LDX hubLDX hub
  • Pricing
  • Documentation
  • API Reference
Information
Files
    List uploaded filesgetUpload a filepostGet file infogetDownload file contentget
Uploads
    Create an upload sessionpostAppend a chunk to an uploadput
StructFlow Models
    List available modelsget
StructFlow Jobs
    List StructFlow job historygetCreate a StructFlow jobpostGet StructFlow job status and resultsget
AnalyzeDoc Models
    List available modelsget
AnalyzeDoc Jobs
    List AnalyzeDoc job historygetCreate an AnalyzeDoc jobpostGet AnalyzeDoc job status and resultsget
RefineLoop Models
    List available modelsget
RefineLoop Jobs
    List RefineLoop job historygetCreate a RefineLoop jobpostGet RefineLoop job status and resultsget
RenderOCR Engines
    List available enginesget
RenderOCR Jobs
    List RenderOCR job historygetCreate a RenderOCR jobpostGet RenderOCR job status and resultsget
CastDoc Engines
    List available enginesget
CastDoc Jobs
    List CastDoc job historygetCreate a CastDoc jobpostGet CastDoc job status and resultsget
ExtractDoc Engines
    List available enginesget
ExtractDoc Jobs
    List ExtractDoc job historygetCreate an ExtractDoc jobpostGet ExtractDoc job status and resultsget
MCP
    MCP Serverpost
Schemas
powered by Zuplo
LDX hub API
LDX hub API

AnalyzeDoc Models

List available vision AI models for AnalyzeDoc


List available models

GET
https://gw.ldxhub.io
/analyzedoc/models

Returns a list of all available vision AI models for document analysis. Each model is offered in one or more resolution variants, indicated by an '@' suffix in the model ID (e.g. 'openai/gpt-5.5@high'). Higher resolution reads dense layouts and fine print more accurately at a higher per-page cost. Input format support varies by model — see 'supported_conversions'.

List available models › Responses

A list of available models

​AnalyzeDocModel[]
GET/analyzedoc/models
curl https://gw.ldxhub.io/analyzedoc/models
Example Responses
{ "data": [ { "id": "openai/gpt-5.5@high", "display_name": "OpenAI GPT-5.5 @high", "description": "OpenAI's latest flagship model. High-resolution reading for the most accurate extraction from dense layouts, small fonts, and numeric tables — best when accuracy justifies premium per-page cost.", "provider": "openai", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "openai/gpt-5.5@low", "display_name": "OpenAI GPT-5.5 @low", "description": "OpenAI's latest flagship model. Low-resolution reading for fast, economical extraction from clean, large-text documents.", "provider": "openai", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "openai/gpt-5.4@high", "display_name": "OpenAI GPT-5.4 @high", "description": "OpenAI's previous flagship model. High-resolution reading with strong accuracy on complex documents at a more accessible price than GPT-5.5.", "provider": "openai", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "openai/gpt-5.4-mini@high", "display_name": "OpenAI GPT-5.4 mini @high", "description": "OpenAI's compact, cost-efficient model. High-resolution reading with a solid balance of accuracy and cost for everyday document extraction.", "provider": "openai", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "azure/gpt-5.4@high", "display_name": "Azure OpenAI GPT-5.4 @high", "description": "GPT-5.4 hosted on Microsoft Azure. High-resolution reading for enterprise use requiring data residency and Azure compliance.", "provider": "azure", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "azure/gpt-5.4@low", "display_name": "Azure OpenAI GPT-5.4 @low", "description": "GPT-5.4 hosted on Microsoft Azure. Low-resolution reading for fast, low-cost extraction from clean, large-text documents, with Azure compliance.", "provider": "azure", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "azure/gpt-5.4-mini@high", "display_name": "Azure OpenAI GPT-5.4 mini @high", "description": "GPT-5.4 mini hosted on Microsoft Azure. Affordable high-resolution extraction with Azure compliance for enterprise use.", "provider": "azure", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "azure/gpt-5.4-mini@low", "display_name": "Azure OpenAI GPT-5.4 mini @low", "description": "GPT-5.4 mini hosted on Microsoft Azure. Fast, low-cost extraction from clean, large-text documents, with Azure compliance.", "provider": "azure", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "google/gemini-3.5-flash@high", "display_name": "Google Gemini 3.5 Flash @high", "description": "Google's fast, cost-efficient model. High-resolution reading for accurate extraction from images and dense layouts at low cost.", "provider": "google", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "google/gemini-3.5-flash@medium", "display_name": "Google Gemini 3.5 Flash @medium", "description": "Google's fast, cost-efficient model. Balanced resolution for a good mix of accuracy and cost on everyday documents.", "provider": "google", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "google/gemini-3.5-flash@low", "display_name": "Google Gemini 3.5 Flash @low", "description": "Google's fast, cost-efficient model. Lowest-cost reading for clean, large-text documents at high volume.", "provider": "google", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "anthropic/claude-fable-5", "display_name": "Claude Fable 5", "description": "Anthropic's Mythos-class model, a tier above Opus. Maximum reasoning depth for complex, nuanced document analysis.", "provider": "anthropic", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "anthropic/claude-sonnet-5", "display_name": "Claude Sonnet 5", "description": "Anthropic's latest Sonnet model, a major upgrade over Sonnet 4.6. Strong schema adherence for demanding document extraction at Sonnet-tier cost.", "provider": "anthropic", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "anthropic/claude-opus-4-8", "display_name": "Claude Opus 4.8", "description": "Anthropic's flagship Opus model. Deep reasoning and nuanced schema interpretation for demanding document extraction.", "provider": "anthropic", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] }, { "id": "bedrock/global.amazon.nova-2-lite-v1:0", "display_name": "Amazon Nova 2 Lite (Bedrock)", "description": "Amazon's lightweight model via Bedrock. Cost-effective option for straightforward document extraction at scale.", "provider": "bedrock", "supported_conversions": [ { "from": "pdf", "to": "json" }, { "from": "jpeg", "to": "json" }, { "from": "png", "to": "json" } ] } ] }
json
application/json

StructFlow JobsAnalyzeDoc Jobs