Kimi K2.7 Code HighSpeed

ChatInput: TextInput: ImageReleased Jun 15, 2026

Built by Moonshot AI · China · moonshot.ai

코딩 특화 · 고속 서빙(~180 tok/s)

How to use

model: "moonshot/kimi-k2.7-code-highspeed"

Anchor routing to this model

Hard questions still come back from this model; only easy ones drop to something cheaper. Nothing pricier than it gets used. How hard to push is the dial's job.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "moonshot/kimi-k2.7-code-highspeed"
  }
}

Naming a model directly gets you that model — routing never runs, so it never saves.

Context

262K

Max output

262K

Input $/1M

$1.90

Output $/1M

$8.00

Features

Image inputTool callingJSON

Serving providers

Moonshot

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Measured latency (lower is better) and throughput (higher is better) per provider.

Speed

Loading provider metrics…

Parameter support

What Celon actually does with each parameter when you call this model. The answer differs by serving provider and by API surface.

This table is derived from the gateway adapters and pinned by a test.