Provider Detail
Nebius
Nebius models listed in the Keeptrusts catalog. Compare model families, capability metadata, and available pricing references.
Catalog snapshot published July 14, 2026. Pricing is reference data and can vary by provider, region, and account.
Quick Start
Explore Nebius models
| Model | Type | Input | Output | Max output | Capabilities |
|---|---|---|---|---|---|
BAAI/bge-multilingual-gemma2 | Embedding | $0.0100/MTok | $0.00/MTok | 8,096 tokens | — |
MiniMaxAI/MiniMax-M2.1 | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
NousResearch/Hermes-3-Llama-405B | Chat | Pricing pending | Pricing pending | 131,072 tokens | — |
NousResearch/Hermes-4-405B | Chat | $1.00/MTok | $3.00/MTok | 131,072 tokens | — |
NousResearch/Hermes-4-70B | Chat | $0.1300/MTok | $0.4000/MTok | 131,072 tokens | — |
PrimeIntellect/INTELLECT-3.1-13B | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
Qwen/QwQ-32B | Chat | Pricing pending | Pricing pending | 131,072 tokens | — |
Qwen/QwQ-32B-fast | Chat | Pricing pending | Pricing pending | 131,072 tokens | — |
Qwen/Qwen2-VL-72B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | Vision |
Qwen/Qwen2-VL-7B-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | Vision |
Qwen/Qwen2.5-1.5B-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen2.5-32B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
Qwen/Qwen2.5-32B-Instruct-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
Qwen/Qwen2.5-72B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
Qwen/Qwen2.5-72B-Instruct-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
Qwen/Qwen2.5-Coder-32B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | Code |
Qwen/Qwen2.5-Coder-32B-Instruct-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | Code |
Qwen/Qwen2.5-Coder-7B | Chat | Pricing pending | Pricing pending | 4,096 tokens | Code |
Qwen/Qwen2.5-Coder-7B-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | Code |
Qwen/Qwen2.5-Coder-7B-Instruct-fast | Chat | Pricing pending | Pricing pending | 4,096 tokens | Code |
Qwen/Qwen2.5-Coder-7B-fast | Chat | $0.0300/MTok | $0.0900/MTok | 4,096 tokens | Code |
Qwen/Qwen2.5-VL-72B-Instruct | Chat | Pricing pending | Pricing pending | 32,000 tokens | Vision |
Qwen/Qwen3-0.6B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-0.6B-Base | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-1.7B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-1.7B-Base | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-14B | Chat | Pricing pending | Pricing pending | 40,960 tokens | — |
Qwen/Qwen3-14B-Base | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-235B-A22B-Instruct-2507 | Chat | $0.2000/MTok | $0.6000/MTok | 262,144 tokens | — |
Qwen/Qwen3-235B-A22B-Thinking-2507 | Chat | $0.2000/MTok | $0.8000/MTok | 262,144 tokens | — |
Qwen/Qwen3-30B-A3B | Chat | Pricing pending | Pricing pending | 40,960 tokens | — |
Qwen/Qwen3-30B-A3B-Instruct-2507 | Chat | $0.1000/MTok | $0.3000/MTok | 262,144 tokens | — |
Qwen/Qwen3-30B-A3B-Thinking-2507 | Chat | $0.1000/MTok | $0.3000/MTok | 262,144 tokens | — |
Qwen/Qwen3-32B | Chat | $0.1000/MTok | $0.3000/MTok | 40,960 tokens | — |
Qwen/Qwen3-32B-fast | Chat | $0.2000/MTok | $0.6000/MTok | 40,960 tokens | — |
Qwen/Qwen3-4B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-4B-Base | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-8B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-8B-Base | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
Qwen/Qwen3-Coder-30B-A3B-Instruct | Chat | $0.1000/MTok | $0.3000/MTok | 262,144 tokens | — |
Qwen/Qwen3-Coder-480B-A35B-Instruct | Chat | $0.4000/MTok | $1.80/MTok | 262,144 tokens | — |
Qwen/Qwen3-Embedding-8B | Embedding | Pricing pending | Pricing pending | 8,096 tokens | — |
Qwen/Qwen3-Next-80B-A3B-Thinking | Chat | Pricing pending | Pricing pending | 32,768 tokens | — |
aaditya/Llama3-OpenBioLLM-70B | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
aaditya/Llama3-OpenBioLLM-8B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
allenai/OLMo-7B-Instruct-hf | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
black-forest-labs/flux-dev | Chat | Pricing pending | Pricing pending | 128,000 tokens | Vision |
black-forest-labs/flux-schnell | Chat | Pricing pending | Pricing pending | 128,000 tokens | Vision |
cognitivecomputations/dolphin-2.9.2-mixtral-8x22b | Chat | Pricing pending | Pricing pending | 32,768 tokens | — |
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | Code |
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct-fast | Chat | Pricing pending | Pricing pending | 4,096 tokens | Code |
deepseek-ai/DeepSeek-R1-0528 | Chat | $0.8000/MTok | $2.40/MTok | 163,840 tokens | — |
deepseek-ai/DeepSeek-R1-0528-fast | Chat | $2.00/MTok | $6.00/MTok | 32,768 tokens | — |
deepseek-ai/DeepSeek-V3 | Chat | Pricing pending | Pricing pending | 163,840 tokens | — |
deepseek-ai/DeepSeek-V3-0324 | Chat | $0.5000/MTok | $1.50/MTok | 128,000 tokens | — |
deepseek-ai/DeepSeek-V3-0324-fast | Chat | $0.7500/MTok | $2.25/MTok | 32,768 tokens | — |
deepseek-ai/DeepSeek-V3.1 | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
deepseek-ai/DeepSeek-V3.2 | Chat | $0.3000/MTok | $0.4500/MTok | 128,000 tokens | — |
google/gemma-2-27b-it | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
google/gemma-2-27b-it-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
google/gemma-2-2b-it | Chat | $0.0200/MTok | $0.0600/MTok | 4,096 tokens | — |
google/gemma-2-2b-it-fast | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
google/gemma-2-9b-it | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
google/gemma-2-9b-it-fast | Chat | $0.0300/MTok | $0.0900/MTok | 4,096 tokens | — |
google/gemma-3-27b-it | Chat | $0.1000/MTok | $0.3000/MTok | 110,000 tokens | Vision |
google/gemma-3-27b-it-fast | Chat | $0.2000/MTok | $0.6000/MTok | 110,000 tokens | Vision |
intfloat/e5-mistral-7b-instruct | Embedding | $0.0100/MTok | $0.00/MTok | 8,096 tokens | — |
llava-hf/llava-1.5-13b-hf | Chat | Pricing pending | Pricing pending | 4,096 tokens | Vision |
llava-hf/llava-1.5-7b-hf | Chat | Pricing pending | Pricing pending | 4,096 tokens | Vision |
meta-llama/Llama-3.2-1B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
meta-llama/Llama-3.2-1B-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
meta-llama/Llama-3.2-3B | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
meta-llama/Llama-3.2-3B-Instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
meta-llama/Llama-3.3-70B-Instruct | Chat | $0.1300/MTok | $0.4000/MTok | 8,192 tokens | — |
meta-llama/Llama-3.3-70B-Instruct-fast | Chat | $0.2500/MTok | $0.7500/MTok | 8,192 tokens | — |
meta-llama/Llama-Guard-3-8B | Chat | $0.2000/MTok | $0.6000/MTok | 4,096 tokens | — |
meta-llama/Meta-Llama-3.1-405B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
meta-llama/Meta-Llama-3.1-70B-Instruct | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
meta-llama/Meta-Llama-3.1-70B-Instruct-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
meta-llama/Meta-Llama-3.1-8B-Instruct | Chat | $0.0200/MTok | $0.0600/MTok | 4,096 tokens | — |
meta-llama/Meta-Llama-3.1-8B-Instruct-fast | Chat | $0.0300/MTok | $0.0900/MTok | 4,096 tokens | — |
microsoft/Phi-3-medium-128k-instruct | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
microsoft/Phi-3-medium-128k-instruct-fast | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
microsoft/Phi-3-mini-4k-instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
microsoft/Phi-3-mini-4k-instruct-fast | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
microsoft/Phi-3.5-MoE-instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
microsoft/Phi-3.5-mini-instruct | Chat | Pricing pending | Pricing pending | 4,096 tokens | — |
mistralai/Devstral-Small-2505 | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
mistralai/Mistral-Nemo-Instruct-2407 | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
mistralai/Mistral-Nemo-Instruct-2407-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
mistralai/Mixtral-8x22B-Instruct-v0.1 | Chat | Pricing pending | Pricing pending | 32,768 tokens | — |
mistralai/Mixtral-8x22B-Instruct-v0.1-fast | Chat | Pricing pending | Pricing pending | 32,768 tokens | — |
mistralai/Mixtral-8x7B-Instruct-v0.1 | Chat | Pricing pending | Pricing pending | 32,768 tokens | Tools |
mistralai/Mixtral-8x7B-Instruct-v0.1-fast | Chat | Pricing pending | Pricing pending | 32,768 tokens | Tools |
moonshotai/Kimi-K2-Instruct | Chat | $0.5000/MTok | $2.40/MTok | 131,072 tokens | — |
moonshotai/Kimi-K2-Thinking | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF-fast | Chat | Pricing pending | Pricing pending | 8,192 tokens | — |
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | Chat | $0.6000/MTok | $1.80/MTok | 131,072 tokens | — |
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | Chat | Pricing pending | Pricing pending | 131,072 tokens | — |
nvidia/Nemotron-Nano-V2-12b | Chat | Pricing pending | Pricing pending | 128,000 tokens | — |
openai/gpt-oss-120b | Chat | $0.1500/MTok | $0.6000/MTok | 131,072 tokens | — |
openai/gpt-oss-20b | Chat | $0.0500/MTok | $0.2000/MTok | 131,072 tokens | — |
zai-org/GLM-4.5 | Chat | $0.6000/MTok | $2.20/MTok | 131,072 tokens | — |
zai-org/GLM-4.5-Air | Chat | $0.2000/MTok | $1.20/MTok | 131,072 tokens | — |
zai-org/GLM-4.7-FP8 | Chat | Pricing pending | Pricing pending | 131,072 tokens | — |
No Nebius models match your search.
Related providers
Compare other large provider catalogs.