OpenAI GPT OSS 120B
OpenAI GPT OSS 120B is a Groq model available in SteelEngine. It supports a 131k token context window. Pricing starts at $0.15/1M input tokens and $0.6/1M output tokens. Key capabilities include Tool choice, Structured outputs.
Higher-priced model for demanding generation and analysis. Handles 131k tokens of context.
INPUT / 1M
$0.15
CACHED INPUT / 1M
$0.075
OUTPUT / 1M
$0.6
CONTEXT WINDOW
131k
MAX OUTPUT
Not published
PRICING
What OpenAI GPT OSS 120B costs to run.
List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.
01 / INPUT
$0.15
per 1M input tokens
02 / CACHED INPUT
$0.075
per 1M cached input tokens
03 / OUTPUT
$0.6
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What OpenAI GPT OSS 120B supports.
Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.
CAPABILITIES
Tool choice, Structured outputs
CONTEXT WINDOW
131k
MAX OUTPUT TOKENS
Not published
MODEL ID
groq/openai/gpt-oss-120b
PROVIDER
Groq
MORE MODELS
More from Groq
Compare nearby options from the same provider before you pick a default for your workflow.
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
BUILD WITH STEELENGINE
Put OpenAI GPT OSS 120B to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.