Last verified
CLOSED TO NEW USERS OCT 31DEPRECATED262K CONTEXTTEXT + VISION + VIDEOPROMPT CACHINGTOOL CALLS

Kimi K2.7 Code API Pricing

Deprecated: Moonshot closes the K2 series to newly registered users from October 31, 2026, keeps it for existing users, and plans to retire it by the end of December 2026; its migration guide points to Kimi K3.1 Pro. Kimi K2.7 Code is Moonshot Kimi's coding-specialized model for long-context programming and agent tasks. The official Kimi pricing page lists $0.19/M cache-hit input, $0.95/M cache-miss input, and $4/M output. Pulled directly from platform.kimi.ai.

Input - cache miss per 1M
$0.95/M
Source Kimi API flat
Output - per 1M tokens
$4.00/M
Context 262,144 tokens flat
Cached input - per 1M tokens
$0.19/M
Cache automatic context caching -80%
Effective - agentic blend
$0.621/M
92/8 split - 82% cache
§ 01 / TERMINAL

Kimi K2.7 Code API cost calculator.

Live calculator pre-loaded with Kimi K2.7 Code rates, which existing users pay until Moonshot retires the K2 series. Tweak spend, output mix, or cache assumptions and share the URL to share the calculation.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Kimi K2.7 Code cost on real workloads.

CODING AGENT

Long-horizon coding

$0.030/task
32,000 in - 5,000 out~3,283 units/$100
REFACTOR

Repository migration

$0.062/task
80,000 in - 9,000 out~1,609 units/$100
VISION

Screenshot-to-code implementation

$0.018/screen
18,000 in - 3,000 out~5,592 units/$100
CHATBOT

Developer assistant

$0.00507/turn
4,500 in - 900 out~19,721 units/$100
§ 03 / TOKENIZER

Kimi K2.7 Code token counter and cost.

What's a token →
Estimate · moonshot-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 426
Words 61
Tokens (estimated) 111 tokens
Cost as input · uncached $0.00011 USD
Cost as output · uncached $0.00044 USD
Cost as cached input $0.00002 USD
§ 04 / SHELF

Kimi K2.7 Code vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Kimi K2.7 Code Current $0.95 cache $0.19 $4.00 $0.621 agentic 92/8 262K Long-context coding agents
Kimi K2.6 $0.95 cache $0.16 $4.00 $0.598 deprecated · −4% 262K frontier
Kimi K3 $3.00 cache $0.30 $15.00 $1.92 +3.1× 1M Kimi flagship
GPT-6.1 Terra $1.00 cache $0.05 $5.00 $0.645 +4% 1.05M OpenAI's fast, efficient GPT-6 tier
Grok Build 0.1 $1.00 cache $0.20 $2.00 $0.476 −23% 256K coding
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −4.1× 1M budget
§ 05 / DEEP LINKS

Kimi K2.7 Code cost by scenario.

All calculators →

Audit links

Provider hub →

Kimi K2.7 Code API pricing FAQ.

Short answers for teams evaluating Kimi K2.7 Code for coding agents and long-context development workflows.

Q · 01 Can I still use Kimi K2.7 Code? +
If your account already exists, yes, at the rates on this page. Moonshot closes the K2 series to newly registered users from October 31, 2026, keeps it for existing users, and plans to retire it by the end of December 2026; its migration guide points to Kimi K3.1 Pro. Moonshot has not published an exact shutdown date, and its coding guides now use K3.1 Pro, including through Codex.
Q · 02 What is Kimi K2.7 Code's input price? +
Kimi lists two input rates: $0.95/M for cache-miss input and $0.19/M for cache-hit input. The calculator uses cache hits when you select a cache hit-rate preset.
Q · 03 What is Kimi K2.7 Code's output price? +
The official Kimi pricing page lists output at $4.00/M tokens. Prices exclude applicable taxes, which Kimi says are calculated at checkout based on jurisdiction.
Q · 04 What context window does it support? +
The pricing table lists 262,144 tokens, and the model description describes it as 256K context with long thinking and deep reasoning support.
Q · 05 Does it support prompt caching? +
Yes. The model description lists automatic context caching, and the pricing table separates cache-hit input from cache-miss input.
Q · 06 Is this only a coding model? +
It is coding-specialized, but Kimi describes native multimodal architecture with text, image, and video input, thinking modes, dialogue, and agent tasks.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against platform.kimi.ai · Last verified Oct 28, 2026
Methodology Report a correction More by Y.V.