Models / Moonshot AI / Kimi K2.7 Code Highspeed

Moonshot AI · kimi-k2

Kimi K2.7 Code Highspeed

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

$1.90 in · $8.00 out

per 1M tokens · provider rate closest to the median. No first-party Moonshot AI price was listed. The reference price is Eden AI's rate, the provider closest to the median.

Context
262,144
Max output
262,144
Cache read
$0.38
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Jun 12, 2026
Updated in source
Jun 12, 2026
Knowledge
2025-01
Providers
13

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
AIHubMix$1.90$8.00$0.32——
DevPass$1.90$8.00$0.38——
Eden AIreference$1.90$8.00$0.38——
EmpirioLabs AI$1.90$8.00$1.90——
GMI Cloud$1.90$8.00$0.38——
LLM Gateway$1.90$8.00$0.38——
Merge Gateway$1.90$8.00$0.38——
NanoGPT$1.90$8.00$0.32——
Ofox$1.90$8.00$0.38——
Tempr Gateway$1.90$8.00$0.38——
Vercel AI Gateway$1.90$8.00$0.38——
Kimi For Coding$0$0$0$0—
Kimi For Coding$0$0$0$0—

Jobs this model qualifies for