modelbenchmark.io
All hosts

nebius

54 models listed here. Prices are this host's, not the vendor list price.

BGE Multilingual Gemma28K$0.01free
DeepSeek V3.2163K$0.30$0.45
DeepSeek V4 Flash131K$0.14$0.28
DeepSeek V4 Pro1M$1.75$3.50
DeepSeek-R1128K$0.80$2.40
DeepSeek-V3.2-fast8K$0.40$2.00
DeepSeek/DeepSeek-V3.2-Exp128K$0.50$1.50
E5 Mistral 7B33K$0.01free
gemma-3-27b-it110K$0.10$0.30
GLM-5200K$1.00$3.20
GLM-5.2432K$1.40$4.40
gpt-oss-120b128K$0.15$0.60
gpt-oss-120b-fast8K$0.10$0.50
Hermes 3 405B Instruct128K$1.00$3.00
Hermes 4 70B128K$0.13$0.40
hermes-4-405b128K$1.00$3.00
INTELLECT-3128K$0.20$1.10
Kimi K2.5256K$0.50$2.50
Kimi K2.7 Code262K$0.95$4.00
Kimi K31M$3.00$15.00
Kimi-K2.5-fast256K$0.50$2.50
Llama 3.1 8B Instruct128K$0.02$0.06
Llama 3.1 Nemotron Ultra 253B128K$0.60$1.80
Llama 3.3 70B Instruct128K$0.13$0.40
Llama 3.3 Nemotron Super 49B v1131K$0.10$0.40
meta-llama-3-1-405b-instruct128K$1.00$3.00
meta-llama-3-1-70b-instruct128K$0.13$0.40
MiniMax-M2.5197K$0.30$1.20
MiniMax-M2.5-fast8K$0.30$1.20
MiniMax-M31M$0.30$1.20
Mistral Nemo Instruct 2407128K$0.04$0.12
Nemotron 3 Super256K$0.30$0.90
Nemotron-3-Nano-Omni66K$0.06$0.24
nvidia-nemotron-3-nano-30b-a3b32K$0.06$0.24
qwen2-5-coder-7b33K$0.01$0.03
qwen2-vl-72b-instruct131K$0.13$0.40
qwen2-vl-7b-instruct131K$0.02$0.06
Qwen2.5 32B Instruct128K$0.06$0.20
Qwen2.5 72B Instruct128K$0.13$0.40
Qwen2.5-VL 72B Instruct128K$0.25$0.75
Qwen3 14B33K$0.08$0.24
Qwen3 235b A22B Instruct 2507262K$0.20$0.60
Qwen3 235B-A22B262K$0.20$0.60
Qwen3 30B A3B33K$0.10$0.30
Qwen3 30b A3b Instruct 2507128K$0.10$0.30
Qwen3 32B128K$0.10$0.30
Qwen3-235B-A22B-Thinking-2507-fast8K$0.50$2.00
qwen3-4b33K$0.08$0.24
Qwen3-Next 80B-A3B (Thinking)128K$0.15$1.20
Qwen3-Next-80B-A3B-Thinking-fast8K$0.15$1.20
Qwen3.5 397B-A17B262K$0.60$3.60
Qwen3.5-397B-A17B-fast8K$0.60$3.60
QwQ 32B33K$0.15$0.45
R1 Distill Llama 70B128K$0.25$0.75