moonshotai/kimi-k2
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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Novitafp8 | $0.570 | $2.30 | 131K | 100% |
Kimi K2 0711 costs $0.570 per million input tokens and $2.30 per million output tokens via OpenRouter, making it 169th cheapest of 298 paid models.
Kimi K2 0711 scores 14.4 on the Artificial Analysis Intelligence Index, ranking 149th of 178 benchmarked models, with a GPQA Diamond score of 54%.
Kimi K2 0711 generates around 15 tokens per second with 1.5s time-to-first-token (p50), the 272nd fastest tracked model.
Kimi K2 0711 supports a 131K-token context window and can output up to 33K tokens. It accepts text input.