Qwen3 Coder
AlibabaReleased Jul 22, 2025Open weights · Apache 2.0qwen3-coder
- 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-480b-a35b-instruct
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Alibaba · cutoff: aiknowledgecutoff.com
The cheapest host, DeepInfra, serves fp8 weights (maker: bf16). Weights and context per host
Run it yourself
open weights, Apache 2.0 · too large for the 6 workstations in our guideSelf-host guide ›- Parameters
- 480B
- 35B active per token (MoE)
- Memory needed
- 288 GB
- in INT4 · 576 GB in INT8
- Smallest cloud setup
- 4× H100
- 320 GB · $8.60/h, about $6,278 a month
- Worth it above
- 5B tokens
- a month, against the cheapest API at $1.30 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 288 GB | 4× H100 · $8.60/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 576 GB | 8× H100 · $17.20/h | near-lossless |
| FP16 (full) | 1152 GB | multi-node, over 640 GB | reference quality |
At home: 288 GB in INT4 is beyond any desktop or Mac in our machines table, so it means a multi-GPU server.
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 |
|---|---|---|---|---|---|---|---|
| Venicefp8 (bf16) · 250K ctx · 64K out | $0.35 | $1.50 | $0.04 | 76 | 0.62 s | 81.2% | Oct 23 |
| DeepInfrafp8 (bf16) · 256K ctx · 64K out | $0.30 | $1.00 | $0.10 | 90 | 0.44 s | 96.7% | Oct 23 |
| Novita AIprecision not stated · 256K ctx · 64K out | $0.38 | $1.55 | — | — | — | — | Oct 8 |
| Googleprecision not stated · 256K ctx · 64K out | $0.22 | $1.80 | — | — | — | 49.0% | Oct 22 |
| Alibabaprecision not read: host terms · 256K ctx · 64K out | $0.97 | $4.88 | — | — | — | 100% | Oct 9 |
5 of 5 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 · 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 |
|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 256K | 64K | yes | yes | no |
| Venice | fp8 | 250K | 64K | yes | yes | no |
| Novita AI | not stated by the host | 256K | 64K | — | — | — |
| not stated by the host | 256K | 64K | yes | yes | no | |
| Alibaba | not read: host terms | 256K | 64K | yes | yes | 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 spec sheet, field by field, with sources
Qwen3 Coder 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
- 480,154,875,392≈ 480.2B
- Active experts
- 8 of 160 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≈ July 22, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Qwen3MoeForCausalLM
- Layers
- 62
- Vocabulary
- 151,936 tokens
- Weights first published
- July 22, 2025
- Weights last updated
- August 21, 2025
- Paper
- arXiv:2505.09388
Qwen/Qwen3-Coder-480B-A35B-Instruct · config.json @ 9d90cf8 · 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 |
|---|---|---|---|
| DeepInfra | $0.80 | $2.90 | $2.20 |
| Venice | $1.10 | $3.55 | $2.90 |
| Novita AI | $1.16 | $3.81 | $3.07 |
| $1.12 | $2.66 | $2.68 | |
| Alibaba | $3.41 | $10.24 | $8.78 |
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