tokenstat
tokenstat

Kimi K2.5

amazon-bedrock/moonshotai.kimi-k2.5 · rates as of · Benchmarks · Plans · Calculator

Kimi multimodal agent model for visual understanding, coding, and planning

Cheapest input
$0.6
$/MTok · models.dev
Cheapest output
$3
$/MTok
Context
262K
tokens
Offers
13
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-k2.5Amazon Bedrock$0.6$3$0262K
LiteLLMmoonshotai.kimi-k2.5$0.6$3$0.06
LiteLLMbedrock/us-east-1/moonshotai.kimi-k2.5$0.6$3$0.06
LiteLLMus-east-1/moonshotai.kimi-k2.5$0.6$3$0.06
LiteLLMus-east-2/moonshotai.kimi-k2.5$0.6$3$0.06
LiteLLMus-west-2/moonshotai.kimi-k2.5$0.6$3$0.06
LiteLLMbedrock/moonshotai.kimi-k2.5$0.6$3.03$0.06
LiteLLMap-northeast-1/moonshotai.kimi-k2.5$0.72$3.60$0.072
LiteLLMap-south-1/moonshotai.kimi-k2.5$0.72$3.60$0.072
LiteLLMap-southeast-3/moonshotai.kimi-k2.5$0.72$3.60$0.072
LiteLLMbedrock/ap-northeast-1/moonshotai.kimi-k2.5$0.72$3.60$0.072
LiteLLMeu-north-1/moonshotai.kimi-k2.5$0.72$3.60$0.072
LiteLLMsa-east-1/moonshotai.kimi-k2.5$0.72$3.60$0.072

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • In: image
  • Out: text
Released: 2026-02-06Family: kimi

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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