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...
Reroute speaks the OpenAI Chat Completions format. Point any OpenAI SDK at https://reroute.wtf/api/v1 and use openai/gpt-oss-20b:batch as the model.
curl https://reroute.wtf/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $REROUTE_API_KEY" \
-d '{
"model": "openai/gpt-oss-20b:batch",
"messages": [
{ "role": "user", "content": "What is the meaning of life?" }
]
}'Set stream: true to receive server-sent events. The final chunk carries usage and cost.
curl -N https://reroute.wtf/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $REROUTE_API_KEY" \
-d '{ "model": "openai/gpt-oss-20b:batch", "stream": true,
"messages": [{ "role": "user", "content": "Count to five" }] }'