tokenstat
tokenstat

Moonshot: Kimi K2 Instruct

moonshotai/Kimi-K2-Instruct · rates as of · Benchmarks · Plans · Calculator

Kimi model for long-context chat, coding, and agentic reasoning

Cheapest input
$0.1
$/MTok · models.dev
Cheapest output
$2
$/MTok
Context
256K
tokens
Offers
16
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestmoonshotai/kimi-k2-instructNanoGPT$0.1$2$0256K
LiteLLMmoonshotai/Kimi-K2-Instruct$0.5$2$0.05
LiteLLMKimi-K2-Instruct$0.5$2$0.05
LiteLLMdeepinfra/moonshotai/Kimi-K2-Instruct$0.5$2$0.05
models.devkimi-k2-instructCortecs$0.551$2.65$0131K
models.devmoonshotai/kimi-k2-instructJiekou.AI$0.57$2.30$0131K
models.devmoonshotai/kimi-k2-instructNovita AI$0.57$2.30$0131K
LiteLLMmoonshotai/kimi-k2-instruct$0.57$2.30$0.057
LiteLLMnovita/moonshotai/kimi-k2-instruct$0.57$2.30$0.057
LiteLLMkimi-k2-instruct$0.6$2.50$0.06
LiteLLMaccounts/fireworks/models/kimi-k2-instruct$0.6$2.50$0.06
LiteLLMfireworks_ai/accounts/fireworks/models/kimi-k2-instruct$0.6$2.50$0.06
LiteLLMwandb/moonshotai/Kimi-K2-Instruct$0.6$2.50$0.06
models.devmoonshotai/Kimi-K2-InstructHugging Face$1$3$0131K
LiteLLMtogether_ai/moonshotai/Kimi-K2-Instruct$1$3$0.1
LiteLLMhyperbolic/moonshotai/Kimi-K2-Instruct$2$2$0.2

Capabilities

  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-10Released: 2025-07-14Family: kimi-k2

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash