Qwen3.6 35B A3B
QwenOpen weights262K context
Lowest price, from Sail
Pricing pagePer million tokens
- Input
- $0.05
- Output
- $0.40
- Cached input
- $0.02
- Batch input / output
- —
- Up to 262K output tokens per request.
Estimate your monthly cost
Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.
From Sail: $1.30 a month.
Where to buy it (8)
Sorted by your monthly estimate. Prices per million tokens.
SailCheapest
- Input / output
- $0.05 / $0.40
- Context
- 262K
- Per month
- $1.30
sail/Qwen/Qwen3.6-35B-A3B
Pinstripes
- Input / output
- $0.14 / $0.45
- Context
- 131K
- Per month
- $2.30
pinstripes/ps/qwen3.6-35b-a3b
Libertai
- Input / output
- $0.15 / $0.50
- Context
- 262K
- Per month
- $2.50
libertai/qwen3.6-35b-a3b
DeepInfra
- Input / output
- $0.10 / $0.95
- Context
- 262K
- Per month
- $2.90
deepinfra/Qwen/Qwen3.6-35B-A3B
W&B Inference
- Input / output
- $0.25 / $1.25
- Context
- 262K
- Per month
- $5.00
wandb/Qwen/Qwen3.6-35B-A3B
Novita AI
- Input / output
- $0.248 / $1.49
- Context
- 262K
- Per month
- $5.45
novita/qwen/qwen3.6-35b-a3b
Scaleway
- Input / output
- $0.25 / $1.50
- Context
- 256K
- Per month
- $5.50
scaleway/qwen/qwen3.6-35b-a3b
AIHubMix
- Input / output
- $0.254 / $1.52
- Context
- 262K
- Per month
- $5.59
aihubmix/qwen3.6-35b-a3b
Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Vision, Reasoning, Tool calling, Web search.