Kimi K2 Instruct
As of Nov 22, 2026, the cheapest Kimi K2 Instruct API price is $0.4 per 1M input tokens (NanoGPT) and $1.8 per 1M output tokens (NanoGPT). Kimi K2 Instruct is offered by 7 providers in the kimi family, open weights.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| NanoGPTopenmoonshotai/kimi-k2-instruct | Cheapest$0.4 | Cheapest$1.8 | $0.2 | — | 256k | — |
| Eden AIopendeepinfra/moonshotai/Kimi-K2-Instruct | $0.5 | $2 | — | — | 131k | — |
| IO.NETopenmoonshotai/Kimi-K2-Instruct-0905 | $0.57 | $2.3 | $0.285 | — | 33k | 31d ago |
| Jiekou.AIopenmoonshotai/kimi-k2-instruct | $0.57 | $2.3 | — | — | 131k | — |
| Novita AIopenmoonshotai/kimi-k2-instruct | $0.57 | $2.3 | — | — | 131k | — |
| Vercel AI Gatewayopenmoonshotai/kimi-k2 | $0.57 | $2.3 | — | — | 131k | — |
| Hugging Faceopenmoonshotai/Kimi-K2-Instruct | $1 | $3 | — | — | 131k | — |
Kimi K2 Instruct price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| IO.NET | $0.39 → $0.57 | $1.9 → $2.3 | +21.1% |
Kimi K2 Instruct pricing FAQ
What is the cheapest Kimi K2 Instruct API?
As of Nov 22, 2026, NanoGPT has the lowest Kimi K2 Instruct output price at $1.8 per 1M tokens, and NanoGPT has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Kimi K2 Instruct?
7 providers list Kimi K2 Instruct on Sovyron; 7 of them sell it at a metered per-token price.
Is Kimi K2 Instruct free?
No provider in the Sovyron catalog lists a free tier for Kimi K2 Instruct.
What is the context window of Kimi K2 Instruct?
Kimi K2 Instruct supports a 256k-token context window and up to 131k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—