This model was retired on 2026-05-25. The pricing below is the last-known rate, kept for migration reference.

Kimi K2 ThinkingDeprecated

MoonshotKnowledgeJul 2025
Tool useReasoningStructured outputWeb search
Context
262K
Max output
262K
Serving providers
6
Cheapest input
$0.60 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards
Speed & latency
Output speed
158 t/s
tokens / second
Time to first token
8.90s
latency
Headline indices
Intelligence Index
32.7
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt3%default
EvalComputeProxy68.5default
GPQA Diamond84%default
Humanity's Last Exam22%default
IFBench68%default
LiveCodeBench85%default
Long-Context Reasoning66%default
MMLU-Pro85%default
Omniscience-20.5default
SciCode42%default
SWE-bench Verified71%default
TerminalBench Hard31%default
τ²-bench93%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Baseten$0.60$2.501
Fireworks AI$0.60$2.501
Moonshot$0.60$2.501
Novita$0.60$2.501
Gmi$0.80$1.201
Crusoe$2.50$2.501

Price history

input + output $/1M since we started tracking
Input Output
$0.000$1.00$2.00$3.00Nov 10Jan 13Apr 9Jun 22$1.20$0.600

Cost calculator

estimate your monthly spend on this model
$320
estimated / month

Model IDs

copy the exact identifier for your platform
baseten/moonshotai/Kimi-K2-Thinkingfireworks_ai/accounts/fireworks/models/kimi-k2-thinkingmoonshot/kimi-k2-thinkingnovita/moonshotai/kimi-k2-thinkinggmi/moonshotai/Kimi-K2-Thinkingcrusoe/moonshotai/Kimi-K2-Thinking

Frequently asked questions

Kimi K2 Thinking pricing, context and availability

Is Kimi K2 Thinking still available?

Kimi K2 Thinking was retired on 2026-05-25. The pricing on this page is the last-known rate, kept for migration reference.

How much did Kimi K2 Thinking cost?

Kimi K2 Thinking's last-known pricing, before it was retired on 2026-05-25, was $0.60 per 1M input tokens and $1.20 per 1M output tokens.

What was the context window of Kimi K2 Thinking?

Kimi K2 Thinking had a 262K token context window and could return up to 262K output tokens.

What could Kimi K2 Thinking do?

Kimi K2 Thinking supported tool use, reasoning, structured output and web search.

Other Moonshot models

compare pricing across the Moonshot lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI