Kimi K2 Thinking
Pricing & Specs
Moonshot AI · $1.2 input / $4 output per 1M tokens · 262.144K context window
No longer offered on OpenMark
Kimi K2 Thinking is no longer offered on OpenMark (deprecated or superseded upstream).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
| Tokens | Price |
|---|---|
| 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
Kimi K2 Thinking Specs
| Spec | Value |
|---|---|
| Context window | 262.144K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~1.3s median response |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | No |
| Batch API | Yes |
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It's been superseded.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.