gpt-oss-120b Check detailed information and pricing for AI models
Context Length 131,000 tokens, openai from provided
131,000
Context Tokens
$0.07
Prompt Price
$0.28
Output Price
7/16
Feature Support
Overall #16
translation #20
programming #20
academia #20
trivia #20
roleplay #20
finance #20
science #20
health #20
seo #20
legal #20
technology #20
marketing #20
Model Overview
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Basic Information
Developer
openai
Model Series
GPT
Release Date
2025-08-05
Context Length
131,000 tokens
Max Completion Tokens
131,000 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.07 / 1M tokens
Completion Tokens
$0.28 / 1M tokens
Data Policy
Supported Features
Supported (7)
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Reasoning
Unsupported (9)
Image Input
Response Format
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A
Other Variants
Actual Usage Statistics
#23
Out of 353 total models
134.4B
Total Tokens Last 30 Days
9.0B
Daily Average Usage
30%
Weekly Usage Change