Kimi K2 Thinking
Pricing & Specs

Moonshot AI · $1.2 input / $4 output per 1M tokens · 262.144K context window

No longer offered on OpenMark

$1.2
per 1M input tokens
$4
per 1M output tokens
262.144K
context window (tokens)

Kimi K2 Thinking is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Kimi K2 Thinking API Pricing

TokensPrice
Input$1.2 / 1M tokens
Output$4 / 1M tokens

50% discount available for batch API requests. Batch API pricing is available via Together at 50%; cache pricing is not published.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0032
1K 1,000 runs of that task: $3.20
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Kimi K2 Thinking Specs

SpecValue
Context window262.144K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~1.3s median response
Reasoning modelYes
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingNo
Batch APIYes

Notes

Scheduled for deprecation on Together AI: March 06, 2026.

FAQ

How much does Kimi K2 Thinking cost?

Kimi K2 Thinking costs $1.2 per 1M input tokens and $4 per 1M output tokens.

What is Kimi K2 Thinking's context window?

Kimi K2 Thinking has a 262.144K-token context window.

Can I test Kimi K2 Thinking on my own task?

Kimi K2 Thinking is no longer offered on OpenMark, but you can benchmark its current alternatives from Moonshot AI and other providers on your own task — free tier available.

Still using Kimi K2 Thinking?

It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives — Free →