kimi-k2.7-code API — per-token pricing and code examples
Price per 1M tokens
Cache rates apply when the provider reports cache tokens.
85% offAbout this model
kimi-k2.7-code is served through OpenAI Chat Completions, OpenAI Responses, Anthropic Messages. You pay $0.1425 per 1M input tokens and $0.60 per 1M output tokens. That is 85% below the official price of $0.95 and $4.00. Cache reads cost $0.01425 per 1M tokens when the provider reports cached tokens. It is included in budget packs from $9.99 up.
Where Kimi K2.7 Code fits
Kimi K2.7 Code is a coding model from Moonshot AI's K2 family, with a 256K-token context window. Moonshot now lists it under its deprecated models: it is "no longer available to newly registered users", accounts registered before November 1 can keep using it, and Moonshot expects to deprecate it in late December 2026. Moonshot's current flagship line is Kimi K3, and its migration note for K2.7 Code is short: set model to kimi-k3 and remove thinking.
Keep using kimi-k2.7-code when you have prompts, agents or evals tuned for it and want time to compare it with kimi-k3 before you switch. For new work, start on a model that is not being retired.
Thinking is always on, sampling is fixed
Moonshot's parameter table describes thinking on this model as "Thinking and Preserved Thinking are always on". reasoning_effort is not supported, so the depth of reasoning cannot be set per request.
Sampling is fixed. Moonshot pins temperature at 1.0, top_p at 0.95, n at 1 and both penalties at 0, and returns an error for any other value. The safest approach is to leave these fields out of the request. For tool calling, tool_choice: "required" returns an error on this model.
What it costs on Cent AI
Kimi K2.7 Code is billed per token from your prepaid USD balance, at the rates in the price box on this page. Because the model always reasons, reasoning tokens, which Cent AI bills as output, are part of every answer.
Moonshot's caching guide names Cache Write support for kimi-k3.1-pro and kimi-k3, not for this model. On Cent AI, cache tokens are billed only when the model reports them in the usage of a request; when nothing is reported, every prompt token is billed at the input rate.
Using it from your tools
kimi-k2.7-code answers on /v1/chat/completions, /v1/responses and /v1/messages. Cent AI does not change your parameters silently, so a temperature left in an old config is not dropped for you and comes back as an upstream_error with the model's status code. Here is a request in the /v1/chat/completions format:
{
"model": "kimi-k2.7-code",
"messages": [{ "role": "user", "content": "Write a unit test for this function." }]
}
Example: the cost of one request
Take a request that sends 2,000 new input tokens, reads 8,000 tokens from cache and gets 800 output tokens back. At the rates in the price box on this page:
- input: 2,000 × $0.1425 / 1,000,000 = $0.000285
- cache read: 8,000 × $0.01425 / 1,000,000 = $0.000114
- output: 800 × $0.60 / 1,000,000 = $0.00048
That request costs $0.000879, about Rp16 at Cent AI's exchange rate on 2026-11-14 (Rp18,231.96 per USD). A thousand requests like it cost $0.879. Your real requests will differ; each one shows its own amount in usage.cost and on the Requests page.
Questions
Is there a 5-hour or weekly limit? No. You pay per token from your balance. Each key accepts up to 600 requests per minute, and you can set your own daily or monthly limit on a key.
Is a failed request charged? A request that fails before the model receives it costs $0. Tokens the model already produced are charged.
Does unused balance expire? No, not while your account exists. Every top-up is manual, with no auto-renewal.
Related models
Compare with kimi-k3, glm-5.3, deepseek-v4-pro, or see every model on the pricing page.
Specification
- Context window
- —
- Input and output
- Text
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
- Smallest pack
- $9.99
Latency and error rate per model are on the status page. status.cent-ai.dev
What a request costs
Open the full calculatorCost per request
Estimate
kimi-k2.7-codeAn estimate at price version 1. Your bill comes from the usage the provider reports for each request.
Save $0.1858Code
curl https://api.cent-ai.dev/v1/chat/completions \
-H "Authorization: Bearer $CENT_AI_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "kimi-k2.7-code", "messages": [{"role": "user", "content": "Hello"}]}'Set CENT_AI_KEY to a key from the dashboard. OpenAI SDKs use https://api.cent-ai.dev/v1; Anthropic SDKs use https://api.cent-ai.dev.
Price history
Version 1, in effect since Oct 30, 2026.
No published price change for this model yet.
Compare with
- hy4-previewInput$0.46704
- deepseek-v4-proInput$0.165
- gpt-6.1-solInput$0.58
- gpt-6.1-terraInput$0.15
Questions
How much does kimi-k2.7-code cost on Cent AI?
$0.1425 per 1M input tokens and $0.60 per 1M output tokens. Cache reads cost $0.01425 and cache writes $0.1425 per 1M tokens. Each request is rounded up once.
Is there a minimum charge?
A successful request costs at least $0.00002. A request that ends early, because the client left or the output was cut off, pays only for its tokens.
How do I pay?
Top up a prepaid USD balance with QRIS or USDT/USDC, or buy a budget pack once. Nothing renews automatically.
What if the provider does not report usage?
The request is billed from an estimate and marked estimated on the Requests page. An estimate never contains cache tokens.
Which endpoint do I call?
/v1/chat/completions, /v1/responses, /v1/messages. The OpenAI base URL is https://api.cent-ai.dev/v1.
Try kimi-k2.7-code with one key
One prepaid balance for every model. Pay with QRIS or USDT/USDC.