anthropic/claude-4.5-haiku
Generate text for chat, Q&A, coding, and document workflows with fast, low-latency responses. Accept text prompts and op...
Found 67 models (showing 41-60)
Generate text for chat, Q&A, coding, and document workflows with fast, low-latency responses. Accept text prompts and op...
Generate and reason over text with optional image inputs, returning text outputs. Handle long-context tasks with a 200k-...
Answer questions about images and videos, perform OCR, and describe scenes, returning text. Accepts an image or a video...
Generate and reason over text from prompts or chat messages, with optional image inputs for multimodal understanding; ou...
Answer questions about images and text with multimodal reasoning. Takes a text prompt with an optional image and outputs...
Answer questions about an image and generate captions and summaries. Accepts a single image and a natural-language quest...
Generate structured JSON or free-form text from prompts, with optional web search and tool use. Accepts text and images...
Generates detailed textual descriptions of images based on input prompts. Utilizes a vision-language model to analyze an...
Generates descriptive text captions from three input images using arithmetic operations on image features. The model com...
Generate and structure text from prompts or multi-turn chat messages, with optional image inputs for basic visual unders...
Answer questions about images and generate image-grounded text. Takes an image and a text prompt and returns text, enabl...
Extract content and answer questions from images of documents. Takes an image plus a text prompt or question and outputs...
Generate and analyze text and code from prompts and images. Accepts chat messages and optional image inputs and returns...
Answer questions about images in Korean. Take an image and a Korean prompt and generate Korean text for visual question...
Generate text from prompts and optionally analyze images with captioning and visual question answering. Accepts text and...
Analyze images or video and generate text captions, answers, and summaries. Accepts single or multiple images or a video...
Answer questions about images and generate captions from an image and a text prompt, outputting text. Perform visual que...
Answer questions about images from an image and text prompt, returning text. Perform visual question answering (VQA), im...
Answer questions about images from an image and text prompt, returning text responses. Perform visual question answering...
Caption images and videos and answer visual questions. Accepts an optional image or video plus a text prompt and returns...