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
MODELS
Groq models in SteelEngine.
Recommended models come first. Open any model for its full price sheet, limits, and supported capabilities.
Groq
OpenAI GPT OSS 120B
Higher-priced model for demanding generation and analysis. Handles 131k tokens of context.
IN / 1M
$0.15
OUT / 1M
$0.6
CONTEXT
131k
Groq
OpenAI GPT OSS 20B
Lower-priced model for high-volume classification, extraction, and routing. Handles 131k tokens of context. 20B-parameter size in its family.
IN / 1M
$0.075
OUT / 1M
$0.3
CONTEXT
131k
Groq
OpenAI GPT OSS Safeguard 20B
Lower-priced model for high-volume classification, extraction, and routing. Handles 131k tokens of context. Safety-tuned variant for content classification and policy checks.
IN / 1M
$0.075
OUT / 1M
$0.3
CONTEXT
131k
Groq
Llama 3.1 8B Instant
The lowest-cost model in the Groq lineup, for high-volume classification, extraction, and routing. Handles 131k tokens of context.
IN / 1M
$0.05
OUT / 1M
$0.08
CONTEXT
131k
Groq
Llama 3.3 70B Versatile
The highest-priced model in the Groq lineup, for the hardest generation and analysis work. Handles 131k tokens of context.
IN / 1M
$0.59
OUT / 1M
$0.79
CONTEXT
131k
MORE PROVIDERS
Compare other providers.
Every provider page lists the same pricing and capability details, so you can compare like for like.
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.