GPT Oss 120b
T powerful open-weight model, fits into an H100 GPU
Context window
131,072 tokens
Input price
Per 1M input tokens
Output price
Per 1M output tokens
Access
Registry access classification
Overview
Where this model fits best
A premium detail page should answer the top-level selection question first, then fan out into technical specifics.
Best fit
Use this model when you need a well-documented, structured option inside the registry and want a single place to inspect pricing, capabilities, and operational limits.
Use cases
Capabilities
What you can actually do with it
Grouped by features, endpoints, and tools so the page reads like a product brief instead of a flat checklist.
Capabilities
High-level features exposed by the model runtime.
Endpoints
APIs and surfaces this model can be called through.
Pricing
Commercial shape at a glance
Pricing is presented as carded offers instead of a plain table, which makes the hierarchy easier to scan on desktop and mobile.
Standard API
Input
Output
Default request pricing when using the primary endpoint.
Controls
Runtime knobs worth knowing
Supported parameters are surfaced as control cards so sampling behavior reads like an operational surface, not a spreadsheet.
Temperature
0 to 2
Top P
0 to 1
Frequency penalty
-2 to 2
Presence penalty
-2 to 2
Max stop sequences
Maximum number of stop values accepted
Specifications
Technical reference
Dense metadata is moved into a card grid so the bottom of the page still feels deliberate and easy to skim.
Model ID
gpt-oss-120bProvider
Family
Access type
Input modalities
Output modalities
Max output tokens