GLM-OCR

Zhipu AI
Model overview

glm-ocr

Z.AI's current open model for document and image OCR.

vision-languagemultimodaldocument understandinglocal inferenceenterprise access
Representative version

glm-ocr

CompanyZhipu AI
Release2026-02-03
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiesimage / file
Output modalitiestext / structured_output
Tool use / function callingNot disclosed
Structured output / reasoningConfirmed: Structured output
Vision / audio / videoConfirmed: Vision
Open weights / LicenseWeights available / MIT (license source pending verification)
zhipu-glm-ocr-current · License source pending verification
Vendor APIAvailable
Z.AI current model catalog and pricingzhipu-glm-ocr-current · 2026-02-03
OpenRouterNot separately listed on OpenRouter
PricingOfficial pricing page
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesOCR / Document extraction / Local document handling / document understanding
Claim evidenceRelease / model specs / weightsZ.AI current model catalog and pricingglm-ocr · 2026-02-03
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versionglm-ocr
zhipu-glm-ocr-current
PricingOfficial pricing page
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

Parameter scale not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed