# Picsart API Platform: model catalog > Every model on the Picsart API Platform, grouped by modality and category, newest first. Each link is the model's own Markdown document: parameters, JSON Schema, live rates and ready-to-run SDK, REST and CLI examples. Every model is called the same way with the same API key; the id is what changes. 257 models from 31 providers. A model's page is https://picsart.com/api-platform/models/ and its document https://picsart.com/api-platform/models//llms.txt. How to call one, and the rest of the platform: https://picsart.com/api-platform/llms.txt. ## Image (78) Generate and edit images. ### Text → Image (62) - [MiniMax H3 Image](https://picsart.com/api-platform/models/minimax-h3-image/llms.txt): `minimax-h3-image` by MiniMax. Detailed images up to 4K, or edits that combine up to 16 reference images. - [MiniMax H3 Image Highspeed](https://picsart.com/api-platform/models/minimax-h3-image-highspeed/llms.txt): `minimax-h3-image-highspeed` by MiniMax. Fast image generation up to 4K, or edits combining up to 16 reference images. [fast] - [Seedream 5.5](https://picsart.com/api-platform/models/seedream-5.5/llms.txt): `seedream-5.5` by ByteDance. Realistic images with clear text, stable multi-turn edits and native transparent backgrounds. - [GPT Image 2.6 Flare](https://picsart.com/api-platform/models/gpt-image-2.6-flare/llms.txt): `gpt-image-2.6-flare` by OpenAI. Fast image generation and precise edits, with animated GIF and SVG output. - [GPT Image 2.6 Sunburst](https://picsart.com/api-platform/models/gpt-image-2.6-sunburst/llms.txt): `gpt-image-2.6-sunburst` by OpenAI. Detailed images with strong text and complex layouts, plus animated GIF and SVG output. - [Ideogram Vector](https://picsart.com/api-platform/models/ideogram-vector-1/llms.txt): `ideogram-vector-1` by Ideogram. SVG logos, icons and illustrations from a prompt, with up to 5 reference images. - [Flux 3 Image Klein](https://picsart.com/api-platform/models/flux-3-image-klein/llms.txt): `flux-3-image-klein` by Flux. Fast image generation and editing up to 4K with up to 10 references and a steps control. [fast] - [Nano Banana 2.1](https://picsart.com/api-platform/models/gemini-nano-banana-2.1/llms.txt): `gemini-nano-banana-2.1` by Google. Fast image generation and editing up to 4K with multi-image references. [fast] - [Ideogram 4.5](https://picsart.com/api-platform/models/ideogram-4-5/llms.txt): `ideogram-4-5` by Ideogram. Text-to-image and iterative editing with up to 4 reference images and an optional mask. - [Seedream 5.0 Flash](https://picsart.com/api-platform/models/seedream-5.0-flash/llms.txt): `seedream-5.0-flash` by ByteDance. Fast 2K image generation with up to 10 reference images. - [Flux 3 Image](https://picsart.com/api-platform/models/flux-3-image/llms.txt): `flux-3-image` by Flux. Generate and edit images up to 4K with up to 10 references and precise local edits. - [Recraft V4.1 Flash](https://picsart.com/api-platform/models/recraftv4_1_flash/llms.txt): `recraftv4_1_flash` by Recraft. Fast raster image generation with 10K-character prompts. [fast] - [GPT Image 2.5 Flare](https://picsart.com/api-platform/models/gpt-image-2.5-flare/llms.txt): `gpt-image-2.5-flare` by OpenAI. Fast everyday image generation and editing up to 4K with multi-image input. - [GPT Image 2.5 Sunburst](https://picsart.com/api-platform/models/gpt-image-2.5-sunburst/llms.txt): `gpt-image-2.5-sunburst` by OpenAI. High-quality image generation and editing up to 4K, trading speed for detail. - [Muse Image 1.0](https://picsart.com/api-platform/models/muse-image-1.0/llms.txt): `muse-image-1.0` by Meta. Agentic image generation that plans with reasoning, web and image search before rendering. - [Qwen 3.0 Pro](https://picsart.com/api-platform/models/qwen-image-3.0-pro/llms.txt): `qwen-image-3.0-pro` by Qwen. Text-to-image and image editing at 2K with prompt-rewrite modes and a thinking mode. [premium] - [Grok Imagine 2.0](https://picsart.com/api-platform/models/grok-imagine-image-2.0/llms.txt): `grok-imagine-image-2.0` by Grok. Detailed image generation and editing at up to 2K, with selectable quality levels. - [Recraft V4 Styles](https://picsart.com/api-platform/models/recraftv4_styles/llms.txt): `recraftv4_styles` by Recraft. Style-focused raster output with 10K-character prompts. - [Recraft V4 Styles Pro](https://picsart.com/api-platform/models/recraftv4_styles_pro/llms.txt): `recraftv4_styles_pro` by Recraft. Pro-quality style-focused raster output with enhanced detail and 10K-character prompts. [premium] - [Recraft V4 Styles Pro Vector](https://picsart.com/api-platform/models/recraftv4_styles_pro_vector/llms.txt): `recraftv4_styles_pro_vector` by Recraft. Pro-quality SVG vector output guided by style references, with enhanced detail. [premium] - [Recraft V4 Styles Vector](https://picsart.com/api-platform/models/recraftv4_styles_vector/llms.txt): `recraftv4_styles_vector` by Recraft. Style-focused SVG vector output with 10K-character prompts. - [Seedream 4.7](https://picsart.com/api-platform/models/seedream-4.7/llms.txt): `seedream-4.7` by ByteDance. All-purpose image generation up to 4K with readable in-image text. - [Ideogram P-Image](https://picsart.com/api-platform/models/ideogram-p-image/llms.txt): `ideogram-p-image` by Ideogram. Text-to-image with four speed and quality tiers, at up to 2K. - [Seedream 5.0 Pro](https://picsart.com/api-platform/models/seedream-5.0-pro/llms.txt): `seedream-5.0-pro` by ByteDance. High-detail 2K image generation with up to 10 reference images. - [Nano Banana 2 Lite](https://picsart.com/api-platform/models/gemini-3.1-flash-lite-image/llms.txt): `gemini-3.1-flash-lite-image` by Google. Lightweight image generation with text rendering, tuned for speed and high volume. [fast] - [Ideogram 4.0](https://picsart.com/api-platform/models/ideogram-v4/llms.txt): `ideogram-v4` by Ideogram. Image generation with strong text rendering at up to 3K resolution. - [Luma UNI-1](https://picsart.com/api-platform/models/luma-uni-1/llms.txt): `luma-uni-1` by Luma. Agentic image generation and editing with up to 9 reference images. - [Luma UNI-1 Max](https://picsart.com/api-platform/models/luma-uni-1-max/llms.txt): `luma-uni-1-max` by Luma. Higher-quality image generation and editing with up to 9 reference images. - [Grok Imagine Quality](https://picsart.com/api-platform/models/grok-imagine-image-quality/llms.txt): `grok-imagine-image-quality` by Grok. Higher-fidelity image generation and editing at up to 2K, tuned for detail over speed. - [Picsart SANA-Sprint](https://picsart.com/api-platform/models/picsart-sana-sprint-v1/llms.txt): `picsart-sana-sprint-v1` by Picsart. Fast text-to-image generation powered by SANA-Sprint. [new, fast] - [Recraft V4.1](https://picsart.com/api-platform/models/recraftv4_1/llms.txt): `recraftv4_1` by Recraft. Raster image generation with refined detail, in-image text and 10K-character prompts. - [Recraft V4.1 Pro](https://picsart.com/api-platform/models/recraftv4_1_pro/llms.txt): `recraftv4_1_pro` by Recraft. Higher-detail raster image generation with in-image text and 10K-character prompts. [premium] - [Recraft V4.1 Pro Vector](https://picsart.com/api-platform/models/recraftv4_1_pro_vector/llms.txt): `recraftv4_1_pro_vector` by Recraft. Higher-detail SVG vector image generation with in-image text. [premium] - [Recraft V4.1 Utility](https://picsart.com/api-platform/models/recraftv4_1_utility/llms.txt): `recraftv4_1_utility` by Recraft. Image generation tuned for icons, logos and functional design assets. - [Recraft V4.1 Utility Pro](https://picsart.com/api-platform/models/recraftv4_1_utility_pro/llms.txt): `recraftv4_1_utility_pro` by Recraft. Higher-quality image generation for icons, logos and design assets. [premium] - [Recraft V4.1 Utility Pro Vector](https://picsart.com/api-platform/models/recraftv4_1_utility_pro_vector/llms.txt): `recraftv4_1_utility_pro_vector` by Recraft. Higher-quality SVG vector generation for icons, logos and design assets. [premium] - [Recraft V4.1 Utility Vector](https://picsart.com/api-platform/models/recraftv4_1_utility_vector/llms.txt): `recraftv4_1_utility_vector` by Recraft. SVG vector generation tuned for icons, logos and design assets. - [Recraft V4.1 Vector](https://picsart.com/api-platform/models/recraftv4_1_vector/llms.txt): `recraftv4_1_vector` by Recraft. SVG vector image generation with clean lines and in-image text. - [Flux 2 Klein 4B](https://picsart.com/api-platform/models/picsart-flux-2-klein/llms.txt): `picsart-flux-2-klein` by Picsart. Fast image generation with up to 3 optional reference images. [fast] - [GPT Image 2](https://picsart.com/api-platform/models/gpt-image-2/llms.txt): `gpt-image-2` by OpenAI. Image generation with arbitrary output dimensions and multi-image input. - [Qwen 2 Pro](https://picsart.com/api-platform/models/qwen-image-2-pro/llms.txt): `qwen-image-2-pro` by Qwen. High-quality 2K image generation and editing with negative prompts. [premium] - [Recraft Explore](https://picsart.com/api-platform/models/recraft-explore/llms.txt): `recraft-explore` by Recraft. Explore creative image ideas from a text prompt. - [Kling 3.0 Image](https://picsart.com/api-platform/models/kling-3.0-image/llms.txt): `kling-3.0-image` by Kling. Cinematic images up to 4K with up to 10 reference images. - [Kling O1 Image](https://picsart.com/api-platform/models/kling-o1-image/llms.txt): `kling-o1-image` by Kling. Image generation up to 2K with multi-reference support. - [Nano Banana 2](https://picsart.com/api-platform/models/gemini-3.1-flash-image/llms.txt): `gemini-3.1-flash-image` by Google. Fast 4K image generation with accurate text and search grounding. [hot, fast] - [Seedream 5.0 Lite](https://picsart.com/api-platform/models/seedream-5.0-lite/llms.txt): `seedream-5.0-lite` by ByteDance. Fast 3K image generation with negative prompts and two-image input. [popular] - [Recraft V4 Pro](https://picsart.com/api-platform/models/recraftv4_pro/llms.txt): `recraftv4_pro` by Recraft. Pro-quality raster and vector output with enhanced detail and 10K-character prompts. [premium] - [Recraft V4 Pro Vector](https://picsart.com/api-platform/models/recraftv4_pro_vector/llms.txt): `recraftv4_pro_vector` by Recraft. Pro-quality SVG vector output with enhanced detail and 10K-character prompts. [premium] - [Recraft V3 Vector](https://picsart.com/api-platform/models/recraftv3_vector/llms.txt): `recraftv3_vector` by Recraft. Dedicated SVG vector output with substyle options and negative prompts. - [Recraft V4](https://picsart.com/api-platform/models/recraftv4/llms.txt): `recraftv4` by Recraft. Raster and vector output with clean text placement and 10K-character prompts. - [Recraft V4 Vector](https://picsart.com/api-platform/models/recraftv4_vector/llms.txt): `recraftv4_vector` by Recraft. Dedicated SVG vector output with clean lines and 10K-character prompts. - [Recraft V3](https://picsart.com/api-platform/models/recraftv3/llms.txt): `recraftv3` by Recraft. SVG vector, illustration, and photo styles with readable in-image text. - [Seedream 4.5](https://picsart.com/api-platform/models/seedream-4.5/llms.txt): `seedream-4.5` by ByteDance. Detailed 4K images with clean in-image text and two-image input. - [Flux 2 Flex](https://picsart.com/api-platform/models/flux-2-flex/llms.txt): `flux-2-flex` by Flux. Adaptable image generation across varied visual styles, up to 4K. - [Flux 2 Max](https://picsart.com/api-platform/models/flux-2-max/llms.txt): `flux-2-max` by Flux. Maximum-detail images up to 4K for intricate compositions and demanding scenes. - [Flux 2 Pro](https://picsart.com/api-platform/models/flux-2-pro/llms.txt): `flux-2-pro` by Flux. Sharp images up to 4K with fine-tuned color accuracy and detail. - [GPT Image 1.5](https://picsart.com/api-platform/models/gpt-image-1.5/llms.txt): `gpt-image-1.5` by OpenAI. Strong text-in-image and infographic rendering with multi-image input. - [Grok Imagine](https://picsart.com/api-platform/models/grok-imagine-image/llms.txt): `grok-imagine-image` by Grok. Rapid image creation with wide aspect-ratio selection and image input. [fast] - [Hunyuan V3](https://picsart.com/api-platform/models/hunyuan-v3/llms.txt): `hunyuan-v3` by Hunyuan. Infographic-friendly image generation with readable text and CFG control. - [Ideogram v3](https://picsart.com/api-platform/models/ideogram-v3/llms.txt): `ideogram-v3` by Ideogram. Image generation with precise text placement for logos, posters and graphic design. - [Nano Banana](https://picsart.com/api-platform/models/gemini-2.5-flash-image/llms.txt): `gemini-2.5-flash-image` by Google. Quick, lightweight image creation for high-volume workflows. [popular, fast] - [Nano Banana Pro](https://picsart.com/api-platform/models/gemini-3-pro-image/llms.txt): `gemini-3-pro-image` by Google. 4K images with precise multilingual text rendering and multi-image input. [popular, premium] ### Image → Image (16) - [Ideogram Vectorize](https://picsart.com/api-platform/models/ideogram-vector-1-vectorize/llms.txt): `ideogram-vector-1-vectorize` by Ideogram. Convert a raster image (JPEG, PNG or WebP) into an SVG. - [Ideogram 4.5 Precise Edit](https://picsart.com/api-platform/models/ideogram-4-5-precise-edit/llms.txt): `ideogram-4-5-precise-edit` by Ideogram. Change one area of an image and keep the rest pixel-intact, with an optional mask. - [Picsart Effects](https://picsart.com/api-platform/models/picsart-flow/llms.txt): `picsart-flow` by Picsart. Apply curated effect presets to a photo, each a multi-step pipeline in one tap. [new] - [Picsart Image Edit](https://picsart.com/api-platform/models/picsart-qwen-image-edit/llms.txt): `picsart-qwen-image-edit` by Picsart. General-purpose image editing for swaps, fixes, style changes, and creative edits. - [Picsart Makeup](https://picsart.com/api-platform/models/picsart-qwen-makeup/llms.txt): `picsart-qwen-makeup` by Picsart. Apply virtual makeup to portraits — lipstick, eye looks, blush, and full styled looks. - [Enhance](https://picsart.com/api-platform/models/picsart-enhance/llms.txt): `picsart-enhance` by Picsart. AI image enhancement with upscale and face enhancement. - [Remove Background](https://picsart.com/api-platform/models/picsart-sod-v8-2/llms.txt): `picsart-sod-v8-2` by Picsart. Remove the background from any image with precision, leaving a clean cutout. - [Recraft Explore Similar](https://picsart.com/api-platform/models/recraft-explore-similar/llms.txt): `recraft-explore-similar` by Recraft. Find images visually similar to a previously explored image. - [Recraft Creative Upscale](https://picsart.com/api-platform/models/recraft-creative-upscale/llms.txt): `recraft-creative-upscale` by Recraft. AI-enhanced upscaling that adds creative detail to enlarged images. - [Recraft Crisp Upscale](https://picsart.com/api-platform/models/recraft-crisp-upscale/llms.txt): `recraft-crisp-upscale` by Recraft. Clean upscaling that preserves sharp edges and fine detail. - [Recraft Replace Background](https://picsart.com/api-platform/models/recraftv3-replace-bg/llms.txt): `recraftv3-replace-bg` by Recraft. Replace the background of an image using a text prompt. - [Recraft Vectorize](https://picsart.com/api-platform/models/recraft-vectorize/llms.txt): `recraft-vectorize` by Recraft. Convert raster images to clean SVG vector format. - [Topaz Image Upscale](https://picsart.com/api-platform/models/topaz-upscale-image/llms.txt): `topaz-upscale-image` by Topaz. Image upscaling and enhancement with Standard, Hi-Fi, CGI, Recovery and Wonder models. - [Picsart Change Background](https://picsart.com/api-platform/models/picsart-change-bg/llms.txt): `picsart-change-bg` by Picsart. Swap the background of a photo using a text prompt for the new scene. - [Ideogram Character](https://picsart.com/api-platform/models/ideogram-character/llms.txt): `ideogram-character` by Ideogram. Maintain a consistent character across scenes using a single reference photo. - [Runway Gen4 Ref](https://picsart.com/api-platform/models/runway-gen4-ref/llms.txt): `runway-gen4-ref` by Runway. Generate a still image from up to 3 reference images with consistent identity. ## Video (103) Generate video from text, images, or video. ### Text → Video (48) - [Seedance 2.5 Flash](https://picsart.com/api-platform/models/seedance-2.5-flash/llms.txt): `seedance-2.5-flash` by ByteDance. Fast video generation, editing and extension up to 30s at 720p with audio and reference inputs. [new, fast, premium] - [Gemini Omni 1.2 Flash](https://picsart.com/api-platform/models/gemini-omni-1.2-flash/llms.txt): `gemini-omni-1.2-flash` by Google. Video up to 4K and 15s with frame interpolation, extension, editing and references. - [Kling 4.0 Flash](https://picsart.com/api-platform/models/kling-v4-flash/llms.txt): `kling-v4-flash` by Kling. Fast 720p video up to 20s from text or a start frame. [new] - [Kling 4.0 Flash Omni](https://picsart.com/api-platform/models/kling-v4-flash-omni/llms.txt): `kling-v4-flash-omni` by Kling. Fast 720p video up to 20s from text, a first frame, reference images or a source video. [new] - [MiniMax H3 Highspeed](https://picsart.com/api-platform/models/minimax-h3-highspeed/llms.txt): `minimax-h3-highspeed` by MiniMax. 768p video up to 15s from text, frames or references, balancing quality and speed. - [MiniMax H3 Lite](https://picsart.com/api-platform/models/minimax-h3-lite/llms.txt): `minimax-h3-lite` by MiniMax. Fast, low-cost 480p or 768p video up to 15s from text, frames or references. - [Flux 3 Max](https://picsart.com/api-platform/models/flux-3-max/llms.txt): `flux-3-max` by Flux. Video up to 20s at 1080p with synchronized audio, from text or start and end frames. - [Kling 4.0](https://picsart.com/api-platform/models/kling-v4/llms.txt): `kling-v4` by Kling. Video up to 30s at 720p or 1080p, with start, middle and end keyframes. [new] - [Kling 4.0 Omni](https://picsart.com/api-platform/models/kling-v4-omni/llms.txt): `kling-v4-omni` by Kling. Video up to 30s at 1080p from text, keyframes, reference images, a source video and elements. [new] - [Grok Imagine 1.5 Lite](https://picsart.com/api-platform/models/grok-imagine-video-1.5-lite/llms.txt): `grok-imagine-video-1.5-lite` by Grok. Faster, lower-cost video generation with audio at up to 1080p and 15s. - [HeyGen Video](https://picsart.com/api-platform/models/heygen-video-1/llms.txt): `heygen-video-1` by HeyGen. Video with native audio from text, a first frame or up to 12 references, up to 15s. - [LTX 2.5 Fast](https://picsart.com/api-platform/models/ltx-v2.5-fast/llms.txt): `ltx-v2.5-fast` by LTX. Fast video up to 4K and 20s with synchronized audio and camera motion control. - [LTX 2.5 Pro](https://picsart.com/api-platform/models/ltx-v2.5-pro/llms.txt): `ltx-v2.5-pro` by LTX. Video with synchronized audio and camera motion control, 6-10s at 720p or 1080p. - [Creatify Boreal](https://picsart.com/api-platform/models/creatify-boreal/llms.txt): `creatify-boreal` by Creatify. Text-to-video with synchronized native audio for product, UGC, and presenter clips. - [MiniMax H3 Max Turbo](https://picsart.com/api-platform/models/minimax-h3-max-turbo/llms.txt): `minimax-h3-max-turbo` by MiniMax. Fast video up to 15s at 1080p from text or start and end frames, with prompt expansion. - [MiniMax H3 Max](https://picsart.com/api-platform/models/minimax-h3-max/llms.txt): `minimax-h3-max` by MiniMax. 1080p video up to 15s from text, start and end frames, or image, video and audio references. - [Gemini Omni 1.1 Flash](https://picsart.com/api-platform/models/gemini-omni-1.1-flash-preview/llms.txt): `gemini-omni-1.1-flash-preview` by Google. Video up to 4K with frame interpolation, extension and reference-guided generation. - [Wan 3.0 Prime](https://picsart.com/api-platform/models/wan-3.0-video-prime/llms.txt): `wan-3.0-video-prime` by Wan. The same all-in-one video model as Wan 3.0, up to 7x faster. - [Seedance 2.5](https://picsart.com/api-platform/models/seedance-2.5/llms.txt): `seedance-2.5` by ByteDance. Cinematic video up to 30s and 4K with synchronized audio and multi-reference input. [new, premium, hot] - [Wan 3.0](https://picsart.com/api-platform/models/wan-3.0-video/llms.txt): `wan-3.0-video` by Wan. Video up to 30s at 1080p with audio, from text, frames or image, video and audio references. - [MiniMax H3](https://picsart.com/api-platform/models/minimax-h3/llms.txt): `minimax-h3` by MiniMax. 2K video up to 15s from text, start and end frames, or image, video and audio references. - [Flux 3 Video](https://picsart.com/api-platform/models/flux-3-video/llms.txt): `flux-3-video` by Flux. Video up to 20s at 1080p with synchronized audio, from text, up to 10 images or a clip. - [Seedance 2.0 Mini](https://picsart.com/api-platform/models/seedance-2.0-mini/llms.txt): `seedance-2.0-mini` by ByteDance. Lightweight cinematic video with audio, reference images, and start/end frame control. [new, fast, premium] - [Gemini Omni](https://picsart.com/api-platform/models/gemini-omni-flash-preview/llms.txt): `gemini-omni-flash-preview` by Google. Multimodal video generation from text, an image or a source video, 3-10s. - [Happy Horse 1.1](https://picsart.com/api-platform/models/happyhorse-1.1-t2v/llms.txt): `happyhorse-1.1-t2v` by Happy Horse. Text-to-video up to 15s at 1080p with an optional start frame. - [Kling V3 Turbo](https://picsart.com/api-platform/models/kling-v3-turbo/llms.txt): `kling-v3-turbo` by Kling. Fast video up to 15s at 720p or 1080p from text or a start frame. [new] - [PixVerse C1](https://picsart.com/api-platform/models/pixverse-c1/llms.txt): `pixverse-c1` by PixVerse. Generate video with audio from a text prompt, 5-15s at up to 1080p. - [PixVerse V6](https://picsart.com/api-platform/models/pixverse-v6/llms.txt): `pixverse-v6` by PixVerse. Text-to-video with audio, 5-15s at up to 1080p. - [Luma Ray 3.2](https://picsart.com/api-platform/models/luma-ray-3.2/llms.txt): `luma-ray-3.2` by Luma. High-fidelity video from start and end frames, with HDR and seamless loops. - [Grok Imagine 1.5](https://picsart.com/api-platform/models/grok-imagine-video-1.5/llms.txt): `grok-imagine-video-1.5` by Grok. Video generation with audio at up to 1080p and 15s, from text or an input image. [new] - [Seedance 2.0](https://picsart.com/api-platform/models/seedance-2.0/llms.txt): `seedance-2.0` by ByteDance. Cinematic video up to 4K and 15s with optional audio and reference images. [new, premium, hot] - [Seedance 2.0 Fast](https://picsart.com/api-platform/models/seedance-2.0-fast/llms.txt): `seedance-2.0-fast` by ByteDance. Fast cinematic video with audio, reference images, and start/end frame control. [new, fast, premium, hot] - [Happy Horse 1.0](https://picsart.com/api-platform/models/happyhorse-1.0-t2v/llms.txt): `happyhorse-1.0-t2v` by Happy Horse. Video up to 15s at 1080p from text, with optional first-frame guidance. - [Runway Avatar](https://picsart.com/api-platform/models/runway-avatar-video/llms.txt): `runway-avatar-video` by Runway. Generate speaking avatar videos from preset characters with natural lip-sync. - [Veo 3.1 Lite](https://picsart.com/api-platform/models/veo-3.1-lite/llms.txt): `veo-3.1-lite` by Google. Fast, lightweight video with built-in audio at 720p or 1080p. [fast] - [Wan 2.7](https://picsart.com/api-platform/models/wan-2.7-t2v/llms.txt): `wan-2.7-t2v` by Wan. Video up to 15s at 1080p with audio input and prompt enhancement. [popular] - [LTX 2.3 Fast](https://picsart.com/api-platform/models/ltx-v2.3-fast/llms.txt): `ltx-v2.3-fast` by LTX. Fast video up to 20s with audio and aspect ratio control. - [LTX 2.3 Pro](https://picsart.com/api-platform/models/ltx-v2.3-pro/llms.txt): `ltx-v2.3-pro` by LTX. 4K video with audio and aspect ratio control, in 6, 8 or 10 second clips. - [HeyGen Video Avatar](https://picsart.com/api-platform/models/heygen-video-avatar/llms.txt): `heygen-video-avatar` by HeyGen. Generate a speaking avatar video from a stock avatar and text script. - [Grok Imagine 1.0](https://picsart.com/api-platform/models/grok-imagine-video/llms.txt): `grok-imagine-video` by Grok. Fast video generation with audio at up to 720p and 15s, from text or a start frame. [fast] - [Hailuo 2.3](https://picsart.com/api-platform/models/hailuo-2.3/llms.txt): `hailuo-2.3` by MiniMax. Stylized 768p video with strong character expression and emotion. - [Hailuo 2.3 Pro](https://picsart.com/api-platform/models/hailuo-2.3-pro/llms.txt): `hailuo-2.3-pro` by MiniMax. 1080p video focused on detailed scenes and polished short-form content. - [Kling V3](https://picsart.com/api-platform/models/kling-v3/llms.txt): `kling-v3` by Kling. Long-form video up to 15s with native audio and start/end frame control. [popular, premium] - [Kling V3 Omni](https://picsart.com/api-platform/models/kling-v3-omni/llms.txt): `kling-v3-omni` by Kling. Video up to 15s and 4K from text, frames, reference images or a source video. - [OVI](https://picsart.com/api-platform/models/ovi/llms.txt): `ovi` by OVI. Straightforward text/image-to-video at 720p with broad style coverage. - [Runway Gen 4.5](https://picsart.com/api-platform/models/runway-gen4.5/llms.txt): `runway-gen4.5` by Runway. Photorealistic 1080p video with nuanced camera movement and lighting. [premium] - [Veo 3.1](https://picsart.com/api-platform/models/veo-3.1/llms.txt): `veo-3.1` by Google. 4K video with built-in audio — voices, music, and effects match every scene. [popular, premium] - [Veo 3.1 Fast](https://picsart.com/api-platform/models/veo-3.1-fast/llms.txt): `veo-3.1-fast` by Google. Quick 4K video with synchronized audio for rapid iteration. [popular, fast] ### Video → Video (30) - [MiniMax H3 Max Recast](https://picsart.com/api-platform/models/minimax-h3-max-recast/llms.txt): `minimax-h3-max-recast` by MiniMax. Replace the people in a video from reference photos, keeping motion, camera and sound. - [Mirelo SFX 2.0 (Video to Video)](https://picsart.com/api-platform/models/mirelo-sfx-2.0-video-to-video/llms.txt): `mirelo-sfx-2.0-video-to-video` by Mirelo. Add a synced soundtrack to your video, returned as video with its new audio. - [SAM 3 Video](https://picsart.com/api-platform/models/sam-3-video/llms.txt): `sam-3-video` by Meta. Segment and track objects through a video from a text prompt, masked across every frame. - [MiniMax H3 Max Relight](https://picsart.com/api-platform/models/minimax-h3-max-relight/llms.txt): `minimax-h3-max-relight` by MiniMax. Relight an existing video up to 2K, with a reference image setting the lighting. - [Video Depth Anything](https://picsart.com/api-platform/models/depth-anything-video/llms.txt): `depth-anything-video` by Depth Anything. Estimate consistent depth for every frame and render it as a depth-map video. - [MiniMax H3 Max Extend](https://picsart.com/api-platform/models/minimax-h3-max-extend/llms.txt): `minimax-h3-max-extend` by MiniMax. Extend an existing video with 5-15s of newly generated footage, up to 2K. - [LTX 2.3 Outpaint](https://picsart.com/api-platform/models/ltx-v2.3-outpaint/llms.txt): `ltx-v2.3-outpaint` by LTX. Expand a video past its original frame, generating the surrounding area to match. - [LTX 2.3 Reframe](https://picsart.com/api-platform/models/ltx-v2.3-reframe/llms.txt): `ltx-v2.3-reframe` by LTX. Reframe a video into a new aspect ratio, generating the newly exposed edges to match. - [FLUX Video Edit](https://picsart.com/api-platform/models/flux-video-edit/llms.txt): `flux-video-edit` by Flux. Edit video with a text instruction while preserving motion, timing and audio, up to 15s. [new, fast] - [Flux 3 Video Upscale](https://picsart.com/api-platform/models/flux-video-upscale/llms.txt): `flux-video-upscale` by Flux. Upscale video 1.5x-3x toward 4K in a source-faithful or detail-enhancing mode. - [Seedance 2.5 Video Edit](https://picsart.com/api-platform/models/seedance-2.5-video-edit/llms.txt): `seedance-2.5-video-edit` by ByteDance. Edit video up to 4K: swap subjects, add or remove objects, or restyle from images. [new, premium, hot] - [Seedance 2.5 Video Extend](https://picsart.com/api-platform/models/seedance-2.5-video-extend/llms.txt): `seedance-2.5-video-extend` by ByteDance. Stitch up to 10 clips into one continuous, extended video. [new, premium, hot] - [ByteDance Video Enhance](https://picsart.com/api-platform/models/bytedance-video-enhance/llms.txt): `bytedance-video-enhance` by ByteDance. Denoises, color-corrects and upscales video up to 8K, with frame-rate conversion. - [Topaz Video Upscale](https://picsart.com/api-platform/models/topaz-upscale-video/llms.txt): `topaz-upscale-video` by Topaz. Video upscaling and enhancement with Proteus, Artemis, Nyx, Gaia and Starlight models. - [Seedance 2.0 Mini Video Edit](https://picsart.com/api-platform/models/seedance-2.0-mini-video-edit/llms.txt): `seedance-2.0-mini-video-edit` by ByteDance. Lightweight video edit — modify scenes with reference images. [new, fast, premium] - [Seedance 2.0 Mini Video Extend](https://picsart.com/api-platform/models/seedance-2.0-mini-video-extend/llms.txt): `seedance-2.0-mini-video-extend` by ByteDance. Lightweight: stitch up to 3 clips into one continuous video. [new, fast, premium] - [Luma Ray 3.2 Edit](https://picsart.com/api-platform/models/luma-ray-3.2-edit/llms.txt): `luma-ray-3.2-edit` by Luma. Edit an existing video from a prompt, with presets from faithful to fully reimagined. - [Luma Ray 3.2 Reframe](https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video/llms.txt): `luma-ray-3.2-reframe-video` by Luma. Reframe a video to a new aspect ratio at up to 1080p. - [Runway Aleph 2](https://picsart.com/api-platform/models/runway-aleph2/llms.txt): `runway-aleph2` by Runway. Video restyling with keyframe image guidance for precise motion and style control. - [Seedance 2.0 Fast Video Edit](https://picsart.com/api-platform/models/seedance-2.0-fast-video-edit/llms.txt): `seedance-2.0-fast-video-edit` by ByteDance. Fast video edit — modify scenes with reference images. [new, fast, premium, hot] - [Seedance 2.0 Fast Video Extend](https://picsart.com/api-platform/models/seedance-2.0-fast-video-extend/llms.txt): `seedance-2.0-fast-video-extend` by ByteDance. Quickly stitch up to 3 clips into one continuous video. [new, fast, premium, hot] - [Seedance 2.0 Video Edit](https://picsart.com/api-platform/models/seedance-2.0-video-edit/llms.txt): `seedance-2.0-video-edit` by ByteDance. Edit 4-15s video: swap subjects, add or remove objects, or restyle from images. [new, premium, hot] - [Seedance 2.0 Video Extend](https://picsart.com/api-platform/models/seedance-2.0-video-extend/llms.txt): `seedance-2.0-video-extend` by ByteDance. Stitch up to 3 clips into one continuous, extended video. [new, premium, hot] - [Happy Horse 1.0 Video Edit](https://picsart.com/api-platform/models/happyhorse-1.0-video-edit/llms.txt): `happyhorse-1.0-video-edit` by Happy Horse. Edit video — style transfer or object replacement, with up to 5 references. [new] - [Grok Extend Video](https://picsart.com/api-platform/models/grok-extend-video/llms.txt): `grok-extend-video` by Grok. Extend an existing video forward with a new prompt — up to 10 seconds. - [Wan 2.7 Ref-to-Video](https://picsart.com/api-platform/models/wan-2.7-r2v/llms.txt): `wan-2.7-r2v` by Wan. Generate video from reference images or a reference video, up to 10s at 1080p. [popular] - [Wan 2.7 Video Edit](https://picsart.com/api-platform/models/wan-2.7-video-edit/llms.txt): `wan-2.7-video-edit` by Wan. Restyle or modify an existing video with reference images, up to 1080p. [popular] - [LTX 2.3 Extend](https://picsart.com/api-platform/models/ltx-v2.3-extend/llms.txt): `ltx-v2.3-extend` by LTX. Seamlessly extend an existing video forward or backward — up to 20s. - [LTX 2.3 Retake](https://picsart.com/api-platform/models/ltx-v2.3-retake/llms.txt): `ltx-v2.3-retake` by LTX. Retake video with new direction — replace audio, video, or both. - [Grok Edit Video](https://picsart.com/api-platform/models/grok-edit-video/llms.txt): `grok-edit-video` by Grok. Restyle or remix an existing video with a new prompt direction. ### Image → Video (24) - [Flux 3 Max Keyframes](https://picsart.com/api-platform/models/flux-3-max-keyframes/llms.txt): `flux-3-max-keyframes` by Flux. Video up to 20s at 1080p animated between up to 10 keyframe images, with audio. - [ByteDance OmniHuman 2.0](https://picsart.com/api-platform/models/bytedance-omnihuman-v2.0/llms.txt): `bytedance-omnihuman-v2.0` by ByteDance. Animate one or more subjects with realistic body movement driven by audio. - [MiniMax H3 Max Lip Sync](https://picsart.com/api-platform/models/minimax-h3-max-lip-sync/llms.txt): `minimax-h3-max-lip-sync` by MiniMax. Lip-synced video up to 2K from a portrait and an audio track, 5-14.8s. - [MiniMax H3 Max Camera Controls](https://picsart.com/api-platform/models/minimax-h3-max-camera-controls/llms.txt): `minimax-h3-max-camera-controls` by MiniMax. Video from a start frame with scripted camera motion set by 2-12 keyframes. - [Picsart Effects Video](https://picsart.com/api-platform/models/picsart-flow-video/llms.txt): `picsart-flow-video` by Picsart. Animate a photo with curated video effect presets, each a multi-step pipeline. [new] - [Happy Horse 1.1 Ref-to-Video](https://picsart.com/api-platform/models/happyhorse-1.1-r2v/llms.txt): `happyhorse-1.1-r2v` by Happy Horse. Video up to 15s at 1080p guided by up to 9 reference images. - [PixVerse C1 Fusion](https://picsart.com/api-platform/models/pixverse-c1-fusion/llms.txt): `pixverse-c1-fusion` by PixVerse. Combine up to 7 reference images of subjects and backgrounds into one video scene. - [PixVerse C1 Image](https://picsart.com/api-platform/models/pixverse-c1-image/llms.txt): `pixverse-c1-image` by PixVerse. Turn a source image into video with audio, 5-15s at up to 1080p. - [PixVerse V6 Fusion](https://picsart.com/api-platform/models/pixverse-v6-fusion/llms.txt): `pixverse-v6-fusion` by PixVerse. Fuse up to 7 reference images of subjects and backgrounds into a new video scene. - [PixVerse V6 Image](https://picsart.com/api-platform/models/pixverse-v6-image/llms.txt): `pixverse-v6-image` by PixVerse. Animate a source image into video with audio, 5-15s at up to 1080p. - [Kling Video Effects](https://picsart.com/api-platform/models/kling-video-effects/llms.txt): `kling-video-effects` by Kling. Apply curated video effects to photos, for single or dual-image scenes. [new] - [Happy Horse 1.0 Ref-to-Video](https://picsart.com/api-platform/models/happyhorse-1.0-r2v/llms.txt): `happyhorse-1.0-r2v` by Happy Horse. Generate video up to 15s at 1080p from up to 9 reference images. [new] - [Wan 2.7 Image-to-Video](https://picsart.com/api-platform/models/wan-2.7-i2v/llms.txt): `wan-2.7-i2v` by Wan. Animate images with start and end frames and optional driving audio, up to 15s at 1080p. [popular] - [HeyGen Talking Photo](https://picsart.com/api-platform/models/heygen-talking-photo/llms.txt): `heygen-talking-photo` by HeyGen. Animate any photo into a speaking avatar with natural lip-sync. - [Kling Motion Control V3](https://picsart.com/api-platform/models/kling-motion-control-v3/llms.txt): `kling-motion-control-v3` by Kling. Map body movement from a video clip onto a portrait photo — V3 quality. [popular] - [Kling Avatar](https://picsart.com/api-platform/models/kling-avatar/llms.txt): `kling-avatar` by Kling. Lip-synced talking head from a portrait and speech audio. - [Kling Motion Control 2.6](https://picsart.com/api-platform/models/kling-motion-control/llms.txt): `kling-motion-control` by Kling. Transfer body movement from a reference video onto a portrait photo. [popular] - [ByteDance OmniHuman](https://picsart.com/api-platform/models/bytedance-omnihuman-v1.5/llms.txt): `bytedance-omnihuman-v1.5` by ByteDance. Animate a portrait with realistic body movement driven by audio. - [Creatify Aurora HD](https://picsart.com/api-platform/models/creatify-aurora/llms.txt): `creatify-aurora` by Creatify. Product showcase video from still images with gentle camera motion. - [Hailuo 2.3 Fast](https://picsart.com/api-platform/models/hailuo-2.3-fast/llms.txt): `hailuo-2.3-fast` by MiniMax. Quick 768p video previews from an image, with expressive characters. - [Hailuo 2.3 Fast Pro](https://picsart.com/api-platform/models/hailuo-2.3-fast-pro/llms.txt): `hailuo-2.3-fast-pro` by MiniMax. Fast 1080p video from an image for short, polished clips in varied styles. - [VEED Fabric 1.0](https://picsart.com/api-platform/models/veed-fabric-v1/llms.txt): `veed-fabric-v1` by VEED. Image-driven video with layered ambient atmosphere and optional audio. - [VEED Fabric 1.0 Fast](https://picsart.com/api-platform/models/veed-fabric-v1-fast/llms.txt): `veed-fabric-v1-fast` by VEED. Quick ambient video from images with optional audio overlay. - [Videography](https://picsart.com/api-platform/models/picsart-videography/llms.txt): `picsart-videography` by Videography. Turn a still photo into polished video with automated composition. ### Audio → Video (1) - [LTX 2.3 Audio-to-Video](https://picsart.com/api-platform/models/ltx-2.3-a2v/llms.txt): `ltx-2.3-a2v` by LTX. Generate video driven by an audio track — 2-20s, optional image for first frame. ## Audio (32) Speech, music, and sound effects. ### Text → Speech (16) - [Eleven Dialogue v4](https://picsart.com/api-platform/models/eleven-dialogue-v4/llms.txt): `eleven-dialogue-v4` by ElevenLabs. Multi-speaker conversation on the v4 engine — a voice per line, audio tags per line. [new] - [Eleven v4](https://picsart.com/api-platform/models/eleven-v4/llms.txt): `eleven-v4` by ElevenLabs. Expressive text-to-speech in 90+ languages, with audio tags to direct delivery. [new, popular] - [Eleven v4 Turbo](https://picsart.com/api-platform/models/eleven-v4-turbo/llms.txt): `eleven-v4-turbo` by ElevenLabs. Eleven v4 tuned for speed — the same audio tags and languages, lower latency. [new, fast] - [Gemini 3.8 Flash Lite TTS](https://picsart.com/api-platform/models/gemini-3.8-flash-lite-tts/llms.txt): `gemini-3.8-flash-lite-tts` by Google. Fast text-to-speech with directable delivery for high-volume speech synthesis. [fast] - [Gemini 3.8 Flash TTS](https://picsart.com/api-platform/models/gemini-3.8-flash-tts/llms.txt): `gemini-3.8-flash-tts` by Google. Text-to-speech with directable delivery and inline vocal events such as laughs and sighs. - [Eleven Dialogue v3](https://picsart.com/api-platform/models/eleven-text-to-dialogue/llms.txt): `eleven-text-to-dialogue` by ElevenLabs. Generate a multi-speaker conversation — a voice per line — in one take. - [Seed Audio Multilingual](https://picsart.com/api-platform/models/seed-audio-1.0-multilingual/llms.txt): `seed-audio-1.0-multilingual` by ByteDance. Text-to-speech in 20 languages with named voices or a voice cloned from audio. - [Seed Audio](https://picsart.com/api-platform/models/seed-audio-1.0/llms.txt): `seed-audio-1.0` by ByteDance. English and Chinese text-to-speech with named voices or a voice cloned from audio. - [Async Flash v1.0](https://picsart.com/api-platform/models/async-flash-v1/llms.txt): `async-flash-v1` by Async AI. Fast, natural text-to-speech with selectable voices and audio formats. - [Grok TTS](https://picsart.com/api-platform/models/grok-tts/llms.txt): `grok-tts` by Grok. Expressive text-to-speech in multiple languages with a choice of five voices. - [Eleven Voice Design Multilingual v2](https://picsart.com/api-platform/models/eleven-voice-design-v2/llms.txt): `eleven-voice-design-v2` by ElevenLabs. Design a new voice from a text description with multilingual support. - [Eleven Voice Design v3](https://picsart.com/api-platform/models/eleven-voice-design-v3/llms.txt): `eleven-voice-design-v3` by ElevenLabs. Design a new voice from a text description using v3 engine. - [Eleven Voice Previews](https://picsart.com/api-platform/models/eleven-voice-create/llms.txt): `eleven-voice-create` by ElevenLabs. Generate voice previews from a description to audition before committing. - [Gemini 2.5 Pro TTS](https://picsart.com/api-platform/models/gemini-2.5-pro-tts/llms.txt): `gemini-2.5-pro-tts` by Google. Richly expressive multilingual text-to-speech with 30 voices and multi-speaker dialogue. [premium] - [Gemini 2.5 Flash TTS](https://picsart.com/api-platform/models/gemini-2.5-flash-tts/llms.txt): `gemini-2.5-flash-tts` by Google. Expressive multilingual text-to-speech with 30 voices and multi-speaker dialogue. - [Eleven v3](https://picsart.com/api-platform/models/eleven-v3/llms.txt): `eleven-v3` by ElevenLabs. Expressive text-to-speech with expanded tone and pacing control. [popular] ### Music (6) - [Lyria 3.5](https://picsart.com/api-platform/models/lyria-3.5/llms.txt): `lyria-3.5` by Google. Full-length song generation with vocals from text and image prompts. - [MiniMax Music v3](https://picsart.com/api-platform/models/minimax-music-v3/llms.txt): `minimax-music-v3` by MiniMax. Text-to-music with vocals or instrumentals from a style prompt and optional lyrics. - [ElevenLabs Music v2](https://picsart.com/api-platform/models/elevenlabs-music-v2/llms.txt): `elevenlabs-music-v2` by ElevenLabs. Generate music with vocals or instrumental from a text prompt. - [Lyria 3 Clip](https://picsart.com/api-platform/models/lyria-3-clip/llms.txt): `lyria-3-clip` by Google. Fast music clips with vocals or instrumentals from text and image prompts. - [Lyria 3 Pro](https://picsart.com/api-platform/models/lyria-3-pro/llms.txt): `lyria-3-pro` by Google. Music generation up to 184s with vocals, from text and image prompts. [premium] - [MiniMax Music v2](https://picsart.com/api-platform/models/minimax-music-v2/llms.txt): `minimax-music-v2` by MiniMax. Text-to-music with vocals or instrumentals from a style prompt and lyrics prompt. ### Audio → Speech (4) - [Eleven Audio Isolation](https://picsart.com/api-platform/models/eleven-audio-isolation/llms.txt): `eleven-audio-isolation` by ElevenLabs. Isolate vocals and remove background noise from an audio file. - [Eleven Dubbing](https://picsart.com/api-platform/models/eleven-dubbing/llms.txt): `eleven-dubbing` by ElevenLabs. Dub audio or video across languages with automatic voice matching. - [Eleven Multilingual STS v2](https://picsart.com/api-platform/models/eleven-multilingual-sts-v2/llms.txt): `eleven-multilingual-sts-v2` by ElevenLabs. Voice swap across 29 languages — preserves emotion and cadence. - [Eleven STS v2](https://picsart.com/api-platform/models/eleven-sts-v2/llms.txt): `eleven-sts-v2` by ElevenLabs. Swap your voice to a different speaker while keeping timing and emotion. ### Video → Audio (3) - [Mirelo SFX 2.0 (Video to Audio)](https://picsart.com/api-platform/models/mirelo-sfx-2.0-video-to-audio/llms.txt): `mirelo-sfx-2.0-video-to-audio` by Mirelo. Generate a soundtrack synced to your video, returned as an audio track. - [Eleven Video to Music](https://picsart.com/api-platform/models/eleven-video-to-music/llms.txt): `eleven-video-to-music` by ElevenLabs. Score a video with a soundtrack written to follow what happens on screen. - [Kling V2A](https://picsart.com/api-platform/models/kling-v2a/llms.txt): `kling-v2a` by Kling. Extract or generate a matching audio track from an uploaded video. ### Text → Audio (2) - [Mirelo SFX 2.0 (Text to Audio)](https://picsart.com/api-platform/models/mirelo-sfx-2.0-text-to-audio/llms.txt): `mirelo-sfx-2.0-text-to-audio` by Mirelo. Generate sound effects and soundscapes from a text prompt. - [Kling T2A](https://picsart.com/api-platform/models/kling-t2a/llms.txt): `kling-t2a` by Kling. Text-to-audio clips of 3–10 seconds from a prompt description. ### Sound effects (1) - [ElevenLabs SFX v2](https://picsart.com/api-platform/models/elevenlabs-sfx/llms.txt): `elevenlabs-sfx` by ElevenLabs. Create custom sound effects from a text description — up to 30 seconds. [popular] ## Text (44) LLM text generation and understanding. ### Image → Text (39) - [Claude Fable 5.2](https://picsart.com/api-platform/models/claude-fable-5-2/llms.txt): `claude-fable-5-2` by Anthropic. LLM for frontier reasoning and long-horizon agentic work, with image input. [new] - [Claude Opus 5.5](https://picsart.com/api-platform/models/claude-opus-5-5/llms.txt): `claude-opus-5-5` by Anthropic. LLM for complex, long-form reasoning tasks, with image input. [new] - [GPT-6.1 Sol](https://picsart.com/api-platform/models/gpt-6.1-sol/llms.txt): `gpt-6.1-sol` by OpenAI. LLM for deep reasoning and complex tasks, with image input and a 1M-token context. [new, premium] - [GPT-6.1 Terra](https://picsart.com/api-platform/models/gpt-6.1-terra/llms.txt): `gpt-6.1-terra` by OpenAI. Balanced general-purpose LLM with image input and a 1M-token context. [new] - [Kimi K3.1 Pro](https://picsart.com/api-platform/models/kimi-k3.1-pro/llms.txt): `kimi-k3.1-pro` by Kimi. Deep-reasoning LLM post-trained from K3, with image input and a 1M-token context. [new] - [Kimi K3.1 Pro Highspeed](https://picsart.com/api-platform/models/kimi-k3.1-pro-highspeed/llms.txt): `kimi-k3.1-pro-highspeed` by Kimi. Kimi K3.1 Pro at 2–3× the speed — same capabilities, faster responses. [new] - [MiniMax M3](https://picsart.com/api-platform/models/minimax-m3/llms.txt): `minimax-m3` by MiniMax. Reasoning LLM with adaptive thinking, image input and a 1M-token context. [new] - [MiniMax M3.1 Flash](https://picsart.com/api-platform/models/minimax-m3.1-flash/llms.txt): `minimax-m3.1-flash` by MiniMax. Fast, low-cost LLM with always-on reasoning and a 1M-token context. [new] - [Grok 4.7](https://picsart.com/api-platform/models/grok-4.7/llms.txt): `grok-4.7` by Grok. LLM with always-on reasoning, image input and a 500K-token context. [new] - [Kimi K3](https://picsart.com/api-platform/models/kimi-k3/llms.txt): `kimi-k3` by Kimi. Deep-reasoning LLM with image input and a 1M-token context. [new] - [Claude Haiku 5.5](https://picsart.com/api-platform/models/claude-haiku-5-5/llms.txt): `claude-haiku-5-5` by Anthropic. Fast, lightweight LLM for high-volume text tasks, with image input. [fast] - [GPT-6 Luna](https://picsart.com/api-platform/models/gpt-6-luna/llms.txt): `gpt-6-luna` by OpenAI. Fast, lightweight LLM for low-latency, high-volume text tasks. [fast] - [GPT-6 Sol](https://picsart.com/api-platform/models/gpt-6-sol/llms.txt): `gpt-6-sol` by OpenAI. LLM for deep reasoning and complex tasks, with image input and adjustable thinking. [premium] - [Claude Sonnet 4.5](https://picsart.com/api-platform/models/claude-sonnet-4-5/llms.txt): `claude-sonnet-4-5` by Anthropic. Balanced LLM for coding, analysis and agents, with image input. - [Claude Sonnet 5](https://picsart.com/api-platform/models/claude-sonnet-5/llms.txt): `claude-sonnet-5` by Anthropic. LLM with strong reasoning at everyday latency and cost, with image input. - [Gemini 2.5 Flash](https://picsart.com/api-platform/models/gemini-2.5-flash/llms.txt): `gemini-2.5-flash` by Google. Fast multimodal LLM for high-volume chat, extraction and summarization. [fast] - [GPT-4.1 Mini](https://picsart.com/api-platform/models/gpt-4.1-mini/llms.txt): `gpt-4.1-mini` by OpenAI. Compact LLM for fast text generation with image input. [fast] - [GPT-4.1 Nano](https://picsart.com/api-platform/models/gpt-4.1-nano/llms.txt): `gpt-4.1-nano` by OpenAI. Small, fast LLM for lightweight text tasks, with image input. [fast] - [GPT-4o](https://picsart.com/api-platform/models/gpt-4o/llms.txt): `gpt-4o` by OpenAI. Multimodal LLM with solid quality at low latency and no reasoning pass. - [GPT-4o Mini](https://picsart.com/api-platform/models/gpt-4o-mini/llms.txt): `gpt-4o-mini` by OpenAI. Small, cost-efficient LLM for high-volume text tasks, with image input. [fast] - [GPT-5](https://picsart.com/api-platform/models/gpt-5/llms.txt): `gpt-5` by OpenAI. Reasoning LLM for general-purpose text generation, with image input. - [GPT-5 Mini](https://picsart.com/api-platform/models/gpt-5-mini/llms.txt): `gpt-5-mini` by OpenAI. Lightweight LLM for fast, high-volume text tasks, with image input. [fast] - [GPT-5.1](https://picsart.com/api-platform/models/gpt-5.1/llms.txt): `gpt-5.1` by OpenAI. Reasoning LLM for reliable general-purpose text generation, with image input. - [GPT-5.2](https://picsart.com/api-platform/models/gpt-5.2/llms.txt): `gpt-5.2` by OpenAI. Reasoning LLM for strong general-purpose text generation, with image input. - [Claude Fable 5](https://picsart.com/api-platform/models/claude-fable-5/llms.txt): `claude-fable-5` by Anthropic. LLM for the most demanding reasoning and agentic tasks, with image input. [new] - [Claude Fable 5.1](https://picsart.com/api-platform/models/claude-fable-5-1/llms.txt): `claude-fable-5-1` by Anthropic. Frontier-reasoning LLM above the Opus tier, with image input. [new] - [Claude Opus 5](https://picsart.com/api-platform/models/claude-opus-5/llms.txt): `claude-opus-5` by Anthropic. LLM for complex reasoning and long-form analysis, with image input. [new] - [GPT-5.6 Luna](https://picsart.com/api-platform/models/gpt-5.6-luna/llms.txt): `gpt-5.6-luna` by OpenAI. Fast, lightweight LLM for high-volume text tasks, with image input and thinking. [fast] - [GPT-5.6 Sol](https://picsart.com/api-platform/models/gpt-5.6-sol/llms.txt): `gpt-5.6-sol` by OpenAI. Deep-reasoning LLM for complex, multi-step tasks, with image input. [premium] - [GPT-5.6 Terra](https://picsart.com/api-platform/models/gpt-5.6-terra/llms.txt): `gpt-5.6-terra` by OpenAI. Balanced general-purpose LLM with strong quality at moderate latency. [popular] - [GPT-6 Astra](https://picsart.com/api-platform/models/gpt-6-astra/llms.txt): `gpt-6-astra` by OpenAI. LLM for advanced reasoning and multimodal tasks, with adjustable thinking. [new] - [Gemini 3.8 Flash](https://picsart.com/api-platform/models/gemini-3.8-flash/llms.txt): `gemini-3.8-flash` by Google. Fast multimodal LLM with adjustable thinking for low-latency chat and extraction. [fast] - [Gemini 3.7 Flash](https://picsart.com/api-platform/models/gemini-3.7-flash/llms.txt): `gemini-3.7-flash` by Google. Fast multimodal LLM for low-latency text generation with image input. [fast] - [Gemini 3.5 Flash Lite](https://picsart.com/api-platform/models/gemini-3.5-flash-lite/llms.txt): `gemini-3.5-flash-lite` by Google. Lightweight, low-cost LLM with image input for high-volume, low-latency tasks. [fast] - [Gemini 3.6 Flash](https://picsart.com/api-platform/models/gemini-3.6-flash/llms.txt): `gemini-3.6-flash` by Google. Low-latency multimodal LLM for text generation, with image input and thinking. [fast] - [Claude Haiku 4.5](https://picsart.com/api-platform/models/claude-haiku-4-5/llms.txt): `claude-haiku-4-5` by Anthropic. Lightweight LLM for fast, high-volume chat and text tasks, with image input. [fast] - [Claude Opus 4.8](https://picsart.com/api-platform/models/claude-opus-4-8/llms.txt): `claude-opus-4-8` by Anthropic. Reasoning LLM for complex problems and long-form analysis, with image input. [premium] - [Claude Sonnet 4.6](https://picsart.com/api-platform/models/claude-sonnet-4-6/llms.txt): `claude-sonnet-4-6` by Anthropic. Balanced LLM with strong reasoning at lower latency and cost, with image input. [popular] - [GPT-5.5](https://picsart.com/api-platform/models/gpt-5.5/llms.txt): `gpt-5.5` by OpenAI. Multimodal LLM for general-purpose text generation, with image input and thinking. [popular] ### Video → Text (4) - [Gemini 4 Carbon](https://picsart.com/api-platform/models/gemini-4-carbon/llms.txt): `gemini-4-carbon` by Google. Deep-reasoning LLM for long coding, research and multimodal tasks, with a 1M-token context. [new, premium] - [Gemini 4 Argon](https://picsart.com/api-platform/models/gemini-4-argon/llms.txt): `gemini-4-argon` by Google. Reasoning LLM for text, image and video input with a 1M-token context. [premium] - [MiniMax H3 Context IR](https://picsart.com/api-platform/models/minimax-h3-context-ir/llms.txt): `minimax-h3-context-ir` by MiniMax. Enhances a video prompt using text, frames and image, video or audio references. [new] - [Gemini 3 Pro](https://picsart.com/api-platform/models/gemini-3-pro/llms.txt): `gemini-3-pro` by Google. Reasoning LLM that understands text, images and video. [premium] ### Audio → Text (1) - [Eleven Scribe v2](https://picsart.com/api-platform/models/eleven-speech-to-text/llms.txt): `eleven-speech-to-text` by ElevenLabs. Transcribe speech from audio or video, with word timings and speaker labels.