Model Catalog
Saudi-hosted and global models behind one OpenAI-compatible gateway. Explore what's available before you sign up.
116,291
Requests served
14
Models
| Model | Type | Context | Tools | Avg latency | Requests |
|---|---|---|---|---|---|
deep-sa/alEmbedding
Saudi-hosted
|
embedding | — | — | ~719ms | 79,301 +105% |
gpt-oss-120b
Saudi-hosted
|
llm | — | ~1091ms | 18,639 +858% | |
llama-3.3-70b
Saudi-hosted
|
llm | — | ~398ms | 14,106 | |
qwen/qwen3.6-27b
Saudi-hosted
|
llm | — | ~4161ms | 962 | |
gpt-oss-20b
Saudi-hosted
|
llm | — | ~603ms | 910 | |
minimaxai/minimax-m2.7
Saudi-hosted
|
llm | — | ~2216ms | 609 | |
qwen3-32b
Saudi-hosted
|
llm | — | ~1721ms | 600 | |
google/gemini-2.5-flash
|
llm | — | ~6457ms | 400 | |
qwen3.8-27b
|
llm | — | ~48800ms | 229 −100% | |
google/gemini-3-flash
|
llm | — | ~3021ms | 201 | |
llama-4-maverick-17b
Saudi-hosted
|
llm | — | ~214ms | 165 | |
google/gemini-3-pro
|
llm | — | ~8498ms | 147 | |
openai/gpt-5-mini
|
llm | — | ~5616ms | 22 | |
google/gemini-2.5-flash-lite
|
llm | — | — | 0 |
1 SAR = 10 requests · Any model, any size input/output
View full pricing details →More than LLMs
Document services available through the same gateway and API keys.
AlOCR Document Intelligence
Extract text from scanned documents, images, and PDFs with state-of-the-art Arabic and English OCR. Powered by Deep.sa's advanced document processing technology.
- Arabic & English text
- Layout preservation
- Table extraction
0.15 SAR / page · 100 free pages to get started
View docsalRetrieval
Ingest documents (PDF, DOCX, PPTX, TXT, MD) and query them with semantic retrieval. PDFs are processed through alOCR; other formats are extracted directly.
- PDF + Text ingestion
- Semantic search
- Auto OCR for PDFs
1 SAR = 10 requests
View docsReady to build?
Create an account, generate an API key, and make your first request in minutes.
A product of Deep.sa