gpt-oss-20b

About gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

OpenAI Model Lineup

Compare all models from OpenAI to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Qwen2.5 Coder 7B Instruct

Alibaba Qwen

Input: $0.03

Output: $0.09

Context: 33k

Gemma 2 9B

Google

Input: $0.03

Output: $0.09

Context: 8k

MythoMax 13B

Gryphe

Input: $0.06

Output: $0.06

Context: 8k

DeepHermes 3 Mistral 24B Preview

Nous Research

Input: $0.02

Output: $0.10

Context: 33k

💡 Cheaper Alternatives

Same Brand (OpenAI)

Cross Brand

🚀 Quick Start

Get started with gpt-oss-20b API

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="openai/gpt-oss-20b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision