openai/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...
The most important technical and pricing details in one place.
Gateway-compatible routes are tried from the lowest cost; other sources are shown for catalog reference.

Current request, token, and latency data across TamgaStudio.
Call OpenAI GPT-OSS 20B with a single request through the OpenAI-compatible TamgaStudio API. Create your API key from the API Keys section in your dashboard.
curl https://api.tamga.studio/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer tl-sk-XXXXXX" \
-d '{"model": "openai/gpt-oss-20b", "messages": [{"role": "user", "content": "Hello!"}]}'
Common questions about this model.
Explore other models from the same provider or in a similar price range as OpenAI GPT-OSS 20B.