Kimi K2 Thinking pricing
Kimi K2 Thinking API cost from Moonshot AI (Kimi) — $0.600 per 1M input tokens and $2.50 per 1M output tokens. Open-weight reasoning. Estimate your real monthly bill below, then compare it against every other model.
Reasoning open weights 256K context · all prices USD per 1M tokens, list price last verified 2026-06-27.
Kimi K2 Thinking capabilities & limits
Representative specs for this tier — confirm exact limits in the Moonshot AI (Kimi) docs.
Call Kimi K2 Thinking from your code
The exact model string and endpoint to use. Works with the OpenAI SDK — just point base_url at the URL below.
kimi-k2-thinkinghttps://api.moonshot.ai/v1MOONSHOT_API_KEYcurl https://api.moonshot.ai/v1/chat/completions \
-H "Authorization: Bearer $MOONSHOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2-thinking",
"messages": [{"role": "user", "content": "Hello"}]
}'Model strings follow each provider's naming convention; confirm the current id in the Moonshot AI (Kimi) docs before relying on it.
What a Kimi K2 Thinking API call actually costs
Blended input + output cost at Kimi K2 Thinking's list rates — useful yardsticks before you commit to volume.
Kimi K2 Thinking cost calculator
Enter your monthly volume to estimate the Kimi K2 Thinking bill. Runs entirely in your browser.
Moonshot AI (Kimi) models — Kimi K2 Thinking in context
How Kimi K2 Thinking prices against its siblings. Cheapest reference cost first.
| Model | Input /1M | Output /1M | Cost / call* | Context | Type |
|---|---|---|---|---|---|
| Kimi K2 Open weights | $0.570 | $2.30 | $0.0029 | 128K | Balanced open |
| Kimi K2 Thinking Open-weight reasoning | $0.600 | $2.50 | $0.0031 | 256K | Reasoning open |
*Reference cost of one call with 1,000 input + 1,000 output tokens — a neutral yardstick. Use the calculator for your real usage. Cheapest row highlighted.
How Kimi K2 Thinking pricing works
Kimi K2 Thinking is billed per token: a lower input price of $0.600 per million tokens for everything you send, and a higher output price of $2.50 per million for everything the model generates. To turn that into a real Kimi K2 Thinking bill, multiply by your monthly request volume and average prompt/response length — the calculator above does exactly that.
Kimi K2 Thinking does not list a separate cached-input rate, so every input token bills at $0.600 per million. If repeated context is a big part of your prompts, a model with prompt caching may end up cheaper in practice.
List prices move fast — always confirm the current numbers on the official Moonshot AI (Kimi) pricing page before relying on them for budgeting.
Kimi K2 Thinking pricing FAQ
How much does the Kimi K2 Thinking API cost?
Kimi K2 Thinking costs $0.600 per 1M input tokens and $2.50 per 1M output tokens. A typical 3K-input / 500-output call works out to about $0.0030.
What is Kimi K2 Thinking's context window?
Kimi K2 Thinking has a 256K-token context window. Tokens you put in the prompt are billed at the $0.600 per 1M input rate.
Does Kimi K2 Thinking charge extra for output tokens?
Yes. Output (generated) tokens cost $2.50 per 1M, versus $0.600 per 1M for input — about 4.2× more, which is normal for LLM APIs.
Is there a cheaper alternative to Kimi K2 Thinking?
In the same reasoning tier, DeepSeek-V4 Pro (DeepSeek) is cheaper at $0.435 in / $0.870 out. The overall cheapest model on the market is Gemini 1.5 Flash-8B.
Is Kimi K2 Thinking open weights?
Yes — Kimi K2 Thinking is released as open weights, so you can self-host it instead of paying per-token API rates. The prices here are a representative hosted endpoint.