Kimi K2.7 Code
Moonshot AIUpdated June 2026. Kimi K2.7 Code by Moonshot AI: ¥6.50/M cache-miss input, ¥27.00/M output tokens. Cached input: ¥1.30/M. 262K context, 33K max output. Vision & Video. Free calculator + compare 40+ models.
Input Price
¥6.50
cache miss / 1M tokens
Cached Input
¥1.30
per 1M tokens
Output Price
¥27.00
per 1M tokens
Context Window
262K
tokens
Specifications
| Provider | Moonshot AI |
| Model ID | kimi-k2.7-code |
| Input Price | $6.5 / 1M cache-miss tokens |
| Cached Input Price | $1.3 / 1M tokens |
| Output Price | $27 / 1M tokens |
| Context Window | 262K tokens |
| Max Output | 33K tokens |
| Capabilities | textvisionvideofunction_calling |
| Release Date | 2026-06 |
| Pricing Source | Official Moonshot AI pricing |
| Price Verified | 2026-06-14 · Moonshot China pricing is published in CNY and is excluded from the USD comparison calculator. |
| Notes | Current Kimi coding model. Thinking-only mode; China API pricing in CNY. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $5.03 | $60.30 |
| 50K | $25.13 | $301.50 |
| 100K | $50.25 | $603.00 |
| 500K | $251.25 | $3015.00 |
| 1.0M | $502.50 | $6030.00 |
About Kimi K2.7 Code
Kimi K2.7 Code is a large language model by Moonshot AI. It features a 262K token context window with up to 33K tokens of output per request. The model supports 4 capabilities: text, vision, video, function_calling.
At $6.5 per million cache-miss input tokens and $27 per million output tokens, Kimi K2.7 Code is positioned as a premium option in the Moonshot AI lineup. Repeated prefix input can be charged at $1.3 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
Kimi K2.7 Code Key Details
- Pricing: $6.5/M cache-miss input tokens, $1.3/M cached input tokens, $27/M output tokens
- Context window: 262K tokens — suitable for large documents and codebases
- Max output: 33K tokens per response
- Capabilities: text, vision, video, function_calling
- Highlights: Current Kimi coding model. Thinking-only mode; China API pricing in CNY.
- Released: 2026-06
Other Moonshot AI Models
Similar Price Range
Related Tools
FAQ
How much does Kimi K2.7 Code cost?
Kimi K2.7 Code costs $6.5 per million cache-miss input tokens and $27 per million output tokens. Cached input costs $1.3 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $60.00/month before cache-hit savings.
What is Kimi K2.7 Code's context window?
Kimi K2.7 Code supports a context window of 262K tokens. This means your combined input prompt and output response can be up to 262K tokens. The maximum output per response is 33K tokens.
Is Kimi K2.7 Code good for my use case?
Kimi K2.7 Code supports text, vision, video, function_calling. As a premium model, it excels at complex reasoning, coding, and tasks requiring maximum quality. Use our Pricing Calculator to compare with alternatives.