moonshotai Open weights

Kimi K2 0905 pricing & benchmarks

Released Sep 4, 2025 · served by 2 providers

Input / 1M tokens$0.600
Output / 1M tokens$2.50
Context window262K
Cached input
1M in + 300K out$1.35

What Kimi K2 0905 is

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Providers and prices for Kimi K2 0905

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 $0.600 $2.50 262K fp8 98.7%
Groq $1.00 $3.00 262K 99.6%

Kimi K2 0905 benchmark results

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

CategoryArenaRankEloWin rate
codecategories models #80 1128 48.5%
website models #81 1132 48.3%

FAQ

How much does the Kimi K2 0905 API cost?

$0.600 per 1M input tokens and $2.50 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.35.

Is Kimi K2 0905 free?

No. It is a paid model starting at $0.600 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Kimi K2 0905?

Novita at $0.600 input / $2.50 output per 1M tokens (fp8 quantization).

Can I self-host Kimi K2 0905?

Yes — weights are published as moonshotai/Kimi-K2-Instruct-0905 on Hugging Face, so you can run it on your own hardware.