Qwen3 Coder Next
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 blocks, simplifying integration for production coding agents.
- Organization
- Alibaba
- Family
- qwen
- Providers
- 18
- Context
- 262,144
- Output limit
- 65,536
- Knowledge
- 2025-09
- Release
- 2026-02-03
- Updated
- —
- Weights
- Open
- Input
- text
- Output
- text
- Capabilities
- —
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock | qwen.qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Cortecs | qwen3-coder-next | 256,000 | 256,000 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Eden AI | ionos/Qwen/Qwen3-Coder-Next | 128,000 | 65,536 | — / — | — | — | — | View |
| Eden AI | amazon/qwen.qwen3-coder-next | 256,000 | 65,536 | — / — | — | — | — | View |
| Hugging Face | Qwen/Qwen3-Coder-Next | 262,144 | 65,536 | — / — | — | — | — | View |
| InferX | Qwen3-Coder-Next-FP8-no-thinking | 260,000 | 65,536 | — / — | — | — | — | View |
| InferX | Qwen3-Coder-Next-FP8 | 256,144 | 65,536 | — / — | — | — | — | View |
| Jiekou.AI | qwen/qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Kilo Gateway | qwen/qwen3-coder-next | 262,144 | 235,929 | — / — | — | — | — | View |
| LLM Gateway | embercloud/qwen3-coder-next | 262,144 | 262,144 | — / — | — | — | — | View |
| Merge Gateway | qwen/qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| NanoGPT | qwen/qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Ofox | bailian/qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Ofox | qwen/qwen3-coder-next | 256,000 | 64,000 | — / — | — | — | — | View |
| Parasailvia OpenRouter | qwen/qwen3-coder-next bf16 | 262,144 | 235,929 | $0.12 / $0.80 | No | Yes | Yes | View |
| Opper | qwen3-coder-next | 262,144 | 65,536 | — / — | — | — | — | View |
| Prime Inference | qwen/qwen3-coder-next | 262,144 | 235,929 | — / — | — | — | — | View |
| Regolo AI | qwen3-coder-next | 262,144 | 16,384 | — / — | — | — | — | View |
| Together AI | Qwen/Qwen3-Coder-Next-FP8 | 262,144 | 262,144 | — / — | — | — | — | View |
| Vercel AI Gateway | alibaba/qwen3-coder-next | 256,000 | 256,000 | — / — | — | — | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
qwen/qwen3-coder-nextObserved - Input
- $0.12
- Output
- $0.80
- Cache read
- $0.07
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Parasailparasail/bf16 | $0.12 | $0.80 | $0.07 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Parasailparasail/bf16 | 1,098.5 ms | 1,470 ms | 1,923.2 ms | 3,532.57 ms |
Output throughput · tokens per second
All throughput percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Parasailparasail/bf16 | 42 t/s | 54 t/s | 65 t/s | 76 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
qwen/qwen3-coder-nextObserved Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| tau bench verified airline | Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03 | OpenRouter | 55.444% | Details |
| Composite indices | Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03 | Artificial Analysis | Intelligence 9.2 · Coding 36.2 · Agentic 0.9 | Details |
| gpqa diamond | Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03 | OpenRouter | 74.776% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Hermes Agent | qwen/qwen3-coder-next-2025-02-03 | 10–49 turns | $0.071127 | Details |
| Hermes Agent | qwen/qwen3-coder-next-2025-02-03 | 2–9 turns | $0.004718 | Details |
| Hermes Agent | qwen/qwen3-coder-next-2025-02-03 | 50+ turns | $0.477622 | Details |
Source: OpenRouter, as of Oct 20, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
qwen/qwen3-coder-nextObserved - Context
- 262,144
- Maximum output
- 235,929
- Tokenizer
- Qwen
- Input
- text
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-02-04
https://openrouter.ai/api/v1qwen/qwen3-coder-nextqwen/qwen3-coder-next-2025-02-03Qwen/Qwen3-Coder-NextSupported parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Default parameters
- top p
- 0.95
- temperature
- 1
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Qwen3 Coder Next cost?
Listed rates start at $0.12 per million input tokens and $0.80 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Qwen3 Coder Next?
There are 21 cataloged offers across 18 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.
Resources
Catalog history · 3 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
42bcb2ae1a11 - ·
8a29bd927f14 - ·
d203c4c85849