Routers
Auto Roleplay
A high-intelligence, long-context model with low input cost for repeatedly sent conversations.
Call itExamples read your key from MINIROUTER_KEY.
curl https://api.minirouter.sh/v1/chat/completions \
-H "Authorization: Bearer $MINIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minirouter/auto:roleplay",
"messages": [
{
"role": "user",
"content": "Explain an API gateway in one sentence."
}
],
"max_tokens": 256
}'How it picksAllowed on your key, within your cost tier, healthy, and able to take the request.
Best first. The first model that passes answers.
- zai/glm-5.3-flash · first available
- openai/gpt-6-luna · available
- deepseek/deepseek-v4-flash-0731 · available
- google/gemini-3.8-flash · available
Live availability: Auto models.
Pricing
- PriceNamed in
x-minirouter-model. You pay for the model that answered.Provider cost plus 8%. - BoundThe dearest model in the list, at this router's rate.At most $0.81 in and $4.05 out per million tokens.