Moonshot
Kimi K2 Thinking
Released 2025-11-06
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
You send / 1M
$0.600
tokens in
It replies / 1M
$2.50
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0020
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| $0.600 | $2.50 | 0% | Read | |
| Novita · bf16 | $0.600 | $2.50 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 98K tokens
- Repeated text is billed at $0.150 per 1M (prompt caching)
- Intelligence score: 22 / 100 (Artificial Analysis)
Similar models
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Reasoning AI ModelsTop No-Training Reasoning Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models