Model Information

Display Name: Gemma 3 27B IT

API Model ID: google/gemma-3-27b-it

Category: Image To Text

Description: Gemma 3 is Google's latest state-of-the-art multimodal open model built from Gemini technology. The 27B instruction-tuned variant delivers exceptional performance for conversational AI tasks. **Key Features:** - 128K token context window for long document processing - Multimodal: processes both text and image inputs - Function calling and structured outputs (JSON) - Support for 140+ languages - Optimized for reasoning, math, and code **Capabilities:** - Text generation and chat - Image understanding and analysis - Question answering and summarization - Code generation and debugging - Function/tool calling **Technical Specs:** - Parameters: 27 billion - Precision: BF16/FP8 - Training: 14 trillion tokens - License: Gemma (Google)

Context Window: 128,000 tokens

Max Output: 8,192 tokens

How to Use This Model

To use Gemma 3 27B IT via the HInow.ai API, use the model ID: google/gemma-3-27b-it

API Request Example (Chat/Text)

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

{
  "model": "google/gemma-3-27b-it",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)

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

{
  "model": "google/gemma-3-27b-it",
  "prompt": "Your image description here"
}
              

Pricing

• input: $0.10
• output: $0.20
• image: $0.01

Available Parameters

• temperature: Controls randomness (0-2). Higher = more creative, lower = more deterministic. Default: 0.7 (Options: 0, 0.3, 0.5, 0.7, 1.0, 1.5, 2.0)
• top_p: Nucleus sampling threshold (0-1). Default: 0.9 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
• top_k: Limits sampling to top K tokens. Default: off (Options: 10, 20, 40, 50, 100)
• max_tokens: Maximum tokens to generate (1-8192). Default: 4096 (Options: 256, 512, 1024, 2048, 4096, 8192)
• repetition_penalty: Penalty for repeating tokens (0.01-5). Default: 1.0 (Options: 1.0, 1.1, 1.2, 1.5, 2.0)
• response_format: Output format for structured responses (Options: text, json_object, json_schema)

Quick Reference

To use this model, set: "model": "google/gemma-3-27b-it"

Featured: No

Documentation: https://hinow.ai/models/google/gemma-3-27b-it

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