Qwen: Qwen3 Coder Next
Qwen3 Coder Next is an AI model from qwen with a substantial context length of 262,144 tokens and supports input in text only. It can generate up to 262,144 completion tokens and integrates tools support but lacks explicit reasoning capabilities or structured output formats. This model should be considered by those requiring tool integration for text-based tasks; however, its blended benchmark score of 35.7 across three benchmarks places it below average compared to other models in the market. Given its pricing at $0.11 per million input tokens and $0.8 per million output tokens, Qwen3 Coder Next may not offer the best value for users seeking high performance without structured outputs or advanced reasoning features.
Benchmark results
Independent, published benchmarks. Blended score 35.7 across 3 benchmarks, last refreshed 2026-07-21. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 34.8 |
| AI Index Coding | software engineering tasks | 59.8 |
| AI Index Agentic | multi-step tool-using tasks | 14.5 |
- Model ID
- qwen/qwen3-coder-next
- Vendor
- qwen
- Released
- February 2026
- Tokenizer
- Qwen
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 262,144 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.11/M input and $0.80/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.10 |
| A month of a busy support chatbot | 5M in / 2M out | $2.15 |
Similar models
Qwen: Qwen Plus 0728
Qwen: Qwen-Plus
Qwen: Qwen3 Next 80B A3B Instruct
Qwen: Qwen3 Coder Flash
Qwen: Qwen3 235B A22B Instruct 2507
Qwen: Qwen3 Coder 480B A35B
Quick answers
- How much does Qwen: Qwen3 Coder Next cost?
- $0.11 per million input tokens and $0.80 per million output tokens.
- What is Qwen: Qwen3 Coder Next's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Qwen: Qwen3 Coder Next support tool calling?
- It supports tool calling, structured output.
- Can Qwen: Qwen3 Coder Next process images?
- No, it is text-only on the input side.