SambaNova - profClaw

SambaNova provides enterprise-grade inference on their custom RDU hardware. They host Llama and other open-source models with high throughput and competitive pricing.

Supported Models

SambaNova hosts various open-source models. Common options:

Model	Notes
Meta-Llama-3.1-70B-Instruct	General purpose
Meta-Llama-3.1-405B-Instruct	Largest open model
Llama-3.2-90B-Vision-Instruct	Multimodal

Check the SambaNova model catalog for the current list.

Setup

Get an API key

Set the environment variable

export SAMBANOVA_API_KEY=...

Configure in profClaw

SambaNova uses an OpenAI-compatible endpoint. Configure it as a custom OpenAI provider:

OPENAI_API_KEY=your-sambanova-key
OPENAI_BASE_URL=https://api.sambanova.ai/v1

Environment Variables

string

required

Your SambaNova Cloud API key. Configure via the OPENAI_API_KEY + OPENAI_BASE_URL pattern.

Configuration Example

.env (via OpenAI-compatible)
settings.yml

# Use the openai provider with SambaNova's endpoint
OPENAI_API_KEY=your-sambanova-api-key
OPENAI_BASE_URL=https://api.sambanova.ai/v1

providers:
  openai:
    api_key: "${SAMBANOVA_API_KEY}"
    base_url: "https://api.sambanova.ai/v1"

Usage Examples

# After configuring via OPENAI_BASE_URL
profclaw chat --model Meta-Llama-3.1-70B-Instruct "Explain this architecture"
profclaw chat --model Meta-Llama-3.1-405B-Instruct "Complex analysis task"

Notes

SambaNova’s API is OpenAI-compatible. Configure it using the openai provider with a custom base URL.
Best suited for enterprise batch inference and high-throughput workloads.
Contact SambaNova for dedicated instance pricing.

AI Providers Overview - Compare all 37 supported providers
Cerebras - Wafer-scale inference for ultra-fast token speeds
Groq - LPU-based inference at competitive speeds
profclaw provider - Add and test providers from the CLI

LM StudioRun local models via LM Studio's built-in OpenAI-compatible server. GUI-based model management with hardware acceleration.

​Supported Models

​Setup

​Environment Variables

​Configuration Example

​Usage Examples

​Notes

​Related