Qwen3 Coder Next
alibaba/qwen3-coder-nextBy Alibaba (Qwen) · family: qwen · released 2026-02-03 · knowledge: 2025-04
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding78
- Tool calling40/40
- Structured output20/20
- Reasoning0/10
- Context window (100K → 1M)8/20
- Provider availability10/10
Agents85
- Tool calling35/35
- Structured output25/25
- Reasoning0/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output98
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume18/20
Cost efficiency69
- Headline price (log-scaled)64/95
- Has prompt-cache pricing5/5
Long context61
- Context window (100K → 2M)51/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.97 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $1.95 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.61 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $1.71 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $1.89 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from kilo · qwen/qwen3-coder-next
Cheapest provider: alibaba-coding-plan · Unknown input + Unknown output
Available on 13 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| Alibaba Coding Plan alibaba-coding-plan | qwen3-coder-next | Unknown | Unknown | 262K | 2026-02-03 |
| Alibaba Coding Plan (China) alibaba-coding-plan-cn | qwen3-coder-next | Unknown | Unknown | 262K | 2026-02-03 |
| Amazon Bedrock amazon-bedrock | qwen.qwen3-coder-next | $0.220 | $1.80 | 131K | 2026-02-06 |
| Vercel AI Gateway vercel | alibaba/qwen3-coder-next | $0.500 | $1.20 | 256K | 2025-07-22 |
| Together AI togetherai | Qwen/Qwen3-Coder-Next-FP8 | $0.500 | $1.20 | 262K | 2026-02-03 |
| Hugging Face huggingface | Qwen/Qwen3-Coder-Next | $0.200 | $1.50 | 262K | 2026-02-03 |
| Jiekou.AI jiekou | qwen/qwen3-coder-next | $0.200 | $1.50 | 262K | 2026-02 |
| NovitaAI novita-ai | qwen/qwen3-coder-next | $0.200 | $1.50 | 262K | 2026-02-03 |
| Kilo Gateway kilo | qwen/qwen3-coder-next | $0.120 | $0.750 | 262K | 2026-02-02 |
| Ollama Cloud ollama-cloud | qwen3-coder-next | Unknown | Unknown | 262K | 2026-02-02 |
| Cortecs cortecs | qwen3-coder-next | $0.158 | $0.840 | 256K | 2026-02-04 |
| LLM Gateway llmgateway | qwen3-coder-next | $0.800 | $4.00 | 262K | 2025-10-15 |
| Regolo AI regolo-ai | qwen3-coder-next | $0.300 | $1.20 | 262K | 2026-03-01 |
Data inconsistencies across providers
- context_window varies: 131072, 256000, 262144
- release_date varies (span 222d): 2025-07-22, 2025-10-15, 2026-02, 2026-02-02, 2026-02-03, 2026-02-04, 2026-02-06, 2026-03-01
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does Qwen3 Coder Next cost?
Qwen3 Coder Next costs $0.120 per 1M input tokens and $0.750 per 1M output tokens, sourced from kilo. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Qwen3 Coder Next?
Qwen3 Coder Next has a context window of 262K tokens, with a max output of 66K tokens per reply. This is the total combined size of prompt + completion.
Does Qwen3 Coder Next support tool calling?
Yes. Qwen3 Coder Next supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Qwen3 Coder Next support structured output / JSON mode?
Yes. Qwen3 Coder Next supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Qwen3 Coder Next accept image input?
No. Qwen3 Coder Next only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Qwen3 Coder Next open-weight?
Yes. Qwen3 Coder Next's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Qwen3 Coder Next?
If Qwen3 Coder Next doesn't fit, consider Qwen3.5 397B-A17B, Qwen3 32B, Qwen3 235B A22B Instruct 2507. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Alibaba (Qwen) models
- Qwen3.5 397B-A17B$0.60 in / $3.60 out
- Qwen3 32B$0.70 in / $2.80 out
- Qwen3 235B A22B Instruct 2507$0.10 in / $0.10 out
- Qwen3-Coder 480B-A35B Instruct$1.50 in / $7.50 out
- Qwen3-235B-A22B-Thinking-2507$0.10 in / $0.10 out
Capability lists this model is in
Last updated:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.