Moonshot

Kimi K2.6

Released 2026-04-20

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

You send / 1M

$0.650

tokens in

It replies / 1M

$3.41

tokens out

Memory

262K

tokens it can read at once

Typical request

$0.0026

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
DigitalOcean$0.570$2.40100%Read
SiliconFlow · fp8$0.770$3.40100%Read
Novita$0.800$3.40100%Read
CoreWeave · fp4$0.650$3.4199%Read
Crusoe · bf16$0.700$3.5099%Read
Inceptron · int4$0.585$3.50100%Read
DeepInfra · fp4$0.750$3.50100%Read
Venice · int4$0.750$3.5099%Read
Parasail · int4$0.750$3.50100%Read
Cloudflare$0.950$4.00100%Read
Moonshot AI$0.950$4.0096%Read
Phala$1.09$4.6096%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: 27 / 100 (Artificial Analysis)

Similar models

Appears in

Estimate your monthly cost with Kimi K2.6 →