MoonshotAI: Kimi K3.
Kimi K3 is Moonshot AI's open-weight multimodal agentic model, 2.8T parameters with 104B active, taking text, images and video with a 1M-token context, under the Kimi K3 licence.
8× AMD MI325 · $25.36/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the Kimi family.
Moonshot's frontier open-weight MoE — 1T total, 32B active.
Moonshot's open-weight reasoning variant — extended chain-of-thought training...
Multimodal agentic variant — adds a vision encoder to the K2 backbone.
Long-horizon coding + autonomous-execution upgrade over K2.5.
Kimi K2.7 Code is a modified-MIT coding agent model, 1T total and 32B active,...
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning mode...
Kimi K2 0905 is a modified-MIT mixture-of-experts model, 1T total and 32B act...
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
2048 GB | $25.36/hr | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for MoonshotAI: Kimi K3 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like MoonshotAI: Kimi K3, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About MoonshotAI: Kimi K3.
Kimi K3 is an open-weight multimodal agentic model from Moonshot AI with 2.8 trillion parameters in total and 104 billion active, using a mixture-of-experts design that routes each token to 16 of 896 experts. It understands text, images and video and has a 1-million-token context window. Moonshot aims it at long coding sessions, research and knowledge work. Weights are released under the Kimi K3 licence, not a standard open-source one.