SambaNova

​

Getting an API Key

1. Sign Up/Sign In: Go to SambaNova Cloud. 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

​

Meta Llama Models

• Llama-4-Maverick-17B-128E-Instruct - Llama 4 Maverick with vision support ($0.63/$1.80 per 1M tokens)
• Llama-4-Scout-17B-16E-Instruct - Llama 4 Scout ($0.40/$0.70 per 1M tokens)
• Meta-Llama-3.3-70B-Instruct (Default) - Versatile 70B model with 128K context ($0.60/$1.20 per 1M tokens)
• Meta-Llama-3.1-405B-Instruct - Largest Llama model ($5.00/$10.00 per 1M tokens)
• Meta-Llama-3.1-8B-Instruct - Compact 8B model ($0.10/$0.20 per 1M tokens)
• Meta-Llama-3.2-1B-Instruct - Ultra-compact 1B model ($0.04/$0.08 per 1M tokens)
• Meta-Llama-3.2-3B-Instruct - Small 3B model ($0.08/$0.16 per 1M tokens)

​

DeepSeek Models

• DeepSeek-R1 - Reasoning model ($5.00/$7.00 per 1M tokens)
• DeepSeek-R1-Distill-Llama-70B - Distilled reasoning model ($0.70/$1.40 per 1M tokens)
• DeepSeek-V3-0324 - General-purpose model ($3.00/$4.50 per 1M tokens)
• DeepSeek-V3.1 - Latest DeepSeek with hybrid reasoning ($3.00/$4.50 per 1M tokens)

​

Qwen Models

• Qwen3-32B - Dense 32B model ($0.40/$0.80 per 1M tokens)
• QwQ-32B - Reasoning-focused Qwen model ($0.50/$1.00 per 1M tokens)

​

Configuration in Cline

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

​

Tips and Notes

• Fast Inference: SambaNova’s custom hardware delivers competitive inference speeds.
• Wide Model Selection: Access models from Meta, DeepSeek, and Qwen on a single platform.
• Pricing: Check the SambaNova documentation for current pricing.