Nebius models
European AI cloud Token Factory with transparent per-token open-model inference.
Gemma 3 27B (Nebius)
$0.1 / $0.3 per 1M tokens
GLM-5.2 (Nebius)
$1.40 / $4.40 per 1M tokens
Kimi K3 (Nebius)
$3.00 / $15.00 per 1M tokens
Llama 3.1 405B (Nebius)
$1.00 / $3.00 per 1M tokens
Nebius
European AI cloud Token Factory with transparent per-token open-model inference.
There are 4 published models here. On a 70/30 mix, combined list rates run from $0.16 to $6.60 per 1 million tokens, with a median of $1.95. The largest listed context window in this group is 1,000,000 tokens. The most recent price check in this group is 2026-08-14.
Nebius list rates
USD per million tokens. The 70/30 mix is a planning default — change it on the model page if your traffic is output-heavy.
| Model | Input / 1M | Output / 1M | Mixed 70/30 | Context | Verified |
|---|---|---|---|---|---|
| Gemma 3 27B (Nebius) | $0.1 | $0.3 | $0.16 | 128,000 | |
| Llama 3.1 405B (Nebius) | $1.00 | $3.00 | $1.60 | 128,000 | |
| GLM-5.2 (Nebius) | $1.40 | $4.40 | $2.30 | 1,000,000 | |
| Kimi K3 (Nebius) | $3.00 | $15.00 | $6.60 | 1,000,000 |
Questions about Nebius rates
Do these Nebius figures include discounts and tax?
No. They are public list rates. Commits, credits, regions, tax, and commercial discounts are not in the number — check the source linked on each model.
When is the more expensive Nebius tier worth the extra?
Kimi K3 (Nebius) sits near $6.60 per 1M tokens on a 70/30 mix, versus $0.16 on Gemma 3 27B (Nebius). Use the high tier when retries or long reasoning actually fail on the cheap one.