Qwq 32 B pricing
Source: litellm · updated 2026-10-28
Short answer: Qwq 32 B costs $0.150 per million input tokens and $0.450 per million output tokens. That is a 3:1 blended rate of $0.225 per million tokens, ranking it #200 of 713 tracked models by input price.
Input / 1M
$0.150
Output / 1M
$0.450
Output ÷ input
3.00×
Context window
32,768
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.150 |
| Output, per 1M tokens | $0.450 |
| Output ÷ input multiple | 3.00× |
| 3:1 blended, per 1M tokens | $0.225 |
| Context window | 32,768 tokens |
| Vendor | nebius |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.150 | $0.113 | $0.263 |
| 10M in / 2.5M out | $1.50 | $1.12 | $2.62 |
| 100M in / 25M out | $15.00 | $11.25 | $26.25 |
Other nebius models
| Model | Input | Output |
|---|---|---|
| Qwen 2.5 Coder 7 B | $0.010 | $0.030 |
| Llama Guard 3.8 B | $0.020 | $0.060 |
| Meta Llama 3.1.8 B Instruct | $0.020 | $0.060 |
| Qwen 2 VL 7 B Instruct | $0.020 | $0.060 |
| Mistral Nemo Instruct 2407 | $0.040 | $0.120 |
Compare against
Cheaper alternatives
Next cheaper option: Au Anthropic Claude Haiku 5.5 at $0.110 per 1M input tokens. Next step up: Qwen 3.8 Omni Flash at $0.150 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.