Kimi K2 0711
Moonshotai · 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...
Kimi K2 0711 ranks #234 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.44 blended per million tokens, it is cheaper than 41% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 100352
Pricing
Output / 1M: 2.30
Blend / 1M: 1.44
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $1.44per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $1.44 |
| 10,000,000 | $14.35 |
| 100,000,000 | $143.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Moonshotai
- Kimi K2.5$1.35 / 1M
- Kimi K2 Thinking$1.55 / 1M
- Kimi K2 0905$1.55 / 1M
- Kimi K2.7 Code$2.03 / 1M
- Kimi K2.6$2.48 / 1M
Closest API price
- GLM 4.5$1.40 / 1M
- Gemini 3.5 Flash Lite$1.40 / 1M · Q 79.3
- Nova 2 Lite$1.40 / 1M
- Nano Banana (Gemini 2.5 Flash Image)$1.40 / 1M
- Morph V3 Large$1.40 / 1M