Inference Provider

SIMBA + Samba Nova Cloud

Very-high-throughput LLM inference on Samba Nova hardware.

Samba Nova Cloud offers high tokens-per-second on open-weight models. Good fit for agents with dense turn-taking where token throughput drives perceived latency.

What agents can do

High-throughput open-source model inference
OpenAI-compatible API

Common workflows

High-turn-density agents

Back-and-forth conversations where throughput matters more than first-token latency.

Setup

1
Request API access in Samba Nova Cloud.
2
Add the Samba Nova integration in SIMBA.
3
Point your agent's LLM provider at Samba Nova.

Frequently asked questions

Do they support function calling?

On recent model versions, yes. Check Samba Nova docs for the model you pick.

Connect Samba Nova Cloud in the dashboard

Bring your own credentials. SIMBA stores them server-side and your agents call Samba Nova Cloud during conversations.

Open dashboard Talk to sales

More inference provider integrations

Groq Cloud Together AI Cloudflare Workers AI