Moonshot

Kimi K2.7 Code

Released 2026-06-12

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

You send / 1M

$0.560

tokens in

It replies / 1M

$3.10

tokens out

Memory

262K

tokens it can read at once

Typical request

$0.0023

1,000 words in, 400 out

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
CoreWeave · int4$0.600$3.0096%Read
Inceptron · int4$0.560$3.10100%Read
Venice · int4$0.750$3.50100%Read
SiliconFlow · fp8$0.859$3.80100%Read
Novita · int4$0.912$3.84100%Read
Nebius · fp4$0.950$4.0096%Read
Cloudflare$0.950$4.00100%Read
Moonshot AI$0.950$4.00100%Read
Moonshot AI$1.90$8.00100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image
  • Writes: text
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 236K tokens
  • Repeated text is billed at $0.150 per 1M (prompt caching)
  • Intelligence score: 25.8 / 100 (Artificial Analysis)

Similar models

Appears in

Estimate your monthly cost with Kimi K2.7 Code →