Vision
Reading images, scans, forms and screenshots alongside text.
De router koppelt een taak aan kandidaatmodellen en past vervolgens je beleid toe: eerst regio, dan prijs, dan het model met het beter gedocumenteerde resultaat.
Only models whose card lists the vision modality are eligible; a text-only model is rejected, not silently used, and pure text extraction goes to the OCR model.
{"model":"llmeu-auto","messages":[{"role":"user","content":"…"}],"llmeu":{"task":"vision"}}Aanbevolen
No first-party endpoint yet
No first-party endpoint serves this task yet. The models listed below are catalogued for reference and run under their own provider’s terms.