Kimi K2.7 Code vs Kimi K3

Moonshot's Kimi K2.7 Code against Moonshot's Kimi K3 — price, context and what each is best at. Both are available through one OpenAI-compatible API.

AnyModel — you pay	Kimi K2.7 Code	Kimi K3
Vendor	Moonshot	Moonshot
Input / 1M	$0.075	$0.15
Output / 1M	$0.075	$0.15
Context	256K	256K
Best for	Coding agents	Complex coding

Kimi K2.7 Code

Moonshot's strongest coder, always-thinking.

Kimi K2.7 Code is Moonshot's coding specialist, served through the connected Kimi Code subscription. It is an always-thinking model tuned for agentic software engineering with a 256K window.

More about Kimi K2.7 Code →

Kimi K3

Moonshot's multimodal flagship for coding, games and knowledge work.

Kimi K3 is Moonshot's newest flagship model with image understanding, served through the connected Kimi Code subscription. It requires the Moderato tier or higher and has the Kimi Code route's 256K context limit.

More about Kimi K3 →

Quick take: Kimi K2.7 Code is cheaper on output tokens ($0.075 vs $0.15 per 1M). Compare their strengths and context for your task; you can switch the model id at any time.

FAQ

Which is cheaper, Kimi K2.7 Code or Kimi K3?

Kimi K2.7 Code is cheaper on output tokens ($0.075 vs $0.15 per 1M).

Which has a larger context window, Kimi K2.7 Code or Kimi K3?

Kimi K2.7 Code: 256K; Kimi K3: 256K.