Kimi K2.7 Code
by Moonshot AI · moonshotai/kimi-k2.7-code · #210 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.82
per 1M tokens
Output
$3.75
per 1M tokens
Blended (3:1)
$1.55
3 input : 1 output
Cache read
$0.16
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Kimi K2.7 Code with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.55 | $0.0874 | — |
| 50% | $1.30 | $0.0544 | −38% |
| 90% | $1.11 | $0.028 | −68% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.001535 | $1.53 |
| Document summary | 8,000 | 1,000 | $0.0103 | $10.31 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0321 | $32.10 |
| Long-context analysis | 150,000 | 5,000 | $0.1417 | $141.75 |
Performance
Intelligence Index
41.9
AA composite quality
Coding Index
60.8
Math Index
—
Agentic Index
29.6
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,300 |
| Web apps | 1,231 |
| Full-stack | 1,238 |
| Mobile apps | 1,220 |
| Android native | 1,261 |
| UI components | 1,302 |
| Data viz | 1,267 |
| SVG | 1,223 |
| 3D | 1,301 |
| Game dev | 1,270 |
| Agentic game dev | 1,144 |
| Godot game dev | 1,208 |
| HTML slides | 1,218 |
| Python→PPTX slides | 1,151 |
| Code categories | 1,291 |
| ASCII art | 1,223 |
Specs
Context window
262K
tokens
Max output
262K
tokens
Input modalities
text, image
Tokenizer
Other