GPT Oss 20b
by OpenAI
Instruct
Reasoning
Tools
GPT Oss 20B is a 21B parameter open-weight language model released by OpenAI in 2025 under the Apache 2.0 license. Using a Mixture-of-Experts architecture with 3.6B active parameters per inference, it delivers efficient reasoning, function calling, and long-context understanding while being deployable on consumer hardware with as little as 16GB RAM. This makes it ideal for edge, local, or specialized use cases requiring speed and cost efficiency.
Provider | Context Size | Throughput | Latency | Input Cost | Output Cost |
|---|---|---|---|---|---|
Usage
Generate your API key and query the model through the OpenAI-compatible interface. The preference parameter allows you to define the routing strategy. For more details, see the documentation.
>Enter ↵