Home / Alibaba / Qwen / Qwen3.6 35B A3B - No Thinking
Qwen3.6 35B A3B - No Thinking API price
Qwen3.6 35B A3B - No Thinking
Qwen3.6 35B A3B - No Thinking API costs $0.10/M input at InferX (inference host), per 1M tokens.
SmallAlibaba / Qwen262K context1 seller
Input
$0.10
per 1M tokens · InferX (inference host)
Output
$0.75
per 1M tokens · InferX (inference host)
Where to buy it
The one source pricing Qwen3.6 35B A3B - No Thinking today, per 1M tokens.
Cost calculator
| Provider | Input $/M | Output $/M | Cached in | Your cost |
|---|---|---|---|---|
| InferX (inference host) | 0.100cheapest | 0.750 | 0.020 |
Against its tier
- This model$0.85
- Cheapest · Nemotron 3.5 Lightning$0.145
- Tier median · Qwen3.6 35B A3B - No Thinking$0.85
- Dearest · GPT 5.4 Mini (03-17 snapshot)$5.25
#11 of 20 small · cheaper than 47%
Details
- Context window
- 262K262,000 tokens
- Developer
- Alibaba / Qwen
- Sellers
- 1
- Cheapest at
- InferX (inference host)
- Cached input
- $0.02where the source publishes one
- Combined
- $0.85in + out per 1M
- Last checked
- 2026-10-12