MoonshotAI: Kimi K2 0905.
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...
4× AMD MI300.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 18.0 | 1228 ms | 5962 ms |
Frequently asked.
How do I run MoonshotAI: Kimi K2 0905?
Where can I access MoonshotAI: Kimi K2 0905?
How much does it cost to run MoonshotAI: Kimi K2 0905?
Is MoonshotAI: Kimi K2 0905 open-source or proprietary?
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 | |
|---|---|---|---|---|---|
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
1536 GB | — | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
768 GB | — | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for MoonshotAI: Kimi K2 0905 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.
