Kimi K3.1 Pro API cost calculator
Estimate a month of Kimi K3.1 Pro API usage. On OpenScale it costs $0.30 input, $0.20 cached input and $9.00 output per 1M tokens, under its list price.
Kimi K3.1 Pro on OpenScale, a month
$150.00
$240.00 at list price. You save $90.00 (38%).
| Tokens | Amount | Price / 1M | Cost |
|---|---|---|---|
| Input | 50M | $2.00 $0.30 | $15.00 |
| Cached input | 450M | $0.20 $0.20 | $90.00 |
| Output | 5M | $10.00 $9.00 | $45.00 |
Prices used
| Model | Input | Cached input | Output |
|---|---|---|---|
| DeepSeek V4.1 Flash | $0.12 $0.06 | $0.006 $0.003 | $0.48 $0.24 |
| GLM 5.3 Flash | $0.15 $0.12 | $0.03 $0.024 | $0.50 $0.40 |
| Qwen3.8 27B | $0.08 $0.04 | $0.02 $0.01 | $2.50 $1.25 |
| Kimi K3.1 Pro | $2.00 $0.30 | $0.20 $0.20 | $10.00 $9.00 |
How the estimate works
Input tokens split into cached and uncached by the percentage you enter. Each part is multiplied by its price per 1M tokens, and output tokens by the output price. The list price is the reference rate before the discount, priced on the same workload.
The default here is a coding agent: almost all input, most of it repeated each turn. Reasoning tokens count as output.
Estimates only: your bill counts the exact tokens of each request. See the price comparison for an agent workload across providers, and the API reference for model limits.