Skip to main content
Nebius offers 39 models through Lava’s AI Gateway, supporting Chat Completions. Authentication uses Authorization: Bearer. See the Nebius API docs for provider-specific parameters.
Supports both managed (Lava’s API keys) and unmanaged (bring your own credentials) mode.

​
Quick Start

const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fapi.tokenfactory.nebius.com%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'deepseek-ai/DeepSeek-R1-0528',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});

​
Chat Completions

Target URL: https://api.tokenfactory.nebius.com/v1/chat/completions
Content Typeapplication/json
StreamingYes (set stream: true in request body)
ModelInput / 1M tokensOutput / 1M tokens
deepseek-ai/DeepSeek-V3-0324-fast$2.00$6.00
deepseek-ai/DeepSeek-R1-fast$2.00$6.00
meta-llama/Meta-Llama-3.1-405B-Instruct$1.00$3.00
NousResearch/Hermes-3-Llama-405B$1.00$3.00
deepseek-ai/DeepSeek-R1-0528$0.80$2.40
deepseek-ai/DeepSeek-R1$0.80$2.40
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1$0.60$1.80
deepseek-ai/DeepSeek-V3-0324$0.50$1.50
deepseek-ai/DeepSeek-V3$0.50$1.50
Qwen/QwQ-32B-fast$0.50$1.50
Qwen/Qwen3-30B-A3B-fast$0.30$0.90
meta-llama/Llama-3.3-70B-Instruct-fast$0.25$0.75
Qwen/Qwen2.5-72B-Instruct-fast$0.25$0.75
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.25$0.75
Qwen/Qwen3-235B-A22B$0.20$0.60
Qwen/Qwen3-32B-fast$0.20$0.60
Qwen/QwQ-32B$0.15$0.45
meta-llama/Llama-3.3-70B-Instruct$0.13$0.40
meta-llama/Meta-Llama-3.1-70B-Instruct$0.13$0.40
Qwen/Qwen2.5-32B-Instruct-fast$0.13$0.40
Qwen/Qwen2.5-72B-Instruct$0.13$0.40
aaditya/Llama3-OpenBioLLM-70B$0.13$0.40
nvidia/Llama-3_3-Nemotron-Super-49B-v1$0.13$0.40
Qwen/Qwen3-30B-A3B$0.10$0.30
Qwen/Qwen3-32B$0.10$0.30
Qwen/Qwen2.5-Coder-32B-Instruct-fast$0.10$0.30
microsoft/phi-4$0.10$0.30
Qwen/Qwen3-14B$0.08$0.24
Qwen/Qwen3-4B-fast$0.08$0.24
mistralai/Devstral-Small-2505$0.08$0.24
Qwen/Qwen2.5-Coder-32B-Instruct$0.06$0.18
Qwen/Qwen2.5-32B-Instruct$0.06$0.20
mistralai/Mistral-Nemo-Instruct-2407$0.04$0.12
meta-llama/Meta-Llama-3.1-8B-Instruct-fast$0.03$0.09
Qwen/Qwen2.5-Coder-7B-fast$0.03$0.09
google/gemma-2-9b-it-fast$0.03$0.09
meta-llama/Meta-Llama-3.1-8B-Instruct$0.02$0.06
google/gemma-2-2b-it$0.02$0.06
Qwen/Qwen2.5-Coder-7B$0.01$0.03

​
Next Steps

All Providers

Browse all supported AI providers

Forward Proxy

Learn how to construct proxy URLs and authenticate requests