Qwen 3.6 35 B A3 B Thinking pricing
Source: litellm · updated 2026-10-27
Short answer: Qwen 3.6 35 B A3 B Thinking costs $0.150 per million input tokens and $0.500 per million output tokens. That is a 3:1 blended rate of $0.237 per million tokens, ranking it #201 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.150 |
| Output, per 1M tokens | $0.500 |
| Output รท input multiple | 3.33× |
| 3:1 blended, per 1M tokens | $0.237 |
| Context window | 262,144 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.150 | $0.125 | $0.275 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $1.50 | $1.25 | $2.75 | ||||
| 100M in / 25M out | $15.00 | $12.50 | $27.50 |
Other libertai models
| Model | Input | Output |
|---|---|---|
| Hermes 3.8 B Tee | $0.150 | $0.600 |
| Gemma 4 31 B It Thinking | $0.150 | $0.400 |
| Qwen 3.6 27 B Thinking | $0.150 | $0.500 |
| Qwen 3.5 122 B A10 B Thinking | $0.250 | $1.75 |
| DeepSeek V4 Flash Thinking | $0.250 | $1.75 |
Compare against
- Qwen 3.6 35 B A3 B Thinking vs Openai GPT-5 Nano
- Qwen 3.6 35 B A3 B Thinking vs Qwen 3.6 27 B Thinking
Cheaper alternatives
Next cheaper option: Hy 3 at $0.132 per 1M input tokens. Next step up: DeepSeek at $0.190 per 1M input tokens.