Qwen3 Coder Next
AlibabaReleased Feb 3, 2026Open weights · Apache 2.0qwen3-coder-next
- Reasoning
- no
- Knowledge cutoff
- September 2025
- Context
- 262K tokens
- Max output
- 64k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
- Alibaba's API
- yes, as qwen3-coder-next
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Alibaba · cutoff: aiknowledgecutoff.com
Run it yourself
open weights, Apache 2.0 · fits 4 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 80B
- 3B active per token (MoE)
- Memory needed
- 48 GB
- in INT4 · 96 GB in INT8
- Smallest cloud setup
- A100
- 80 GB · $1.19/h, about $869 a month
- Worth it above
- 944M tokens
- a month, against the cheapest API at $0.92 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 48 GB | A100 · $1.19/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 96 GB | 2× H100 · $4.30/h | near-lossless |
| FP16 (full) | 192 GB | 4× H100 · $8.60/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (96 GB unified), about $5,499 once, or $0.2092/h over 3 years, electricity aside; it pays for itself after about 6B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| StreamLakeprecision not read: host terms · 256K ctx · 64K out−40% | $0.18 | $0.90 | $0.036 | — | — | 100% | Oct 9 |
| Parasailbf16 · 256K ctx | $0.12 | $0.80 | $0.07 | 75 | 0.43 s | 100% | Oct 23 |
| Novita AIprecision not stated · 256K ctx · 64K out | $0.20 | $1.50 | — | — | — | — | Oct 8 |
| Alibabaprecision not read: host terms · 256K ctx · 64K out | $0.30 | $1.50 | — | — | — | 94.9% | Oct 9 |
4 of 4 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Parasail | bf16 | 256K | not read: host terms | yes | yes | no |
| StreamLake | not read: host terms | 256K | 64K | yes | no | no |
| Novita AI | not stated by the host | 256K | 64K | — | — | — |
| Alibaba | not read: host terms | 256K | 64K | yes | no | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Qwen3 Coder Next spec sheet, field by field, with sources
Qwen3 Coder Next spec sheetmaker-declared
What Alibaba declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 262,144 tokens
- Parameters
- 79,674,391,296≈ 79.7B
- Active experts
- 10 of 512 active per token
- Weight precision
- bfloat16
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ September 2025 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ February 3, 2026 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Qwen3NextForCausalLM
- Layers
- 48
- Vocabulary
- 151,936 tokens
- Weights first published
- January 30, 2026
- Weights last updated
- February 3, 2026
Qwen/Qwen3-Coder-Next · config.json @ a7fbcb5 · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Parasail | $0.52 | $1.36 | $1.28 |
| StreamLake | $0.63 | $1.89 | $1.62 |
| Novita AI | $0.95 | $2.35 | $2.30 |
| Alibaba | $1.05 | $3.15 | $2.70 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Alibaba models · all its models, hosts and history ›
- Qwen3.8 27B16 providers · from $1.29
- Qwen3.6 35B A3B12 providers · from $1.00
- Qwen3 235B A22B Instruct 250710 providers · from $0.44
- Qwen3.5 397B A17B10 providers · from $3.45
- Qwen3.6 27B9 providers · from $2.25
- Qwen3.5-35B-A3B8 providers · from $1.14
Head-to-head: Qwen3 Coder Next (Alibaba) vs Kimi K2.7 Code (Moonshot AI)