Kimi K2.6: API price, context window and how to connect

Kimi K2.6 by Moonshot AI: $0.65 per million input tokens, $3.41 per million output tokens, a 262K-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

Moonshot AI's multimodal model for long-horizon coding, code-driven UI generation and orchestrating several agents. It handles tasks in Python, Rust and Go confidently. The weights are open.

Specifications#

Provider Moonshot AI
Released 2026-04-20
Context window 262K tokens
Accepts text, images
Answers with text
Reasoning mode yes
Tool calling yes
Open weights yes
Identifier moonshotai/kimi-k2.6

Price#

Per 1M tokens In dollars
Input (question, context) $0.65
Output (answer) $3.41

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.061. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Code in Python, Rust and Go
  • Interfaces and layout from code
  • Orchestrating several agents

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Grok 4.3 $1.25 $2.5 1M about the same
Grok 4.20 $1.25 $2.5 2M about the same
Kimi K2.7 Code $0.671 $3.35 262K about the same
Gemini 3.8 Flash $0.825 $4.125 1.05M 1.2× more expensive
DeepSeek V4 Pro 0423 $0.955 $1.911 1.05M 1.3× cheaper

Other Moonshot AI models#

How to connect in SKILLOK#

Kimi K2.6 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the moonshotai/kimi-k2.6 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?