Kimi K2.7 Code vs Kimi K3

Price, context and benchmark scores side by side — every number from the live model catalogue.

Kimi K2.7 Codemoonshotai Kimi K3moonshotai
Input / 1M tokens $0.710 $3.00
Output / 1M tokens $3.50 $15.00
1M in + 300K out $1.76 $7.50
Context window 262K 1.0M
Intelligence index 41.9 57.1
Coding index 60.8 76.2
Agentic index 29.6 50.1
Cheapest provider CoreWeave BaseTen
Providers serving it 13 6
Weights Open Open
Image input Yes Yes
Tool calling Yes Yes
Reasoning mode Yes Yes
Released Jun 12, 2026 Jul 16, 2026

Which one to pick

Pick Kimi K2.7 Code if…

  • Token cost matters: $3.50 per 1M output vs $15.00.
  • You want provider redundancy: 13 providers serve it.

Pick Kimi K3 if…

  • You want the higher general-intelligence score (57.1).
  • Code quality is the priority — it leads on the coding index (76.2).
  • You are running agent loops — higher agentic index (50.1).
  • You need the bigger context window (1.0M).

FAQ

Is Kimi K2.7 Code better than Kimi K3?

Kimi K3 scores higher on general intelligence (41.9 vs 57.1), while Kimi K2.7 Code is 4.3× cheaper per output token ($3.50 vs $15.00). For code, Kimi K3 leads (76.2 coding index). Kimi K3 takes the larger context at 1.0M.

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

Kimi K2.7 Code, at $3.50 per 1M output tokens versus $15.00. On a 1M input + 300K output workload that is $1.76 against $7.50.

Can I self-host Kimi K2.7 Code or Kimi K3?

Kimi K2.7 Code: open weights (moonshotai/Kimi-K2.7-Code). Kimi K3: open weights (moonshotai/Kimi-K3).

Related comparisons