Sypha AI Docs
Providers

SambaNova

Discover how to activate SambaNova's incredibly fast inference within Sypha. Harness powerful open-source Meta Llama, DeepSeek, and Qwen models running exclusively on SambaNova's custom AI hardware.

SambaNova delivers lightning-fast AI inference by hosting models on their custom, purpose-built hardware. By using SambaNova, you can access the most popular open-source models from developers like Meta, DeepSeek, and Qwen at rapid speeds.

Website: https://sambanova.ai/

Getting an API Key

  1. Sign Up or Log In: Navigate to SambaNova Cloud and create an account or sign in.
  2. Go to API Keys: Find the API key management area in your dashboard.
  3. Create a New Key: Tap the button to generate a new API key.
  4. Save the Key: Copy the key to your clipboard instantly and store it securely.

Configuration in Sypha

  1. Open Sypha Settings: Click the gear icon (⚙️) inside the Sypha extension panel.
  2. Choose Provider: Find and select "SambaNova" under the "API Provider" dropdown menu.
  3. Enter API Key: Paste the SambaNova key you acquired into the required field.
  4. Select Your Model: Choose your intended model from the "Model" dropdown list.

Tips and Notes

  • Extreme Speed: Because SambaNova runs models on highly customized hardware, expect extremely fast execution speeds.
  • Excellent Model Variety: Use top-tier models from creators like Meta, DeepSeek, and Qwen natively within the platform.
  • Current Pricing: Be sure to review the SambaNova documentation for up-to-date token pricing details.

On this page