Inference and agents, in the KingdomPay per token · Saudi RiyalDCP-Agent for Saudi business · agents.dcp.saAgents can rent a GPU · npx -y github:dhnpmp-tech/dcp-mcpEarn Riyal from your GPUPDPL · Saudi data residencyInference and agents, in the KingdomPay per token · Saudi RiyalDCP-Agent for Saudi business · agents.dcp.saAgents can rent a GPU · npx -y github:dhnpmp-tech/dcp-mcpEarn Riyal from your GPUPDPL · Saudi data residency
DCP∞
Sign inStart free →
DCP∞
Explore
01Overviewنظرة عامةSovereign Arabic AI runtime→02InferenceالاستدلالOpenAI-compatible · live catalog→03Fine-Tuningالضبط الدقيقLoRA contracts · proof-gated serving→04BatchالدُفعاتJSONL validation · execution gated→05DeploymentsالنشرEndpoint proof · traffic gated→06BenchmarksالقياساتMeasured rows · quality claims gated→07PricingالأسعارPer-million-token · SAR→08GPU Podsحاويات GPURent a whole GPU on demand→09AgentsالوكلاءZero-human onboarding · MCP→10DocsالتوثيقOpenAI-compatible API→11EarnاكسبEarn Riyal from your GPU→12SupportالدعمTalk to the team→
In-Kingdom · PDPL© 2026 · Riyadh

ALLaM for Saudi Arabic workloads, shown only as far as the live fleet proves

This page packages the ALLaM path honestly: read /v1/models for availability, pricing, context, and feature readiness; use the page as a developer landing surface, not as a promise that ALLaM is currently served when provider_count is zero.

Matching rowsloadingfrom GET /v1/models
Live matching modelsloadingrequires provider_count > 0
Catalog-only rowsloadingnot advertised as serveable
Quality claimsgatedloading
Riyadh skyline used as the visual signal for DCP Saudi model deployment readinessfig. 04 - model family proof path

Use the family when it is served. Do not infer unavailable rails.

ALLaM is the local Arabic anchor, but DCP should only send traffic when the model has verified providers. Dedicated deployment and LoRA serving stay gated by strict load proof.

Prompt cachenot reportedgated
Batch APInot reportedgated
LoRA adaptersnot reportedgated
Dedicated deploymentsnot reportedgated
from openai import OpenAI

client = OpenAI(
    api_key="$DCP_RENTER_KEY",
    base_url="https://api.dcp.sa/v1",
)

response = client.chat.completions.create(
    model="MODEL_ID_FROM_V1_MODELS",
    messages=[{"role": "user", "content": "Answer in Arabic: summarize this Saudi customer support ticket."}],
)

print(response.choices[0].message.content)
Claim guard

Arabic quality pages should be useful before they are boastful.

These model pages package the catalog and developer path, but public quality claims, rankings, case studies, and frontier comparisons remain blocked until reproducible benchmark artifacts exist.

Inspect benchmarksBack to inference
01benchmark_suite

saudi-arabic-v1

02arabic_quality_claim_allowed

false

03next_action

Attach reproducible eval artifacts before public quality claims.