---
id: "nebius"
site: "nebius.com"
headquarters: "NL"
gateways: ["openrouter", "requesty", "vercel"]
models: 46
endpoints: 64
tokens_week: 22944770030
token_share: "0.2%"
rank: 50
cheapest_on: "13 of 55 shared models"
cheaper_than: "59% of offers at the median"
vs_card: "at the card price at the median over 10 models"
cache_hit: "71.2%"
uptime_1d: 93.2000
latency_p50_ms: 882
tokens_per_second: 82
trains_on_some: false
retains_on_some: false
quantization: "fp4 (23), fp8 (21), bf16 (2), int4 (1), unknown (1)"
---
# Nebius

`alibaba/qwen3-235b-a22b-instruct-2507`, `alibaba/qwen3-30b-a3b-instruct-2507`, `alibaba/qwen3-32b`, `alibaba/qwen3.5-397b-a17b`, `alibaba/qwen3-embedding-8b`, `alibaba/qwen3-next-80b-a3b-thinking`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-pro-0424`, `deepseek/deepseek-v4-pro-0813`, `google/gemma-3-27b-it`, `meta/llama-3.3-70b-instruct`, `meta-llama/llama-3.3-70b-instruct`, `meta/muse-spark-open`, `minimax/minimax-m2.5`, `minimax/minimax-m3`, `minimax/minimax-m3.1-flash`, `moonshotai/kimi-k3`, `moonshotai/kimi-k3.1-pro`, `moonshot/kimi-k2.6`, `moonshot/kimi-k3`, `nousresearch/hermes-4-405b`, `nousresearch/hermes-4-70b`, `nvidia/nemotron-3.5-super-vl`, `nvidia/nemotron-3-nano-30b-a3b`, `nvidia/nemotron-3-nano-omni`, `nvidia/nemotron-3-super-120b-a12b`, `nvidia/nemotron-3-ultra-550b-a55b`, `openai/gpt-oss-120b`, `qwen/qwen2.5-vl-72b-instruct`, `qwen/qwen3-235b-a22b-2507`, `qwen/qwen3-30b-a3b-instruct-2507`, `qwen/qwen3-32b`, `qwen/qwen3.8-27b`, `qwen/qwen3-embedding-8b`, `qwen/qwen3-next-80b-a3b-thinking`, `reflection/beam`, `reflection/beam-1.0-501b-a23b`, `z-ai/glm-5.1`, `zai/glm-5.1`, `z-ai/glm-5.2`, `zai/glm-5.2`, `z-ai/glm-5.3`, `z-ai/glm-5.3-flash`, `zai/glm-5.3-flash`