MoonshotAI · live price
Kimi K2 Thinking API pricing
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...
- Input
- $0.6
- per 1M tokens
- Output
- $2.50
- per 1M tokens
- Cached input
- –
- per 1M tokens
- Context
- 262K
- 236K max output
List price from OpenRouter, which passes MoonshotAI's price through without markup. Refreshed hourly. Released November 6, 2025. Model id moonshotai/kimi-k2-thinking.
What Kimi K2 Thinking costs in practice
1,000 chat messages
$1.85
1,000 input + 500 output tokens each
1,000 RAG questions
$6.05
8,000 input + 500 output tokens each
100 coding-agent steps
$2.30
30,000 input + 2,000 output tokens each, no caching
Kimi K2 Thinking price history
Kimi K2 Thinking price by host
- Google$0.6 in · $2.50 out · 262K ctx · 100.0% uptime 24h
- Novita$0.6 in · $2.50 out · 262K ctx · 99.7% uptime 24h
Where to buy MoonshotAI credits for less
Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare
Kimi K2 Thinking cost calculator
Cheaper alternatives to Kimi K2 Thinking
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |
| Z.ai: GLM 5.3 FlashX | $0.37 | $1.25 |
| DeepSeek: DeepSeek V4.1 Flash | $0.03 | $0.5 |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 |
Other MoonshotAI models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Kimi K2 0905 | $0.6 | $2.50 |
| Kimi K2.5 | $0.45 | $2.25 |
| Kimi K2 0711 | $0.57 | $2.30 |
| Kimi K2.6 | $0.434 | $1.83 |
| Kimi K2.7 Code | $0.671 | $3.35 |
| Kimi K3 | $0.684 | $10 |