OpenAI

gpt-oss-120b

by OpenAItext->text23 endpoints
Neura Intelligence Index
46.1/ 100
Rank
#196
Confidence
low
Benchmarks
3(8% coverage)

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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
118.0K tokens
Knowledge Cutoff
2024-06-30
Tokenizer
GPT
Uptime (24h)
10000.0%
Parameters
116800000000B
License
apache_2_0Open Weights
Country
🇺🇸US
Release Date
August 5, 20251y

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Benchmark Performance

reasoning

BenchmarkScoreSource
GPQA Diamond
80.1
verified
Humanity's Last Exam
14.9
verified

agent

BenchmarkScoreSource
TAU-Bench Retail
67.8
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.04
Output$0.17
Added
August 5, 2025
Last synced 9/16/2026