Qwen 3 Coder

Model Information

Display Name: Qwen 3 Coder

API Model ID: qwen/qwen3-coder

Category: Text To Text

Description: Qwen 3 Coder é o modelo especializado em código da Alibaba, utilizando arquitetura MoE com 480B de parâmetros totais. Estado-da-arte em geração e análise de código. **Key Features:** - 128K+ token context window - Arquitetura MoE (480B total, 35B ativos) - Especializado em 90+ linguagens - Code completion e generation - Bug detection e fixing - Code review automatizado **Capabilities:** - Geração de código em múltiplas linguagens - Debugging e error analysis - Code refactoring - Unit test generation - Documentation generation - Code explanation **Best For:** - Assistentes de programação - Code review automatizado - Geração de testes - Migração de código - Documentação técnica **Technical Specs:** - Parameters: 480B (35B active) - Context: 128K tokens - Languages: 90+ supported - License: Apache 2.0 (Open Source)

Context Window: 131,072 tokens

Max Output: 16,384 tokens

How to Use This Model

To use Qwen 3 Coder via the HInow.ai API, use the model ID: qwen/qwen3-coder

API Request Example (Chat/Text)


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

{
  "model": "qwen/qwen3-coder",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

Pricing

  • input: $0.414
  • output: $4.14

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": "qwen/qwen3-coder"

Featured: No

Documentation: https://hinow.ai/models/qwen/qwen3-coder

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

Back to Models

Qwen 3 Coder

qwen/qwen3-coder

$0.414 / $4.14
per 1M tokens (in/out)

About

Qwen 3 Coder é o modelo especializado em código da Alibaba, utilizando arquitetura MoE com 480B de parâmetros totais. Estado-da-arte em geração e análise de código.

Key Features:

  • 128K+ token context window
  • Arquitetura MoE (480B total, 35B ativos)
  • Especializado em 90+ linguagens
  • Code completion e generation
  • Bug detection e fixing
  • Code review automatizado

Capabilities:

  • Geração de código em múltiplas linguagens
  • Debugging e error analysis
  • Code refactoring
  • Unit test generation
  • Documentation generation
  • Code explanation

Best For:

  • Assistentes de programação
  • Code review automatizado
  • Geração de testes
  • Migração de código
  • Documentação técnica

Technical Specs:

  • Parameters: 480B (35B active)
  • Context: 128K tokens
  • Languages: 90+ supported
  • License: Apache 2.0 (Open Source)

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": "qwen/qwen3-coder",
    "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": ""
    }
  }'