SambaCloud
Hosted inference service serving open-weight models on SambaNova's own RDU hardware, billed per token.
Find alternatives to SambaCloud
What it does
- Model inference
How it compares
-
GroqCloud
Groq similarly focuses on low-latency inference through its Language Processing Units and GroqCloud service.
Research report · 19 Sep 2026
Sources
- Pricing
- Sold within
-
SambaCloud's plans page offers a Free plan ("Start exploring SambaNova Cloud. Add a payment method and purchase credits to run your first requests.") and a Developer plan ("Pay as you go for fast inference that reliably scales on-demand", "Add Card to Upgrade"); per-model token rates are on cloud.sambanova.ai/plans/pricing. Enterprise is "Contact Sales".
- Deployment
-
Inferred 2026-09-08, not read off a page: every already-decided product of type 'model-api' in this catalogue includes "saas" in its deployment list, zero exceptions, per item 198's measured cross-tab. May be incomplete if this product also offers a self-hosted or private-cloud option; not wrong either way.
- Interfaces
-
Official documentation · 29 Sep 2026
Page states: 'With the SambaNova OpenAI compatible endpoints, simply set OPENAI_API_KEY to your SambaNova API Key.'
Also from SambaNova
-
SambaNova RDU Hardware
Reconfigurable Dataflow Unit accelerators designed to run large models at low latency.
-
SambaStack Infrastructure service
Full-stack AI system pairing SambaNova's RDU hardware with its serving software, deployed in a customer's own data centre.
-
SambaRack Hardware
Air-cooled, rack-scale AI inference hardware system integrating 16 SN50 RDU chips per rack (scalable across multiple racks); accessed via on-premises deployment, SambaCloud, or contact-sales for enterprise/government deployments.
Open SambaNova in the directory
Something wrong here? Send a correction — quote this product id: sambacloud.