HiNow LogoHiNow

HiCode

Model Information

Display Name: HiCode

API Model ID: hinow/hicode

Category: Text To Text

Description: HiCode is Hinow's specialized coding model featuring a Mixture-of-Experts architecture with 480B total parameters. State-of-the-art performance in code generation and analysis. **Key Features:** - 128K+ token context window - MoE architecture (480B total, 35B active) - Specialized in 90+ programming languages - Code completion and generation - Bug detection and fixing - Automated code review **Capabilities:** - Multi-language code generation - Debugging and error analysis - Code refactoring - Unit test generation - Documentation generation - Code explanation **Best For:** - Programming assistants - Automated code review - Test generation - Code migration - Technical documentation **Technical Specs:** - Parameters: 480B (35B active) - Architecture: Mixture-of-Experts - Context: 128K tokens - Languages: 90+ supported - License: Hinow Enterprise

Context Window: 131,072 tokens

Max Output: 16,384 tokens

How to Use This Model

To use HiCode via the HInow.ai API, use the model ID: hinow/hicode

API Request Example (Chat/Text)


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

{
  "model": "hinow/hicode",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}

Pricing

  • input: $0.55
  • output: $5.50

Available Parameters

  • temperature: Controls randomness (0-2). Default: 0.3 for code (Options: 0, 0.1, 0.3, 0.5, 0.7, 1.0)
  • top_p: Nucleus sampling (0-1). Default: 0.9 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
  • max_tokens: Max tokens to generate (1-16384) (Options: 256, 512, 1024, 2048, 4096, 8192, 16384)
  • repetition_penalty: Reduce repetition (0.01-5). Default: 1 (Options: 1.0, 1.1, 1.2, 1.5, 2.0)
  • response_format: Output format (Options: text, json_object)
  • stop: Stop sequences (array of strings)

Quick Reference

To use this model, set: "model": "hinow/hicode"

Featured: Yes

Documentation: https://hinow.ai/models/hinow/hicode

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

Back to Models

HiCode

Featured

hinow/hicode

$0.550 / $5.50
per 1M tokens (in/out)

About

HiCode is Hinow's specialized coding model featuring a Mixture-of-Experts architecture with 480B total parameters. State-of-the-art performance in code generation and analysis.

Key Features:

  • 128K+ token context window
  • MoE architecture (480B total, 35B active)
  • Specialized in 90+ programming languages
  • Code completion and generation
  • Bug detection and fixing
  • Automated code review

Capabilities:

  • Multi-language code generation
  • Debugging and error analysis
  • Code refactoring
  • Unit test generation
  • Documentation generation
  • Code explanation

Best For:

  • Programming assistants
  • Automated code review
  • Test generation
  • Code migration
  • Technical documentation

Technical Specs:

  • Parameters: 480B (35B active)
  • Architecture: Mixture-of-Experts
  • Context: 128K tokens
  • Languages: 90+ supported
  • License: Hinow Enterprise

Capabilities

Text To Text
Context131K tokens
Max Output16K tokens

Parameters

temperature

Controls randomness (0-2). Default: 0.3 for code

00.10.30.50.71.0
top_p

Nucleus sampling (0-1). Default: 0.9

0.10.50.70.90.951.0
max_tokens

Max tokens to generate (1-16384)

256512102420484096819216384
repetition_penalty

Reduce repetition (0.01-5). Default: 1

1.01.11.21.52.0
response_format

Output format

textjson_object
stop

Stop sequences (array of strings)

Code Examples

curl -X POST https://api.hinow.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "hinow/hicode",
    "messages": [
      {"role": "user", "content": "Hello! How are you?"}
    ],
    "parameters": {
      "temperature": "0",
      "top_p": "0.1",
      "max_tokens": "256",
      "repetition_penalty": "1.0",
      "response_format": "text",
      "stop": ""
    }
  }'