Qwen3 235B A22B Thinking 2507
AlibabaReleased Jul 25, 2025Open weights · Apache 2.0qwen3-235b-a22b-thinking
- Intelligence (Epoch)
- 144 · 67th of 111
- Reasoning
- yes
- Knowledge cutoff
- September 2025
- Context
- 262K tokens
- Max output
- 32k tokens
- Input
- text
- API features
- tools, JSON mode, seed
- Alibaba's API
- yes, as qwen3-235b-a22b-thinking-2507
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Alibaba · cutoff: aiknowledgecutoff.com
The cheapest host, Alibaba, serves a weights precision we can't read (host terms) and serves a 128K context (maker: 256K). Weights and context per host
Intelligence for the price
23 models score higher for the same price or less; it ranks 24 of the 60 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 144 with an interval of 142 to 145.
Against its rivals
The best of its price range and the top score
- Qwen3 235B A22B Thinking 2507this model$2.53144
- Claude Opus 5.5top score$24.00169
- Gemini 3.7 Flashsame price range$4.50158
- Gemini 3.8 Flashsame price range$4.50157
Same level for 16× less: Qwen3.7 Flash at Alibaba, $0.16 per M input + output · their Epoch intervals overlap (144 against 144).
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Run it yourself
open weights, Apache 2.0 · fits 1 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 235B
- 22B active per token (MoE)
- Memory needed
- 141 GB
- in INT4 · 282 GB in INT8
- Smallest cloud setup
- 2× H100
- 160 GB · $4.30/h, about $3,139 a month
- Worth it above
- 1B tokens
- a month, against the cheapest API at $2.53 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 141 GB | 2× H100 · $4.30/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 282 GB | 4× H100 · $8.60/h | near-lossless |
| FP16 (full) | 564 GB | 8× H100 · $17.20/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (256 GB unified), about $9,499 once, or $0.3615/h over 3 years, electricity aside; it pays for itself after about 4B 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 |
|---|---|---|---|---|---|---|---|
| Alibabaprecision not read: host terms · 128K ctx (256K) | $0.23 | $2.30 | — | — | — | 99.4% | Oct 9 |
| Novita AIprecision not stated · 128K ctx (256K) · 32K out | $0.30 | $3.00 | — | — | — | — | Oct 8 |
| Venicefp8 (bf16) · 125K ctx (256K) · 16K out | $0.45 | $3.50 | — | 30 | 0.84 s | 100% | Oct 23 |
3 of 3 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 |
|---|---|---|---|---|---|---|
| Alibaba | not read: host terms | 128K | not read: host terms | yes | no | yes |
| Novita AI | not stated by the host | 128K | 32K | — | — | — |
| Venice | fp8 | 125K | 16K | yes | no | yes |
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 235B A22B Thinking 2507 spec sheet, field by field, with sources
Qwen3 235B A22B Thinking 2507 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
- 235,093,634,560≈ 235.1B
- Active experts
- 8 of 128 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 25, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Qwen3MoeForCausalLM
- Layers
- 94
- Vocabulary
- 151,936 tokens
- Weights first published
- July 25, 2025
- Weights last updated
- August 17, 2025
Qwen/Qwen3-235B-A22B-Thinking-2507 · config.json @ 6cbffae · 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 |
|---|---|---|---|
| Alibaba | $1.38 | $2.99 | $3.22 |
| Novita AI | $1.80 | $3.90 | $4.20 |
| Venice | $2.20 | $5.35 | $5.30 |
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