Moonshot AI (Kimi)

Kimi K2 Instruct

Type
language model
Context
131K tokens
Max output
8K
Released
1 July 2025
API string
moonshotai/kimi-k2-instruct
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
NanoGPT $0.1 $2 31 Jul 2026
DeepInfra $0.5 $2 31 Jul 2026
Cortecs $0.551 $2.646 31 Jul 2026
novita-ai $0.57 $2.3 31 Jul 2026
Jiekou.AI $0.57 $2.3 31 Jul 2026
Novita AI $0.57 $2.3 31 Jul 2026
alibaba-cn $0.574 $2.294 1 Aug 2026
Fireworks AI $0.6 $2.5 31 Jul 2026
Weights & Biases $0.6 $2.5 31 Jul 2026
Hugging Face $1 $3 31 Jul 2026
Together AI $1 $3 31 Jul 2026
Hyperbolic $2 $2 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Creative writing (Lech Mazur’s evaluation) 85.6 % lechmazur/writing Github repository
Fiction.LiveBench — holding a long context 61.1 % Fiction.live leaderboard
Aider Polyglot — code edits in six languages 59.1 % · with a tuned harness Aider LLM Leaderboards
WeirdML — unusual machine learning tasks 39.36 % WeirdML Leaderboard
Terminal-Bench — working in the command line 27.8 % · with a tuned harness Terminal-Bench v2 Leaderboard
SimpleBench — trick questions 11.56 % SimpleBench Leaderboard
GSO-Bench — code optimisation 4.9 % GSO Leaderboard