docs: Add input token pricing to Moonshot Kimi public endpoint - #734
Conversation
Split the per-token pricing into separate input and output rates for each Kimi variant (K2.6, K2.7 Code, K3), matching the console playground.
![promptless[bot]](https://avatars.githubusercontent.com/in/979718?s=60&v=4){kind=small}
| |---|---| | ||
| | **Endpoint** | `https://api.runpod.ai/v2/moonshot-kimi/runsync` | | ||
| | **Pricing** | \$4.00–\$15.00 per 1M tokens | | ||
| | **Pricing** | \$4.00–\$15.00 per 1M output tokens, \%0.95-$3.00 per 1M input tokens | |
There was a problem hiding this comment.
Summary Pricing row range $0.95-$15.00 per 1M tokens matches console banner: K2.6/K2.7-Code $0.95 input/$4.00 output, K3 $3.00 input/$15.00 per 1m tokens.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| | `kimi-k3` | Flagship model with always-on reasoning and configurable reasoning effort for long-horizon coding and knowledge work. | 1M (1,048,576 tokens) | \$15.00 per 1M tokens | | ||
| | `model` value | Description | Context window | Input price | Output price | | ||
| |---|---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$0.95 per 1M tokens | \$4.00 per 1M tokens | |
There was a problem hiding this comment.
Kimi K2.6 input $0.95/1M and output $4.00/1M per console banner: "Kimi K2.6 & Kimi K2.7 Code - $4.00 per 1m output tokens, $0.95 per 1m input tokens".
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| | `model` value | Description | Context window | Input price | Output price | | ||
| |---|---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$0.95 per 1M tokens | \$4.00 per 1M tokens | | ||
| | `kimi-k2.7-code` | Coding-focused model with thinking mode and agentic capabilities. | 256K (262,144 tokens) | \$0.95 per 1M tokens | \$4.00 per 1M tokens | |
There was a problem hiding this comment.
Kimi K2.7-code input $0.95/1M and output $4.00/1M per console banner (same rate as K2.6, grouped together in banner text).
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| |---|---|---|---|---| | ||
| | `kimi-k2.6` (default) | General-purpose model with thinking and non-thinking modes, agentic capabilities, and multimodal input. | 256K (262,144 tokens) | \$0.95 per 1M tokens | \$4.00 per 1M tokens | | ||
| | `kimi-k2.7-code` | Coding-focused model with thinking mode and agentic capabilities. | 256K (262,144 tokens) | \$0.95 per 1M tokens | \$4.00 per 1M tokens | | ||
| | `kimi-k3` | Flagship model with always-on reasoning and configurable reasoning effort for long-horizon coding and knowledge work. | 1M (1,048,576 tokens) | \$3.00 per 1M tokens | \$15.00 per 1M tokens | |
There was a problem hiding this comment.
Kimi K3 input $3.00/1M (explicit "input tokens" in banner) and output $15.00/1M (banner says "$15.00 per 1m tokens" without explicit output label; doc infers output rate by parallel structure with K2.6/K2.7 and standard output-priced-higher convention).
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| ## Cost calculation | ||
|
|
||
| Moonshot Kimi uses tiered pricing based on the variant. Kimi K2.6 and Kimi K2.7 Code charge \$4.00 per 1M tokens, while Kimi K3 charges \$15.00 per 1M tokens. Example costs: | ||
| Moonshot Kimi charges separate rates for input and output tokens, and the rate depends on the variant. Kimi K2.6 and Kimi K2.7 Code charge \$0.95 per 1M input tokens and \$4.00 per 1M output tokens. Kimi K3 charges \$3.00 per 1M input tokens and \$15.00 per 1M output tokens. Example costs: |
There was a problem hiding this comment.
Cost calculation prose restates K2.6/K2.7-Code $0.95 input/$4.00 output and K3 $3.00 input/$15.00 output per 1M tokens, matching console banner figures.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
| | 10,000 tokens | \$0.04 | \$0.15 | | ||
| | 100,000 tokens | \$0.40 | \$1.50 | | ||
| | 1,000,000 tokens | \$4.00 | \$15.00 | | ||
| | Tokens | K2.6 & K2.7 Code input (\$0.95/1M) | K2.6 & K2.7 Code output (\$4.00/1M) | K3 input (\$3.00/1M) | K3 output (\$15.00/1M) | |
There was a problem hiding this comment.
Example-cost table headers restate the four per-1M rates ($0.95, $4.00, $3.00, $15.00) used to compute the example row arithmetic; all row values verified correct given these rates.
Source: https://console.runpod.io/hub/playground/text/moonshot-kimi
|
Just a reminder: If you'd like me to act on any feedback you have via Github comments, just type @Promptless in your suggestion and I'll get right on it! (I won't show up in the user dropdown, but I'll process any request that has @Promptless in the comment body.) |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
1 participant
Open this suggestion in Promptless to view citations and reasoning process
The Moonshot Kimi public endpoint page listed only a single per-token price for each variant, which was actually the output-token rate, and did not show input-token costs at all. This updates the page to present input and output pricing separately for every variant, matching the rates shown in the Hub playground.
Trigger Events
Tip: Enable auto-create PR in your Configuration to review suggestions directly in GitHub 🤖