OpenAIgpt-oss-120b
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.
Share
Model details
Context window131,072 tokens
Max completion size52 tokens
Prompt cost / 1K tokens$0.00000004
Completion cost / 1K tokens$0.0000002
Accepts
Produces
Benchmark performanceAll scores have maximum of 100 points.
All scores have maximum of 100 points.
Overall
62
score
23rd
placement
Cost
100
score
1st
placement
Logic
82
score
6th
placement
Speed
90
score
10th
placement
Scoring
32
score
15th
placement
Tool Use
39
score
6th
placement
Hallucination
37
score
19th
placement
Classification
29
score
3rd
placement
Structured Output
25
score
9th
placement
Pricing
| Usage pricing | |
|---|---|
| $0.00000004 | |
| $0.0000002 | |
| FREE | |
| FREE | |
| FREE | |
| FREE |
Best Overall scoring LLMs
xAI
Grok 4 Fast
88
score
1st
placement
Qwen
Qwen3 VL 235B A22B Instruct
86
score
2nd
placement
xAI
Grok 4.1 Fast
84
score
3rd
placement
OpenAI
GPT-5.1 Chat
82
score
4th
placement
OpenAI
GPT-5.1-Codex
82
score
4th
placement
Anthropic
Claude Haiku 4.5
80
score
5th
placement