11 models
Inference tasks:Image to text
mistral-document-ai-2512image-to-text
Input typepdf, image
Output typetext
Context window128k
Token limits4.096k output
Generally available (GA)
Fara1.5-27Bweb-agent-tasks
Input typeimage, text
Output typetext
Generally available (GA)
Salesforce-BLIP-image-captioning-baseimage-to-text
Preview
mistral-ocr-4-0image-to-text
Input typepdf, image
Output typetext
Context window128k
Token limits4.096k output
Generally available (GA)
Phi-4-Reasoning-Vision-15Bchat-completion
Input typeimage, text
Output typetext
Generally available (GA)
Fara-7Bimage-to-text
Input typeimage, text
Output typetext
Generally available (GA)
Fara1.5-4Bweb-agent-tasks
Input typeimage, text
Output typetext
Generally available (GA)
Salesforce-BLIP-2-opt-2-7b-image-to-textimage-to-text
Preview
Llama-3.1-Nemotron-Nano-VL-8B-v1-NIM-microserviceimage-classification
Input typetext, image
Output typetext
Preview
Fara1.5-9Bweb-agent-tasks
Input typeimage, text
Output typetext
Preview
ertugrul-qwen2-vl-7b-captioner-relaxedimage-to-text
Generally available (GA)
