gpt-oss-20b
OpenAI logo

gpt-oss-20b

OpenAI
gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.

Pricing

  • Input Tokens: $0.110 /M tokens
  • Output Tokens: $0.550 /M tokens

Input Modalities

  • Text

Output Modalities

  • Text

Capabilities

  • Thinking
  • Tool calling
  • Structured outputs

Providers

Groq gpt-oss-20b
Pricing$0.110$0.550
Context128K
Max output128K
Latency0.1S
Throughput2619.0TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for gpt-oss-20b

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is gpt-oss-20b?

gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.