Kimi K3.1 Pro
Last verified October 24, 2026 · Moonshot pricing ↗$2.00/1M input · $10.00/1M output · 1.0M context · Moonshot
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
Alternatives to Kimi K3.1 Pro
Pricing Details
MoonshotLaunched October 23, 2026; post-trained Kimi K3 (~2.8T MoE). Card: $2.00 input, $2.00 5-minute cache write, $4.00 1-hour cache write, $0.20 cache hit, $10.00 output. Kimi's own price table rendered empty on 2026-10-24; rates read from OpenRouter, Vercel AI Gateway, Artificial Analysis and OrcaRouter, which all agree. 33% below K3's $3/$15 on input and output. Flat pricing to 1M, no context tiers. Caching automatic, 5m default TTL, 1h optional; partial cache blocks bill as misses. Max output defaults to 131,072, settable to 1,048,576. Reasoning always on, effort low/high/max, default max; temperature 1.0 and top_p 0.95 fixed. Same $2/$10 card as Claude Sonnet 5.5, GPT-6.1 Sol and Gemini 4 Argon (intro, to Nov 30), but cache hit is 2x theirs ($0.10). Artificial Analysis (read 2026-10-24): Intelligence Index 55, #4, $2.11 per index task, 150M output tokens (very verbose), 77.1 t/s. Moonshot-reported: Terminal-Bench 4.0 65.7 vs Opus 5.5 66.4. Open weights promised by Nov 4, license not yet stated. Only provider today is Moonshot. API ID: kimi-k3.1-pro.
Input / 1M tokens
$2
Output / 1M tokens
$10
Context Window
1.0M
Max Output
131K
Price History
Launched at current price on 2026-10-23. No price changes recorded since.
Frequently Asked Questions
Common questions about Kimi K3.1 Pro pricing and usage