HiNow LogoHiNow

Gemini 3.1 Pro

Model Information

Display Name: Gemini 3.1 Pro

API Model ID: google/gemini-3.1-pro

Category: Image To Text

Description: Gemini 3.1 Pro is Google's most powerful reasoning-first model, optimized for complex agentic workflows and coding. Features adaptive thinking for deep analysis with a 1M token context window. **Key Features:** - 1M token context window (1,048,576 tokens) - Up to 65K output tokens - Vision: text, image, audio, video input - Adaptive thinking/reasoning mode - Native function calling and structured outputs - Code execution and grounding with Google Search - Agentic workflows **Capabilities:** - Deep reasoning and complex analysis - Expert-level code generation - Multimodal understanding (text, images, video, audio) - Long-form document processing - Multi-step agentic task execution - Mathematical reasoning and proofs - Structured data extraction - Research and synthesis **Best For:** - Complex reasoning and deep analysis - Expert-level coding and architecture - Agentic workflows with multiple tools - Tasks requiring maximum accuracy - Long-context research tasks **Technical Specs:** - Model ID: gemini-3.1-pro-preview - Context Window: 1,048,576 tokens (1M) - Max Output: 65,536 tokens - Modalities: Text, image, audio, video input - API: Google AI (generativelanguage.googleapis.com) - Thinking Mode: Adaptive (auto-configured) - Tool Use: Native function calling - Status: GA (February 2026)

Context Window: 1,048,576 tokens

Max Output: 65,536 tokens

How to Use This Model

To use Gemini 3.1 Pro via the HInow.ai API, use the model ID: google/gemini-3.1-pro

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-3.1-pro",
  "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-3.1-pro",
  "prompt": "Your image description here"
}

Pricing

  • input: $2.20
  • output: $13.20

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)
  • response_format: Output format (Options: text, json_object)

Quick Reference

To use this model, set: "model": "google/gemini-3.1-pro"

Featured: Yes

Documentation: https://hinow.ai/models/google/gemini-3.1-pro

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

Back to Models

Gemini 3.1 Pro

Featured

google/gemini-3.1-pro

$2.20 / $13.20
per 1M tokens (in/out)

About

Gemini 3.1 Pro is Google's most powerful reasoning-first model, optimized for complex agentic workflows and coding. Features adaptive thinking for deep analysis with a 1M token context window.

Key Features:

  • 1M token context window (1,048,576 tokens)
  • Up to 65K output tokens
  • Vision: text, image, audio, video input
  • Adaptive thinking/reasoning mode
  • Native function calling and structured outputs
  • Code execution and grounding with Google Search
  • Agentic workflows

Capabilities:

  • Deep reasoning and complex analysis
  • Expert-level code generation
  • Multimodal understanding (text, images, video, audio)
  • Long-form document processing
  • Multi-step agentic task execution
  • Mathematical reasoning and proofs
  • Structured data extraction
  • Research and synthesis

Best For:

  • Complex reasoning and deep analysis
  • Expert-level coding and architecture
  • Agentic workflows with multiple tools
  • Tasks requiring maximum accuracy
  • Long-context research tasks

Technical Specs:

  • Model ID: gemini-3.1-pro-preview
  • Context Window: 1,048,576 tokens (1M)
  • Max Output: 65,536 tokens
  • Modalities: Text, image, audio, video input
  • API: Google AI (generativelanguage.googleapis.com)
  • Thinking Mode: Adaptive (auto-configured)
  • Tool Use: Native function calling
  • Status: GA (February 2026)

Capabilities

Image To TextText To Text
Context1049K tokens
Max Output66K tokens

Parameters

temperature

Controls randomness (0-2). Default: 1

00.30.50.71.01.52.0
top_p

Nucleus sampling (0-1). Default: 0.95

0.10.50.70.90.951.0
max_tokens

Max tokens to generate (1-65536)

2565121024204840968192163843276865536
response_format

Output format

textjson_object

Code Examples

curl -X POST https://api.hinow.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "google/gemini-3.1-pro",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image"},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
        ]
      }
    ],
    "parameters": {
      "temperature": "0",
      "top_p": "0.1",
      "max_tokens": "256",
      "response_format": "text"
    }
  }'