Kimi K2.7 Code membership plans & usage tiers
If you want to use Kimi K2.7 Code directly in your terminal or IDE, the simplest path is through a Kimi Code subscription.
| Moderato | Allegretto | Allegro | Vivace | |
|---|---|---|---|---|
| Monthly Price | $19 / month | $39 / month | $99 / month | $199 / month |
| Description | Weekly refreshed usage quotas with multi-device login, allowing you to share your plan across devices and work efficiently on multiple projects | Ample weekly limits and increased concurrency caps, providing a high-value solution for advanced users | Expansive quota designed for excellence. Seamlessly handles everything from daily tasks to intensive development | Offering our highest weekly plan quotas, enabling you to handle complex projects and large codebases with ease |
Each plan includes weekly refreshed usage quotas. Higher tiers provide larger weekly limits and higher concurrency caps, making them suitable for more demanding projects. For the latest plan details, see the official membership page.
What's included beyond Kimi Code?
Purchasing any Kimi Code plan also unlocks the broader Kimi membership benefits, powered primarily by Kimi K2.6.
| Adagio | Moderato | Allegretto | Allegro | Vivace | |
|---|---|---|---|---|---|
| Price | $0 | $19 / month | $39 / month | $99 / month | $199 / month |
| Agent Usage | 6 | 60 | 150 | 360 | 720 |
| Agent Concurrent Tasks | 1 task | 2 tasks | 2 tasks | 4 tasks | 4 tasks |
| Agent Priority Queue | ✗ | 4x speed | 4x speed | 4x speed | 4x speed |
| Agent Swarm | ✗ | 25 uses included | 50 uses included | 120 uses included | 240 uses included |
| Agent Swarm Concurrent Subagents | ✗ | 2 subagents | 4 subagents | 4 subagents | 8 subagents |
| Kimi Claw | ✗ | ✗ | ✓ | ✓ | ✓ |
| Kimi Claw Android | ✗ | ✗ | ✓ | ✓ | ✓ |
| Kimi Claw PC | ✗ | ✗ | ✓ | ✓ | ✓ |
| Group Chat with Claw | ✗ | ✗ | 10 group chats | 10 group chats | 10 group chats |
| Deploy a Website with a Database | ✗ | ✓ | ✓ | ✓ | ✓ |
| Kimi Work Active Scheduled Tasks | 2 tasks | 10 tasks | 15 tasks | 20 tasks | 20 tasks |
These cross-product benefits are available across all paid tiers alongside your Kimi K2.7 Code usage, giving you both a dedicated coding agent and a full AI workspace in one subscription.
Kimi K2.7 Code API pricing
The Kimi K2.7 Code API pricing uses a token-based model, with usage billed per 1M tokens (1,000,000 tokens) for both input and output processing, enabling clear and predictable cost control.
| Model | Unit | Input price (cache hit) | Input price (cache miss) | Output price | Context window |
|---|---|---|---|---|---|
| kimi-k2.7-code | 1M tokens | $0.19 | $0.95 | $4.00 | 262,144 tokens |
| kimi-k2.7-code-highspeed | 1M tokens | $0.38 | $1.90 | $8.00 | 262,144 tokens |
The standard kimi-k2.7-code model delivers Kimi's most intelligent coding performance with full support for long-context reasoning and agentic tasks. The kimi-k2.7-code-highspeed variant offers approximately 180 Tokens/s output speed (up to 260 Tokens/s in short context scenarios), providing an extreme coding experience for latency-sensitive workflows.
How Kimi K2.7 Code API billing works
Kimi K2.7 Code API uses a token-based pricing model for each request, where every interaction with the model consumes tokens that are billed according to their type. Within this model, tokens are generally categorized into three types: input tokens, output tokens, and cached input tokens.
Input tokens
Input tokens represent everything sent to the model, including:
User prompts
System instructions
Conversation history or context
These tokens determine how much context the model needs to process before generating a response.
Cached input tokens
Cached input tokens occur when previously processed context is reused.
If the same or similar context is reused, it can be served at a reduced cost
This significantly improves efficiency for repetitive workflows
It is especially useful in long-context applications or multi-turn interactions
Output tokens
Output tokens are generated by the model in response to a request. They represent the actual AI-generated content, such as:
Code generation
Text responses
Structured outputs
Because output generation requires additional computation, it is typically priced higher than input tokens.
Conclusion
Kimi K2.7 Code offers a transparent and flexible pricing structure that scales from individual development projects to large production workloads. With token-based billing, cache discounts, and a high-speed model option, developers can balance performance and cost based on their specific requirements. This makes it easier to build, test, and deploy AI-powered coding workflows while maintaining predictable spending.