moonshotai Open weights

Kimi K2 0711 pricing & benchmarks

Released Jul 11, 2025 · served by 1 provider

Input / 1M tokens$0.570
Output / 1M tokens$2.30
Context window131K
Cached input
1M in + 300K out$1.26

What Kimi K2 0711 is

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Providers and prices for Kimi K2 0711

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Novitacheapest $0.570 $2.30 131K fp8 100.0%

Kimi K2 0711 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
uicomponent models #83 1068 55.1%
codecategories models #91 1064 51.7%
dataviz models #91 1048 49.4%
website models #93 1075 53.1%
gamedev models #96 1030 46.4%

FAQ

How much does the Kimi K2 0711 API cost?

$0.570 per 1M input tokens and $2.30 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.26.

Is Kimi K2 0711 free?

No. It is a paid model starting at $0.570 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Kimi K2 0711?

Novita at $0.570 input / $2.30 output per 1M tokens (fp8 quantization).

Can I self-host Kimi K2 0711?

Yes — weights are published as moonshotai/Kimi-K2-Instruct on Hugging Face, so you can run it on your own hardware.