# Nebius

HQ NL · serves 42 tracked open-weights models, 24 confirmed by its own catalog. · privacy policy

models
42
verified
24
of overall top 10
7
cheapest on
4 models
vs best $
1.32×
ctx (median)
147k
uptime
99.6%

# models

model rank $/M in $/M out $/M cache src ✓
glm-5.3 #1 $1.40 $4.40 $0.26 openrouter ✓
kimi-k3 #2 — — — nebius ✓
glm-5.3-flash #3 $0.15 $0.50 $0.03 openrouter ✓
deepseek-v4-flash-0731 #6 — — — nebius ✓
deepseek-v4-pro #7 — — — nebius ✓
qwen3.8-27b #8 — — — nebius ✓
glm-5.2 #10 $1.40 $4.40 $0.14 openrouter ✓
minimax-m3 #12 — — — nebius ✓
kimi-k2.6 #15 — — — nebius ✓
glm-5.1 #18 $1.40 $4.40 — openrouter ✓
kimi-k2.7-code #19 $0.95 $4.00 $0.15 openrouter ✓
minimax-m2.5 #20 $0.30 $1.20 $0.30 requesty —
deepseek-v4-flash #22 $0.14 $0.28 — litellm —
qwen3.5-397b-a17b #31 — — — nebius ✓
deepseek-r1 #55 $0.80 $2.40 — litellm —
qwen3-235b-a22b-instruct-2507 #59 — — — nebius ✓
gpt-oss-120b #63 $0.15 $0.60 — openrouter ✓
deepseek-v3 #77 $0.50 $1.50 — litellm —
qwq-32b #85 $0.15 $0.45 — litellm —
llama-3.3-70b-instruct #94 $0.13 $0.40 $0.13 requesty —
qwen2.5-72b-instruct #99 $0.13 $0.40 — litellm —
gemma-3-27b-it #106 $0.10 $0.30 — openrouter ✓
beam-1.0-501b-a23b — $0.25 $1.00 $0.05 openrouter —
deepseek-chat-v3-0324 — $0.50 $1.50 — litellm —
deepseek-r1-0528 — $0.80 $2.40 — litellm —
deepseek-v4-pro-0813 — — — — nebius ✓
deepseek-v4.1-flash — $0.30 $1.20 $0.01 openrouter ✓
deepseek-v4.1-flash-1017 — $0.30 $1.20 $0.01 openrouter ✓
llama-3.1-405b-instruct — $1.00 $3.00 — litellm —
minimax-m3.1-flash — $0.15 $0.60 $0.01 openrouter ✓
muse-spark-open — $1.25 $4.25 $0.15 openrouter ✓
nemotron-3-nano-30b-a3b — $0.06 $0.24 — openrouter —
nemotron-3-super-120b-a12b — — — — nebius ✓
nemotron-3-ultra-550b-a55b — — — — nebius ✓
nemotron-3.5-super-vl — — — — nebius ✓
qwen2.5-vl-72b-instruct — $0.25 $0.75 — litellm —
qwen3-14b — $0.08 $0.24 — litellm —
qwen3-235b-a22b — $0.20 $0.60 — litellm —
qwen3-30b-a3b — $0.10 $0.30 — litellm —
qwen3-30b-a3b-instruct-2507 — $0.10 $0.30 — openrouter ✓
qwen3-32b — $0.10 $0.30 $0.10 requesty —
qwen3-next-80b-a3b-thinking — $0.15 $1.20 $0.15 requesty —

all providers · machine-readable: providers.json