Qwen: Qwen3 Coder Next

Text input Text output
Author's Description

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.

Key Specifications
Cost
$$$$
Context
262K
Parameters
80B (Rumoured)
Released
Feb 03, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Temperature Stop Frequency Penalty Response Format Seed Tool Choice Structured Outputs Max Tokens Top P Presence Penalty Tools
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Qwen3-Coder-Next, an 80B sparse MoE model with 3B activated parameters, is designed for coding agents and local development. It exhibits a strong focus on reliability, achieving an exceptional 99% success rate across benchmarks, indicating consistent and usable responses. However, its speed performance tends to be slower, ranking in the 15th percentile. Conversely, its pricing is competitive, falling in the 52nd percentile. The model demonstrates perfect accuracy in Ethics, making it the most accurate at its price point and among models of comparable speed. It also performs well in General Knowledge (99.0% accuracy) and Coding (89.5% accuracy), ranking in the 64th percentile for both. Its ability to handle long-horizon coding tasks and complex tool usage is a key strength, supported by its native 256k context window. While its Hallucinations accuracy is 94.0%, it ranks in the 50th percentile, suggesting room for improvement in acknowledging uncertainty. A notable weakness is its performance in Reasoning, where it ranks in the 1st percentile for duration, indicating significantly longer processing times for complex problems, despite a respectable 79.6% accuracy. Its Instruction Following accuracy is moderate at 59.6%. The model's exclusive non-thinking mode simplifies integration for production coding agents.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $1.5

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Novita
Novita | qwen/qwen3-coder-next-2025-02-03 262K $0.2 / 1M tokens $1.5 / 1M tokens
Together
Together | qwen/qwen3-coder-next-2025-02-03 262K $0.5 / 1M tokens $1.2 / 1M tokens
Chutes
Chutes | qwen/qwen3-coder-next-2025-02-03 262K $0.12 / 1M tokens $0.75 / 1M tokens
Parasail
Parasail | qwen/qwen3-coder-next-2025-02-03 262K $0.12 / 1M tokens $0.75 / 1M tokens
Chutes
Chutes | qwen/qwen3-coder-next-2025-02-03 262K $0.12 / 1M tokens $0.75 / 1M tokens
Parasail
Parasail | qwen/qwen3-coder-next-2025-02-03 262K $0.15 / 1M tokens $0.8 / 1M tokens
Ionstream
Ionstream | qwen/qwen3-coder-next-2025-02-03 262K $0.12 / 1M tokens $0.75 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-coder-next-2025-02-03 262K $0.18 / 1M tokens $1.35 / 1M tokens
Ionstream
Ionstream | qwen/qwen3-coder-next-2025-02-03 262K $0.15 / 1M tokens $0.8 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen