Qwen3-Coder-Next
Qwen3-Coder-Next is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 256k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Family
- Qwen3-Coder
- Released
- 2026-02-03
- Context
- 256k
- Parameters
- 80B total, 3B active
- Architecture
- Mixture of Experts
- Specialization
- code
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Cheapest of 4 routes · OpenRouter
About
Qwen3-Coder-Next is an ultra-sparse Mixture-of-Experts coding agent model from Alibaba's Qwen team, released February 3, 2026 under Apache 2.0. It has 80B total parameters with 3B active at inference, delivering substantially higher throughput than comparable dense models. It supports a native 256K context window, function calling, structured outputs, Claude Code, Qwen Code, Cline, Kilo, and other scaffold templates. Benchmarks reported in the DAT-3724 datapack include SWE-Bench Pro 44.3%, SWE-Bench Resolved 70.6%, and TerminalBench 2 36.2%.
Qwen3-Coder-Next is an open-source model in the Qwen3-Coder family. The structured metadata tracks a 256k-token context window, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through AWS Bedrock, OpenRouter, Vercel AI Gateway, and 1 more, with the cheapest tracked route listed at $0.12 input and $0.8 output per 1M tokens. Headline tracked benchmarks include AIME 2024 89.0, AIME 2025 83.1, and Google-Proof Q&A 74.5.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C3 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ B1 relevant benchmark in the decision map.
Provider price ladder
Compare all 4Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.120 | $0.800 | Serverless |
| AWS Bedrock | $0.500 | $1.20 | Serverless |
| Vercel AI Gateway | $0.500 | $1.20 | Serverless |
| Novita AI | $0.200 | $1.50 | Serverless |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(8)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| AIME 2024 | 89.0 | From official technical report arXiv:2603 (accuracy) | https://arxiv.org/html/2603.00729v1 |
| AIME 2025 | 83.1 | From official technical report arXiv:2603 (accuracy) | https://arxiv.org/html/2603.00729v1 |
| Google-Proof Q&A | 74.5 | GPQA Diamond (accuracy) | https://arxiv.org/html/2603.00729v1 |
| HumanEval | 86.6 | HumanEval (pass@1) | https://arxiv.org/html/2603.00729v1 |
| LiveCodeBench | 58.9 | LiveCodeBench v6 (pass@1) | https://arxiv.org/html/2603.00729v1 |
| Massive Multitask Language Understanding | 87.7 | From official technical report arXiv:2603 (accuracy) | https://arxiv.org/html/2603.00729v1 |
| MMLU PRO | 80.5 | From official technical report arXiv:2603 (accuracy) | https://arxiv.org/html/2603.00729v1 |
| SWE-bench Verified | 71.3 | Best across SWE-Agent/MiniSWE-Agent/OpenHands scaffolds (70 (resolved) | https://arxiv.org/html/2603.00729v1 |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Frequently asked questions
What is the context window of Qwen3-Coder-Next?
Qwen3-Coder-Next has a context window of 256k tokens.
How much does Qwen3-Coder-Next cost?
Qwen3-Coder-Next pricing ranges from $0.12/1M to $0.5/1M input tokens depending on the provider.
When was Qwen3-Coder-Next released?
Qwen3-Coder-Next was released on 2026-02-03.
Which providers offer Qwen3-Coder-Next?
Qwen3-Coder-Next is available from 4 providers: AWS Bedrock, OpenRouter, Vercel AI Gateway, Novita AI.
What benchmarks has Qwen3-Coder-Next been tested on?
Qwen3-Coder-Next has been evaluated on 8 benchmarks, including AIME 2024, AIME 2025, Google-Proof Q&A, HumanEval, LiveCodeBench.
Cheapest of 4 routes · OpenRouter