Moonshot
Kimi K2 0711
Released 2025-07-11 · Knowledge up to 2024-12-31
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
You send / 1M
$0.570
tokens in
It replies / 1M
$2.30
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0019
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 |
|---|---|---|---|---|
| Novita · fp8 | $0.570 | $2.30 | 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: No
- Tool calling: Yes
- Longest reply: 98K tokens
- Intelligence score: 12.7 / 100 (Artificial Analysis)
Similar models
- GPT Audio MiniOpenAI · $0.600 in / $2.40 out per 1M
- Kimi K2 0905Moonshot · $0.600 in / $2.50 out per 1M
- Devstral 2 2512Mistral · $0.400 in / $2.00 out per 1M
- GPT-3.5 Turbo (older v0613)OpenAI · $1.00 in / $2.00 out per 1M
- Morph V3 LargeMorph · $0.900 in / $1.90 out per 1M
- Relace SearchRelace · $1.00 in / $3.00 out per 1M