openai/gpt-oss-120b

gpt-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.

8/5/2025

131,072 tokens

#77 Text (Japanese)

Input: ¥16/M

Output: ¥79/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

min_p

presence_penalty

reasoning

reasoning_effort

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Leaderboard

Text

🏆OverallELO: 1,354

#134

🇯🇵JapaneseELO: 1,317

#77

🇨🇳ChineseELO: 1,375

#130

🇰🇷KoreanELO: 1,262

#137

🇬🇧EnglishELO: 1,362

#149

frenchELO: 1,356

#125

germanELO: 1,323

#125

spanishELO: 1,364

#109

russianELO: 1,334

#139

💻CodingELO: 1,391

#141

🧮MathELO: 1,384

#107

✍️Creative WritingELO: 1,280

#188

📝Instruction FollowingELO: 1,326

#149

🌶️Hard PromptsELO: 1,363

#142

💬Multi-TurnELO: 1,328

#157