OpenAI has released gpt-oss series, a new line of open-weight models built for strong reasoning, agentic tasks, and flexible developer use. There are two variants of these models:
gpt-oss-120b — with 117B parameters with 5.1B active parameters and suits for production, general purpose, high reasoning use cases that fit into a single H100 GPU.
gpt-oss-20b — with 21B parameters with 3.6B active parameters and fits for low latency, and local or specialized use cases.
NOTE
You can try out gpt-oss model on gpt-oss playground.
Apache 2.0 License: Use, modify, and sell your projects freely without legal worries.
Custom reasoning levels: Choose the model reasoning level (low, medium, high) based on your scenario and latency needs.
Full chain-of-thought: Full access to how the model reasons, which helps with debugging and understanding its outputs.
Fine-tuning: Train the models further to fit your specific needs.
Built-in tools: Include function calling, web brwosing, Python code execution and structured outputs.
Native MXFP4 quantization: The models use a memory-efficient format (MXFP4), therefore allowing gpt-oss-120b to run on a single H100 GPU and gpt-oss-20b to run in just 16GB of memory.
NOTE
gpt-oss-120b and gpt-oss-20b were trained on harmony response format (the only format should be used).
Every message that the model processes has a role associated with it. The types of roles:
system – Sets reasoning level, knowledge cutoff, and built-in tools.
developer – Provides model instructions and available tools.
user – Represents user input to the model.
assistant – Model’s output: a reply or tool call, sometimes tied to a specific channel.
tool – Output from a tool call; the tool’s name is used as the role in the message.
Assistant messages can be sent through three distinct “channels,” separating user-visible replies from internal reasoning and tool-related content.
final – Model’s response meant for the end-user.
analysis – Used for the model’s internal reasoning / chain-of-thought (CoT); not safe for user display.
commentary – Typically used for function tool calls or preambles before tool use; sometimes includes built-in tools.
The model uses special tokens to understand input structure. Here’s what each token means:
<|start|> – Marks the beginning of a message, followed by header info (starting with role).
<|end|> – Marks the end of a message.
<|message|> – Separates the message header from its main content.
<|channel|> – Indicates the start of channel information in the header.
<|constrain|> – Marks the start of data type definitions in a tool call.
<|return|> – Signals the end of the model’s response; inference should stop.
<|call|> – Signals a tool call; also used to stop inference.
The harmony response format is made up of “messages” and the model may generate several messages at once. Each message generally follows this structure:
<|start|>{header}<|message|>{content}<|end|>Here’s an example of how special tokens are used in the harmony message format for chat conversations. For more use cases, see the OpenAI Harmony Response Format.
<|start|>user<|message|>What is 2 + 2?<|end|>
<|start|>assistantThis is a basic chat format where the input begins with a user message, followed by the assistant.
<|channel|>analysis<|message|>User asks: "What is 2 + 2?" Simple arithmetic. Provide answer.<|end|>
<|start|>assistant<|channel|>final<|message|>2 + 2 = 4.<|return|>The output includes a message in the analysis channel for the model's chain-of-thought reasoning. Then it switches to the final channel and ends with <|return|> when the final answer is generated.
| Requirement | Details |
|---|---|
| Python version | 3.12 |
| macOS | Install Xcode Command Line Tools: xcode-select --install |
| Linux | Requires CUDA for reference implementations |
| Windows | Not officially tested; consider using tools like Ollama for local runs |
You can install it directly from PyPI if you want to try of the code.
# if you just need the tools
pip install gpt-oss
# if you want to try the torch implementation
pip install gpt-oss[torch]
# if you want to try the triton implementation
pip install gpt-oss[triton]The model weights are available on Hugging Face Hub. You can download it by Hugging Face CLI:
# gpt-oss-120b
huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
# gpt-oss-20b
huggingface-cli download openai/gpt-oss-20b --include "original/*" --local-dir gpt-oss-20b/OpenAI has released GPT-5, its most advanced language model to date. It is built as a unified system that can switch between fast responses and deeper reasoning depending on the complexity of the user's prompt. GPT-5 offers improved accuracy, better reasoning, and more useful responses across a wide range of topics including coding, health, and creative writing.
ChatGPT Agent has been introduced by OpenAI. It is a tool that can think and take action by proactively selecting from a set of agentic tools to carry out tasks on your behalf using its own virtual computer. This feature is available to ChatGPT Pro, Plus and Team users.
