qwen
Qwen: Qwen3 Coder Next
qwen/qwen3-coder-next
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3-coder-next is an open-weight, text-only language model aimed at coding agents and local development. Per its documentation, it uses a sparse MoE architecture with 80B total and 3B activated parameters, a native 262,144-token context, and an Apache-2.0 license. Qwen reports strong agentic and tool-calling abilities plus efficiency comparable to models with far more active parameters; these are vendor claims, not independently verified here. The OpenRouter catalog confirms text I/O, tool support, and structured outputs.[1][2]
Strengths
- Sparse MoE design with 80B total and only 3B activated parameters, which the vendor positions as highly cost-effective for agent deployment.[1][2]
- Native 262,144-token context and adaptability to scaffold templates for CLI and IDE integrations such as Claude Code, Cline, and Qwen Code.[1][2]
- Broad tool-calling and structured-output support, with documented local options (Ollama, llama.cpp, LM Studio, MLX-LM, KTransformers) and OpenAI-compatible serving via vLLM or SGLang.[1][2]
Limitations
- Text-only input and output; no multimodal capability is reported in the catalog.[1]
- Non-thinking mode only: the documentation states it does not emit reasoning blocks, and the catalog lists reasoning as null.[1][2]
- Evidence is limited to the vendor model card and an aggregator catalog; headline efficiency and agentic claims are source-reported, the knowledge cutoff is unstated, and real workloads should be validated before adoption.[1][2]
Where to use it
- Agentic coding assistants that rely on tool calling and multi-step execution, matching the model's stated design target.[1][2]
- Self-hosted or local development workflows where the low activated-parameter count may reduce serving cost, subject to your own hardware testing.[1][2]
- Repository-scale code tasks that could benefit from the long context window, worth piloting if large-codebase comprehension matters.[1][2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3 Coder NextSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3 Coder NextSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- qwen/qwen3-coder-next
- Canonical ID
- qwen/qwen3-coder-next-2025-02-03
- Creator
- qwen
- Added to OpenRouter
- 04.02.2026
- Context length
- 262,144
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.120 / out $0.800
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 36.2 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.9 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Parasailbf16 | 262,144 | $0.120 | $0.800 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.