// Alibaba (Qwen)
Qwen3.6-35B-A3B
A Alibaba (Qwen) model. 6 prices across 5 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- ¥1.8 / ¥10.8
- Lowest (DeepInfra)
- $0.1 / $0.95
- Context
- 262K
- AA index
- 18.2
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Alibaba (Qwen) |
|---|---|
| Context window | 262K (262,144 tokens) |
| Max output | 66K |
| Input | Text · Image · Video |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · Apache-2.0 · Hugging Face |
| Parameters | 36B (from weight files) |
| Released | Apr 27, 2026 |
| Model IDs | qwen3.6-35b-a3b · qwen/qwen3.6-35b-a3b · Qwen/Qwen3.6-35B-A3B |
02Prices on 5 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Official Vendor’s China site, billed in CNY | Official 10-10 | ¥1.8 | ¥10.8 | — | 0.604 | 262K | Batch −50%Beijing region; batch -50% on supported models; explicit cache create 125% / hit 10% of input |
| DeepInfra Inference platform (own price page) | Platform 10-10 | $0.1 | $0.95 | $0.1 | 0.313 | 262K | DeepInfra own pricing page |
| Parasail · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.1 | $0.95 | $0.05 | 0.313 | 262K | Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page |
| AtlasCloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.25 | $1.25 | $0.25 | 0.5 | 262K | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against AtlasCloud's own page |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥1.8 | ¥10.8 | — | 0.604 | — | SiliconFlow (硅基流动) own pricing page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.24 | $1.8 | $0.15 | 0.63 | 262K | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Vendor’s China site, billed in CNY
Official - Inference platform (own price page)
DeepInfra · SiliconFlow - Via OpenRouter / provider listed there
Parasail · AtlasCloud · SiliconFlow - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
Qwen3.6-35B-A3B→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexQwen3.6 35B A3B (Reasoning)
- 18.2
- Output speed (median)
- 132 tok/s
- Time to first tokenQwen3.6 35B A3B (Non-reasoning): 2s
- 2.06s
- AA index per $ (blended)
- 30.16
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| GPQA Diamond | 83.8% | independent | 2026-08-07 |
| AIME (OTIS Mock AIME 2024–2025) | 86.7% | independent | 2026-08-07 |
| Terminal-Bench 2.0 | 24.6% | official | 2026-04-16 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-20 · Parasail · output1 → 0.95 USD (-5%)
- 2026-10-20 · Parasail · input0.15 → 0.1 USD (-33.3%)
- 2026-10-19 · AtlasCloud · cache read0.186 → 0.25 USD (+34.4%)
- 2026-10-19 · AtlasCloud · output1.11375 → 1.25 USD (+12.2%)
- 2026-10-19 · AtlasCloud · input0.186 → 0.25 USD (+34.4%)
06More from Alibaba (Qwen)
FAQ
How much does the Qwen3.6-35B-A3B API cost?
On the official pricing page: ¥1.8 / ¥10.8 per 1M input / output tokens (checked 2026-10-10). The lowest price we found is $0.1 / $0.95 on DeepInfra.
What is the context window of Qwen3.6-35B-A3B?
262K tokens of context, up to 66K output tokens. Platforms may cap it lower – see the table.
Is Qwen3.6-35B-A3B open source?
Yes, the weights are published on Hugging Face (Qwen/Qwen3.6-35B-A3B). Licence: Apache-2.0.