Skip to main content

gpt-oss-120b vs gpt-oss-20b

Pricing, Performance & Features Comparison

Authoropenai

Context Length131K

Reasoning

-

Providers0

ReleasedAug 2025

Knowledge Cutoff–

License–

OpenAI most powerful open weight model, which fits into a single H100 GPU.

Input–

Output–

Latency (p50)–

Output Limit131K

Function Calling

JSON Mode

-

InputText

OutputText

–

Authoropenai

Context Length131K

Reasoning

-

Providers0

ReleasedAug 2025

Knowledge Cutoff–

License–

OpenAI medium-sized open weight model for low latency.

Input–

Output–

Latency (p50)–

Output Limit131K

Function Calling

-

JSON Mode

-

InputText

OutputText

–