MODEL PROVIDER

Groq

Open-weight models such as GPT-OSS and Llama, served on Groq’s LPU inference platform for low-latency responses.

Groq has 5 models available in SteelEngine with pricing, context window, and capability details.

MODELS

5

DEFAULT MODEL

Llama 3.3 70B Versatile

PRICING

USD PER 1M TOKENS

BUILD WITH STEELENGINE

Put Groq models to work.

Use these models in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.