Nebius AI Provider
Nebius AI Studio - OpenAI-compatible API for large language models
Available Models
llama-3.1-8b-instruct
meta-llama/Meta-Llama-3.1-8B-Instruct
nebius/llama-3.1-8b-instructContext: 128k
$0.02 in/$0.06 out
llama-3.1-nemotron-ultra-253b
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
nebius/llama-3.1-nemotron-ultra-253bContext: 128k
$0.60 in/$1.80 out
llama-3.3-nemotron-super-498
nvidia/Llama-3_3-Nemotron-Super-49B-v1
nebius/llama-3.3-nemotron-super-498Context: 128k
$0.60 in/$1.80 out
llama-3.3-70b-instruct
meta-llama/Llama-3.3-70B-Instruct
nebius/llama-3.3-70b-instructContext: 128k
$0.13 in/$0.40 out
llama-3.1-405b-instruct
meta-llama/Meta-Llama-3.1-405B-Instruct
nebius/llama-3.1-405b-instructContext: 128k
$1.00 in/$3.00 out
openbio-llama3-70b
aaditya/Llama3-OpenBioLLM-70B
nebius/openbio-llama3-70bContext: 8.2k
$0.13 in/$0.40 out
deepseek-v3
deepseek-ai/DeepSeek-V3
cloudrift/deepseek-v3Context: 163.8k
$0.15 in/$0.40 out
deepseek-r1
deepseek-ai/DeepSeek-R1
cloudrift/deepseek-r1Context: 163.8k
$0.15 in/$0.40 out
deepseek-r1-distill-llama-70b
deepseek-r1-distill-llama-70b
groq/deepseek-r1-distill-llama-70bContext: 131.1k
$0.75 in/$0.99 out
mistral-nemo-instruct-2407
mistralai/Mistral-Nemo-Instruct-2407
nebius/mistral-nemo-instruct-2407Context: 128k
$0.04 in/$0.12 out
qwen3-235b-a22b
Qwen/Qwen3-235B-A22B
nebius/qwen3-235b-a22bContext: 131.1k
$0.20 in/$0.60 out
qwen25-coder-7b
Qwen/Qwen2.5-Coder-7B
nebius/qwen25-coder-7bContext: 32.8k
$0.01 in/$0.03 out
qwen25-32b-instruct
Qwen/Qwen2.5-32B-Instruct
nebius/qwen25-32b-instructContext: 32.8k
$0.06 in/$0.20 out
qwen25-72b-instruct
Qwen/Qwen2.5-72B-Instruct
nebius/qwen25-72b-instructContext: 32.8k
$0.13 in/$0.40 out
qwen2-vl-72b-instruct
Qwen/Qwen2-VL-72B-Instruct
nebius/qwen2-vl-72b-instructContext: 32.8k
$0.13 in/$0.40 out
qwen2-5-vl-72b-instruct
Qwen/Qwen2.5-VL-72B-Instruct
nebius/qwen2-5-vl-72b-instructContext: 32.8k
$0.13 in/$0.40 out
hermes-3-llama-405b
NousResearch/Hermes-3-Llama-405B
nebius/hermes-3-llama-405bContext: 131.1k
$1.00 in/$3.00 out