Qwen3 Coder Next
Qwen · released Jan 30, 2026 · Qwen/Qwen3-Coder-Next
- Type
- Open weightsApache License 2.0
- Params
- 79.7B
- Context
- 262K
active per word not recorded by us · about 197K words of context
Our take
Written Sep 2, 2026Qwen3 Coder Next is a 79.7-billion-parameter code-specialist model with a permissive Apache licence and a 262,144-token request limit. Its weights can be downloaded and used commercially, though no benchmark scores are available to verify its coding quality.
Pick this for open-weights code work where Apache 2.0 licensing matters, or for repository-scale tasks needing a very large context window. Use it if you want provider choice and can shop for the cheapest rate. Skip it if you need measured quality scores, multimodal input, or guaranteed fast throughput — speed varies sharply across hosts with no clear quality trade-off.
The case for it
- Permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- 262,144-token request limit, among the largest we list for open code models.
- Wide provider choice with a 2.6× spread in input pricing, so shopping around pays off.
The case against it
- No benchmark scores in our data, so code quality is unverified.
- Throughput varies 2.4× across measured hosts — the most expensive is also the slowest.
- Text-only; no image, audio or video input.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M2 Max (38-core GPU) · 96 GB
Room to spare. 17.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.12 in / $0.80 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.12 / $0.80checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Parasailbf16Through OpenRouter | $0.12 / $0.80checked 2 hours ago | 262K236K max reply | 43 tok/s | No | No | Confirmed |
| StreamLakeThrough OpenRouter | $0.18 / $0.90checked 2 hours ago | 256K64K max reply | 71 tok/s | No | Yesunknown period | Unknown |
| Novita AIfp8Direct and through OpenRouter | $0.20 / $1.50checked 2 hours ago | 262K66K max reply through OpenRouter | 61 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Alibaba CloudThrough OpenRouter | $0.30 / $1.50checked 2 hours ago | 262K66K max reply | 84 tok/s | No | Yesunknown period | Unknown |
Novita AIAcross the 5 listings we hold: 4 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Parasailbf16Through OpenRouter | ✓ | ✓ | ✓ |
| StreamLakeThrough OpenRouter | ✓ | ✓ | ✗ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Alibaba CloudThrough OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 2 of 5 listings say yes, 3 say no.
When we formed this view
Recent changes
What moved
input +5% ($0.110 → $0.116 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen3-Coder-Next
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- qwen-qwen3-coder-next