Kimi K2.6

Moonshot AItextimage

Open-weights agentic MoE (1T total / 32B active) released April 2026; strong on SWE-Bench-style coding tasks.

Kimi K2.6 strengths

  • Open weights
  • Strong agentic coding
  • Cost-effective
  • Long-horizon task handling

Pricing & context

Context window262K tokens (64K max output)
Input price /1M$0.60 (verify; varies by provider)
Output price /1M$2.50 (verify; varies by provider)
Modalitiestext, image

Cost guide: a typical call of ~10K input + 2K output tokens runs roughly $0.60 (verify; varies by provider) × 0.01 + $2.50 (verify; varies by provider) × 0.002 — worth modelling against cheaper tiers before committing high-volume traffic.

When to choose Kimi K2.6

Kimi K2.6 is best for Open-model coding agents and budget-conscious agentic pipelines. If your workload is more cost-sensitive, weigh it against Llama 4 Scout (~$0.08 (varies by host) input /1M) first.

Kimi K2.6 FAQ

How much does Kimi K2.6 cost?

Kimi K2.6 is priced at $0.60 (verify; varies by provider) per 1M input tokens and $2.50 (verify; varies by provider) per 1M output tokens (public API list price), with a 262K tokens (64K max output) context window.

What is Kimi K2.6 best for?

Kimi K2.6 by Moonshot AI is best for Open-model coding agents and budget-conscious agentic pipelines.

Is Kimi K2.6 multimodal?

Kimi K2.6 supports text, image.

Other models

All models →
01GPT-5.5OpenAI$5.00
02GPT-5.4OpenAI$2.50
03GPT-5.4 miniOpenAI$0.75
04Claude Opus 4.8Anthropic$5.00