unrecognized.ai
API reference

First request in a minute.

The chat endpoint follows the familiar OpenAI chat completions shape.

Base URL
Use this in your SDK or HTTP client.
https://models.dylojestem.com/v1
Authentication
Put your key in an environment variable and send it on every request.
Authorization: Bearer $UNRECOGNIZED_API_KEY
Chat completion
POST a message and choose a model.
curl https://models.dylojestem.com/v1/chat/completions \
  -H "Authorization: Bearer $UNRECOGNIZED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "reasoning_effort": "max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Reasoning effort
Control how much work the model performs before answering.
lowmediumhighxhighmax

DeepSeek V4 Flash supports high and max. If omitted, the default is max.