Developer API

Serverless Endpoints. Zero Migration.

Fully compatible with the OpenAI SDK. Access our fine-tuned models instantly with ultra-low latency. We log your metering data, never your payloads.

Generate API Key Read Documentation

terminal

View full docs →

curl https://api.dcp.sa/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer dcp_your_api_key_here" \
  -d '{
    "model": "dcp/pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What's the meaning of life?"}
    ]
  }'

Blazing Fast TTFT

Absolute Zero Logging

We only keep metering data for billing. We do not log, store, or train on your API payloads. Your requests vanish the moment inference completes.

Sovereign Infrastructure

All API requests are routed and processed entirely on bare-metal servers physically located within Saudi Arabia.

Transparent Economics

Pay strictly for what you compute.

Our pricing is anchored to a Base Rate per 1 Million tokens, adjusted dynamically via multipliers based on your model and workload.

Base Price (Input)

7.50⃁/ 1M tokens

Resource	Multiplier	Final Rate
Fast Model Input	0.2x	1.50 ⃁
Pro Model Input	1.0x	7.50 ⃁
Deep-Research Input	1.2x	9.00 ⃁
Output Tokens (All Models)	2.0x	15.00 ⃁
Cache-Hit Input	0.33x	2.48 ⃁