- Source
- Registry entry — not yet fetched from Hugging Face or OpenRouter
- Verified
- Evidence not verified
- Confidence
- Unknown
01What this is
- Author
- openai
- Family
- GPT
- Task
- text-generation
- Hugging Face
- not listed
- OpenRouter
- openai/gpt-5
- Also known as
- GPT-5, gpt5
02Registry facts
- LicenceFACT
not yet fetched
- Evidence not verified
- ParametersFACT
not yet fetched
- Evidence not verified
- Context lengthFACT
not yet fetched
- Evidence not verified
- Downloads (30 days)FACT
not yet fetched
- Evidence not verified
- LikesFACT
not yet fetched
- Evidence not verified
- GatedFACT
not yet fetched
- Evidence not verified
None of these has been fetched yet. The registry knows which model this is and where its card lives; our next refresh reads the values from the publisher and attaches the evidence.
Other
- available on platform · azureFACT
azure
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: — parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total | ||
|---|---|---|---|---|
| fp16Needs a fetched parameter count. | not yet fetched | |||
| int8Needs a fetched parameter count. | not yet fetched | |||
| int4Needs a fetched parameter count. | not yet fetched | |||
No parameter count has been fetched for this model, so there is nothing to compute. We will not infer a size from the model’s name.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
No hosted provider has been fetched for this model. OpenRouter’s catalogue is read when our refresh next runs; until then this is empty rather than assumed.
06Deployment stacks
- Vendor apiDocument extraction with local parsing and a model APIDocling parses each document to markdown locally, a closed model API (GPT-5, Claude or Gemini) fills a JSON schema under structured outputs, code validates the result, and rows that fail go to a person. The pipeline and the parsing are yours; only the model is rented.
- Private cloudDocument extraction pipeline in your cloud accountA landing zone in object storage, a managed document-understanding service (Azure AI Document Intelligence, Amazon Textract or Google Document AI), a managed model constrained to a JSON schema, validation in code, and a confidence-thresholded review queue — all in the region you pin, reached over private networking.
- Private cloudAssistant on Microsoft Foundry (Azure OpenAI)A model deployed in Microsoft Foundry (the platform that was Azure AI Foundry / Azure OpenAI), Azure AI Search for retrieval over your content, a web application you build, Microsoft Entra ID for sign-in, and private endpoints so the call never leaves your virtual network.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
Foundry Models sold by Azure - Microsoft Foundry
https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
AgeingRetrieved 19 Sep 2026sha256:ab56886011561 record
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.