Kimi K2 0711

Moonshotai · moonshotai/kimi-k2

← Back to leaderboard

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).

open weightstexttext->text

Context

Max context: 131072
Max output: 100352

Pricing

Input / 1M: 0.57
Output / 1M: 2.30
Blend / 1M: 1.44

Quality

Quality index:

Provider

Provider: Moonshotai
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 / monthEst. 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

Closest API price