AI model · Moonshot AI
MoonshotAI: Kimi K2 Thinking available
moonshotai/kimi-k2-thinking
MoonshotAI: Kimi K2 Thinking costs US$ 0.6 per million input tokens and US$ 2.50 per million output tokens (OpenRouter reference price, verified 2026-11-12).
| Input price (per 1M tokens) | US$ 0.6 |
|---|---|
| Output price (per 1M tokens) | US$ 2.50 |
| Typical request (2,000 tokens in, 500 out) | US$ 0.00245 |
| Context window | 262,144 |
| Max output tokens | 98,304 |
| Announced retirement date | none |
| Knowledge cutoff | — |
| Last verified | 2026-11-12 17:41:15 UTC |
Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.
Frequently asked questions
How much does MoonshotAI: Kimi K2 Thinking cost?
MoonshotAI: Kimi K2 Thinking costs US$ 0.6 per million input tokens and US$ 2.50 per million output tokens (OpenRouter reference price, verified 2026-11-12).
What is the context window of MoonshotAI: Kimi K2 Thinking?
MoonshotAI: Kimi K2 Thinking accepts up to 262,144 tokens of context.
Is MoonshotAI: Kimi K2 Thinking being retired?
No retirement date has been announced for MoonshotAI: Kimi K2 Thinking (checked 2026-11-12).
Other Moonshot AI models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| moonshotai/kimi-k3.1-pro | US$ 0.238 | US$ 8.79 | 1,048,576 |
| moonshotai/kimi-k3.1-pro:batch | US$ 0.7 | US$ 6.00 | 1,048,576 |
| moonshotai/kimi-k3 | US$ 0.192 | US$ 16.00 | 1,048,576 |
| moonshotai/kimi-k3:batch | US$ 2.28 | US$ 11.40 | 1,048,576 |
| moonshotai/kimi-k2.7-code | US$ 0.6 | US$ 3.50 | 262,144 |
| moonshotai/kimi-k2.6 | US$ 0.65 | US$ 3.41 | 262,144 |
| moonshotai/kimi-k2.5 | US$ 0.5 | US$ 2.50 | 262,144 |
| moonshotai/kimi-k2-0905 | US$ 0.6 | US$ 2.50 | 262,144 |
| moonshotai/kimi-k2 | US$ 0.57 | US$ 2.30 | 131,072 |
Give your AI agent these facts
Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.
claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp
Add to CursorAdd to VS Code★ Star on GitHub
Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests
For agents
GET https://vigia.coredls.cloud/v1/models/moonshotai/kimi-k2-thinking