoning level. Default: medium. This model has no minimal/off level. (Options: low, medium, high)
• response_format: Output format for structured responses (Options: text, json_object, json_schema)
• tools: Function/tool definitions for agentic workflows

Quick Reference

To use this model, set: "model": "google/gemini-3.8-flash"

Featured: No

Documentation: https://hinow.ai/models/google/gemini-3.8-flash

API Endpoint: https://api.hinow.ai/v1