Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
Moonshot AI
Moonshot AI
ReasoningAUTO PROFILELIVE INDEX

Kimi K2 Thinking

text->text

Kimi K2 Thinking is a reasoning-tuned model: optimised for chain-of-thought, mathematics, and step-by-step problem solving rather than chat throughput. Available via Moonshot AI. 262,144-token context. Mid-tier pricing.

Kimi K2 Thinking is a reasoning AI model from Moonshot AI. It costs $0.600 per million input tokens and $2.500 per million output tokens (blended $1.170/M), with a 262,144-token context window.

INPUT
$0.600/M
per million input tokens
OUTPUT
$2.500/M
per million output tokens
BLENDED 70/30
$1.170/M
unchanged since 3 May
CONTEXT
262,144
tokens
What it is good at
  • Step-by-step reasoning traces
  • Mathematics and proofs
  • Code synthesis with planning
  • Robust on multi-step problems
Typical use cases
  • Math problem solving
  • Hard coding tasks
  • Research-grade Q&A
  • Multi-step planning

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Moonshot AI

See all 5

Frequently asked questions

How much does Kimi K2 Thinking cost?

Kimi K2 Thinking costs $0.600 per million input tokens and $2.500 per million output tokens, for a blended reference rate of $1.170 per million tokens.

What is Kimi K2 Thinking's context window?

Kimi K2 Thinking supports up to 262,144 tokens of context in a single request.

What is Kimi K2 Thinking best for?

Kimi K2 Thinking is well suited to Step-by-step reasoning traces, Mathematics and proofs and Code synthesis with planning.

Who makes Kimi K2 Thinking?

Kimi K2 Thinking is developed and served by Moonshot AI.

Terms used on this page