Qwen 3 Coder pricing
Source: litellm · updated 2026-10-30
Short answer: Qwen 3 Coder costs $0.355 per million input tokens and $1.61 per million output tokens. That is a 3:1 blended rate of $0.669 per million tokens, ranking it #355 of 732 tracked models by input price.
Input / 1M
$0.355
Output / 1M
$1.61
Output ÷ input
4.55×
Context window
131,072
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.355 |
| Output, per 1M tokens | $1.61 |
| Output ÷ input multiple | 4.55× |
| 3:1 blended, per 1M tokens | $0.669 |
| Context window | 131,072 tokens |
| Vendor | kyma |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.355 | $0.403 | $0.758 |
| 10M in / 2.5M out | $3.55 | $4.03 | $7.58 |
| 100M in / 25M out | $35.46 | $40.30 | $75.76 |
Other kyma models
| Model | Input | Output |
|---|---|---|
| GPT OSS 120 B | $0.047 | $0.230 |
| Llama 3.3 70 B | $0.135 | $0.432 |
| Gemma 4 31 B | $0.164 | $0.469 |
| GPT-5.6 Luna Pro | $0.270 | $1.62 |
| Qwen 3.7 Plus | $0.432 | $1.73 |
Compare against
Cheaper alternatives
Next cheaper option: Gemma 2 27 B It at $0.650 per 1M input tokens. Next step up: Meta Llama 3.1 70 B Instruct at $0.670 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.