Skip to main content
Model Explorer

Qwenqwen3-coder-next

2024-05

by Qwen

StreamingChat

qwen3-coder-next by Qwen — a powerful language model optimized for chat and reasoning tasks.

Technical Specifications

Detailed technical parameters and capabilities

Context Window
128,000 tokens
Max Output
4,096 tokens
Training Cutoff
April 2024
Tokenizer
cl100k_base

Quick Integration

Get started with a single API call

quickstart.py
import openai
 
client = openai.OpenAI(
base_url="https://api.example.com/v1",
api_key="sk-ms-...",
)
 
response = client.chat.completions.create(
model="qwen3-coder-next",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Performance Benchmarks

How qwen3-coder-next compares across industry benchmarks

MMLU
60%vs 86.4%
HumanEval
55%vs 67%
GSM8K
58%vs 92%
qwen3-coder-next
GPT-4o Reference

Pricing

Pay-as-you-go

Standard Pricing

No commitments, pay only for what you use

Input$0.50 per 1M tokens
Output$2.00 per 1M tokens

Indicative pricing — final cost is confirmed at request time.

Enterprise

Volume & Enterprise

Custom pricing for high-volume workloads

  • Volume discounts available
  • Dedicated throughput guarantees
  • Fine-tuning support