Nebius AI Studio

Nebius AI Studio provides inference for a wide range of open-source models including DeepSeek, Qwen, Llama, and others, with competitive pricing and fast/standard speed tiers.

Website: https://studio.nebius.com/

Getting an API Key

1. Sign Up/Sign In: Go to Nebius AI Studio. Create an account or sign in.
2. Navigate to API Keys: Access the API key section in your dashboard.
3. Create a Key: Generate a new API key.
4. Copy the Key: Copy the API key immediately and store it securely.

Supported Models

Cline supports the following Nebius models:

DeepSeek Models

• deepseek-ai/DeepSeek-V3 - General-purpose model ($0.50/$1.50 per 1M tokens)
• deepseek-ai/DeepSeek-V3-0324-fast - Fast variant ($2.00/$6.00 per 1M tokens)
• deepseek-ai/DeepSeek-R1 - Reasoning model ($0.80/$2.40 per 1M tokens)
• deepseek-ai/DeepSeek-R1-fast - Fast reasoning ($2.00/$6.00 per 1M tokens)
• deepseek-ai/DeepSeek-R1-0528 - Latest reasoning version (163K context, $0.80/$2.40 per 1M tokens)
• deepseek-ai/DeepSeek-R1-0528-fast - Fast latest reasoning ($2.00/$6.00 per 1M tokens)

Qwen Models

• Qwen/Qwen3-Coder-480B-A35B-Instruct - 480B coding model (262K context, $0.40/$1.80 per 1M tokens)
• Qwen/Qwen3-235B-A22B - 235B MoE model ($0.20/$0.60 per 1M tokens)
• Qwen/Qwen3-235B-A22B-Instruct-2507 - Latest instruct version (262K context, $0.20/$0.60 per 1M tokens)
• Qwen/Qwen3-32B / Qwen/Qwen3-32B-fast - Dense 32B model
• Qwen/Qwen3-30B-A3B / Qwen/Qwen3-30B-A3B-fast - Compact MoE model
• Qwen/Qwen3-4B-fast - Small fast model ($0.08/$0.24 per 1M tokens)
• Qwen/Qwen2.5-Coder-32B-Instruct-fast - Coding-optimized ($0.10/$0.30 per 1M tokens)
• Qwen/Qwen2.5-32B-Instruct-fast (Default) - General-purpose ($0.13/$0.40 per 1M tokens)

Other Models

• moonshotai/Kimi-K2-Instruct - Kimi K2 with prompt caching (131K context, $0.50/$2.40 per 1M tokens)
• openai/gpt-oss-120b - OpenAI's 120B open-weight model ($0.15/$0.60 per 1M tokens)
• openai/gpt-oss-20b - OpenAI's 20B open-weight model ($0.05/$0.20 per 1M tokens)
• zai-org/GLM-4.5 / zai-org/GLM-4.5-Air - Z AI models with prompt caching
• meta-llama/Llama-3.3-70B-Instruct-fast - Fast Llama 3.3 ($0.25/$0.75 per 1M tokens)

Configuration in Cline

1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
2. Select Provider: Choose "Nebius AI Studio" from the "API Provider" dropdown.
3. Enter API Key: Paste your Nebius API key.
4. Select Model: Choose your desired model from the "Model" dropdown.

Tips and Notes

• Speed Tiers: Models with -fast suffix offer faster inference at higher prices.
• Wide Selection: Access models from DeepSeek, Qwen, Meta, Moonshot, OpenAI, and Z AI.
• Competitive Pricing: Generally lower prices than direct provider APIs.
• Pricing: Check the Nebius documentation for current rates.