Skip to content

Kimi K2.7 Code HighSpeed

Kimi K2.7 Code HighSpeed is the same model as Kimi K2.7 Code served at roughly 180 tokens per second, at double the price.

Last updated

Available nowkimi-k2.7-code-highspeed

Key facts

At a glance

Context window
262,144
Parameters
Not published
Released
Not published
Output / 1M
$8.00

Pricing

How much does Kimi K2.7 Code HighSpeed cost?

Kimi K2.7 Code HighSpeed costs $1.90 per million input tokens on a cache miss, $0.38 per million on a cache hit, and $8.00 per million output tokens. Prices exclude tax.

Source: Moonshot AI platform documentation, verified August 6, 2026.
Token typePrice per 1M tokens
Input — cache hit$0.38
Input — cache miss$1.90
Output$8.00

What a real request costs

A 100,000-token prompt with a 5,000-token response costs $0.230 cold. Repeat that same prompt prefix so 80% of the input hits the cache and it drops to $0.108 — a 53% saving.

This is why headline per-token prices mislead on agent workloads, where the system prompt and tool definitions repeat on every call.

Capabilities

What can Kimi K2.7 Code HighSpeed do?

  • Text inputsupported
  • Image inputsupported
  • Video inputsupported
  • Thinking modesupported
  • Tool callingsupported
  • JSON modesupported
  • Structured outputnot supported
  • Partial modesupported
  • Context cachingsupported
  • Web searchnot supported
  • Open weightsnot supported

Notes

What the spec sheet leaves out

  • Identical weights to Kimi K2.7 Code — the only difference is serving speed and price.
  • Moonshot quotes roughly 180 tokens/second, reaching up to 260 tokens/second in short-context scenarios.
  • Costs exactly 2× Kimi K2.7 Code on every pricing tier. Worth it only when latency is the binding constraint.

FAQ

Kimi K2.7 Code HighSpeed questions

What is Kimi K2.7 Code HighSpeed?

Kimi K2.7 Code HighSpeed is the same model as Kimi K2.7 Code served at roughly 180 tokens per second, at double the price.

What is the Kimi K2.7 Code HighSpeed context window?

Kimi K2.7 Code HighSpeed has a 262,144-token context window. That total covers input and output combined, so a long prompt reduces the room left for the response.

How much does Kimi K2.7 Code HighSpeed cost?

Kimi K2.7 Code HighSpeed costs $1.90 per million input tokens on a cache miss, $0.38 per million on a cache hit, and $8.00 per million output tokens. Prices exclude tax.

Is Kimi K2.7 Code HighSpeed open source?

Moonshot AI has not published open weights for Kimi K2.7 Code HighSpeed. It is available through the hosted API only.

Sources

Where these figures come from

Every specification and price on this page is transcribed from Moonshot AI’s own documentation and re-checked on the date shown. Nothing is estimated.