GPT OSS 120B

Overview

GPT-OSS-120B is an open-weight, 116.8B-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. It achieves near-parity with OpenAI o4-mini on core reasoning benchmarks. Note: While referred to as '120b' for simplicity, it technically has 116.8B parameters.

GPT OSS 120B was released on August 5, 2025. API access is available through 5 providers, including DeepInfra, Novita and others.

Benchmarks

GPT OSS 120B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Sat Dec 27 2025

Pricing

Pricing, performance, and capabilities for GPT OSS 120B across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
DeepInfraint4	$0.09	$0.45	131.1K	131.1K	—	—	int4	Text Image Audio Video	Text Image Audio Video
Novitabf16	$0.10	$0.50	131.1K	131.1K	—	—	bf16	Text Image Audio Video	Text Image Audio Video
OpenAI	$0.10	$0.50	131.1K	131.1K	5.2	115.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Fireworks	$0.15	$0.60	131.0K	30.0K	—	—	—	Text Image Audio Video	Text Image Audio Video
Groq	$0.15	$0.60	131.0K	30.0K	0.5	500 tok/s	—	Text Image Audio Video	Text Image Audio Video

Price Comparison for GPT OSS 120B

Price per 1M input tokens (USD), lower is better

llm-stats.com - Sat Dec 27 2025

Throughput Comparison for GPT OSS 120B

Tokens per second, higher is better

llm-stats.com - Sat Dec 27 2025

Latency Comparison for GPT OSS 120B

Time to first token (s), lower is better

llm-stats.com - Sat Dec 27 2025

API Access