tokenstat
tokenstat
302ai

kimi-k2-thinking

302ai/kimi-k2-thinking · rates as of · Benchmarks · Plans · Calculator

Kimi reasoning model for long-horizon research, planning, and tool use

Cheapest input
$0.4
$/MTok · models.dev
Cheapest output
$2.50
$/MTok
Context
262K
tokens
Offers
9
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.devcheapestkimi-k2-thinkingOpenCode Zen$0.4$2.50$0.4262K
models.devkimi-k2-thinkingHelicone$0.48$2$0256K
models.devkimi-k2-thinkingAlibaba / Qwen$0.574$2.29$0262K
models.devkimi-k2-thinking302.AI$0.575$2.30$0262K
models.devkimi-k2-thinkingLLM Gateway$0.6$2.50$0.06262K
models.devkimi-k2-thinkingMoonshot AI (China)$0.6$2.50$0.15262K
LiteLLMkimi-k2-thinking$0.6$2.50$0.06
models.devkimi-k2-thinkingCortecs$0.656$2.73$0262K
LiteLLMKimi-K2-Thinking$0.8$1.20$0.08

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-06Released: 2025-09-05Family: kimi-thinking

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