Is gpt-oss-120b (free) available on FastMetal?

Not at the moment. GPT-5.6 Sol, from the same lab, is available on the FastMetal API today.

What is the context window of gpt-oss-120b (free)?

131,072 tokens, shared between the prompt and the response.

openai/gpt-oss-120b%3Afree

Not Available

gpt-oss-120b (free)

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

Specifications

Modalities

Input

text

Output

text

Supported Parameters

include_reasoning

max_tokens

reasoning

seed

stop

temperature

tool_choice

tools

Max Output Tokens

131,072

Frequently asked questions

Is gpt-oss-120b (free) available on FastMetal?: Not at the moment. GPT-5.6 Sol, from the same lab, is available on the FastMetal API today.
What is the context window of gpt-oss-120b (free)?: 131,072 tokens, shared between the prompt and the response.

Models you can use on FastMetal