gpt-oss-120b

The gpt-oss-120b model from OpenAI is a generative model with reasoning capabilities.

Model ID

gpt-oss-120b

Source

Hugging Face

Modality

• Input: text
• Output: text

Features

• Streaming
• Tool calling
• Structured outputs

Context limit

• Context window: 128k tokens

Endpoints

• /v1/chat/completions
• /v1/completions

Rate limits

This model has a rate limit multiplier of 1.0. The effective rate limit for the Free and Standard tier is 100,000 prompt tokens/minute and 10,000 completion tokens/minute. The effective monthly quota for the Free tier is 1,000,000 tokens/month.