Qwen 3 235 B A22 B Instruct 2507 pricing
Source: litellm · updated 2026-11-19
Short answer: Qwen 3 235 B A22 B Instruct 2507 costs $0.200 per million input tokens and $0.600 per million output tokens. That is a 3:1 blended rate of $0.300 per million tokens, ranking it #296 of 847 tracked models by input price.
Input / 1M
$0.200
Output / 1M
$0.600
Output ÷ input
3.00×
Context window
262,144
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.200 |
| Output, per 1M tokens | $0.600 |
| Output ÷ input multiple | 3.00× |
| 3:1 blended, per 1M tokens | $0.300 |
| Context window | 262,144 tokens |
| Vendor | nebius |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.200 | $0.150 | $0.350 |
| 10M in / 2.5M out | $2.00 | $1.50 | $3.50 |
| 100M in / 25M out | $20.00 | $15.00 | $35.00 |
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
- Qwen 3 235 B A22 B Instruct 2507 vs Qwen 3 235 B
- Qwen 3 235 B A22 B Instruct 2507 vs Qwen 3 235 B A22 B
Cheaper alternatives
Next cheaper option: Open Mistral Nemo at $0.300 per 1M input tokens. Next step up: DeepSeek V3.2 Exp at $0.270 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.