AI Models

Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.

Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.

Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.

Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.

Mistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.

DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.

DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.

Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.

ElevenLabs' most natural-sounding TTS model. Supports 29 languages with emotional range.

FLUX 1.1 Pro in ultra mode. Up to 4 megapixel images with raw mode for photorealism.

Black Forest Labs' development model. Fast, high-quality image generation with LoRA support.

Google's fastest multimodal model. Supports text, images, audio, and video input.

Google's latest thinking model. Excels at reasoning, coding, math, and science with massive context window.

Google's April 2026 fast multimodal model. Combines Gemini 3 Pro's reasoning with Flash-tier latency and price. Default model in the Gemini app.

Google DeepMind's February 2026 flagship. 2M-token context, native multimodal (text/image/audio/video), Deep Think reasoning.

Google's Imagen 4. Text-to-image with strong photorealism and improved typography support.

Premium Imagen 4 tier. Highest fidelity, prompt adherence and typography quality from Google.

Google's state-of-the-art video generation model. Simulates real-world physics with various visual styles.

Google's Veo 3. High-fidelity text-to-video with native audio generation, up to 8s clips.

Latest Veo with image-to-video and context-aware audio

OpenAI's newest flagship model. Improved reasoning, instruction following, and coding over GPT-4o.

OpenAI's most capable multimodal model. Excellent for complex reasoning, coding, and creative tasks.

OpenAI's unified flagship combining GPT and o-series reasoning into one model. 1M context, multimodal, top SWE-Bench Pro and OSWorld scores.

OpenAI's efficient mid-tier model. 2x faster than its predecessor, 400k context, approaches GPT-5.4 quality on SWE-Bench Pro at a fraction of the cost.

xAI's flagship reasoning model with vision and tool use. 256k context, strong at complex reasoning and STEM tasks.

xAI's May 2026 flagship. 1M context, vision, always-on reasoning, real-time X/web retrieval via DeepSearch.

Ideogram's flagship text-to-image model with industry-leading text rendering and prompt adherence.

Moonshot AI's 1T-parameter MoE model. Industry-leading agentic coding and tool-use benchmarks.

Cinematic video up to 15s with multi-shot and native audio

Most versatile: multi-reference images, video editing, native audio

The latest Midjourney model. Industry-leading aesthetic quality and prompt adherence for image generation.

MiniMax's 456B hybrid lightning-attention model with native 4M-token context. Industry-leading long-context.

Meta's music generation model. Generate up to 1 minute of music from text descriptions.

OpenAI's reasoning model optimized for STEM tasks, coding, and math. Uses chain-of-thought reasoning.

OpenAI's second-generation Sora video model. Realistic motion, improved physics, audio support.

Perplexity's premium web-grounded search model with multi-step reasoning over live sources.

Alibaba's Qwen 3 flagship MoE: 235B total / 22B active. Strong reasoning and tool use, open-weights.

Top-ranked for motion quality and visual fidelity

Meta Segment Anything 2. Promptable segmentation across images and video with temporal memory. Zero-shot, point/box/mask prompts, fast on a single H100.

OpenAI video generation model. Create realistic and imaginative videos from text prompts up to 20 seconds.

OpenAI's most powerful embedding model. 3072 dimensions for maximum accuracy.

Voyage's general-purpose embedding model. 1024 dims, 32k context, strong retrieval performance.

OpenAI's Whisper model. State-of-the-art speech recognition supporting 99+ languages.

OpenAI's distilled Whisper Large v3. ~216x realtime, 99+ languages, MIT-licensed weights.

AI21's flagship hybrid Mamba-Transformer model with a 256k context window for long-document tasks.

Cost-efficient hybrid Mamba-Transformer model with 256k context. Tuned for high-throughput RAG.

Plug-and-play motion module that animates personalized Stable Diffusion models without further training. 16-frame clips at 512x512.

Community fork of AnimateDiff with improved motion modules, beta scheduler control and ControlNet integration for richer animation control.

ByteDance distillation of AnimateDiff. 4-step sampling for over 10x faster inference at comparable quality to multi-step base model.

Meta's AudioCraft framework wrapping MusicGen, AudioGen and EnCodec. Unified text-to-audio research toolkit for music and sound effects.

Latent-diffusion model for general-purpose text-to-audio. Generates speech, music, and sound effects with a unified prior.

fal.ai's fully open-source 6.8B flow-based text-to-image model. Up to 1536x1536 resolution.

Suno's text-to-audio model. Generates realistic speech, music, and sound effects.

BRIA's first commercial-safe background-removal model. Trained on fully-licensed data, suitable for production e-commerce and design pipelines.

BRIA's professional background-removal model trained on fully-licensed data. Commercial-safe.

Cartesia's ultra-low-latency TTS (~90ms TTFB). State-space model with voice cloning support.

Content-Consistent Super-Resolution model. Reduces hallucination compared to typical diffusion-based upscalers while keeping perceptual quality high.

Champ controllable human image animation. Uses 3D parametric guidance (SMPL) for realistic full-body motion transfer from a single reference image.

High-resolution image upscaler with creative detail re-imagination via SD-based hallucination. Strong for photography and product shots.

Anthropic's fast and affordable model. Great for quick tasks, summarization, and simple coding.

Anthropic's fastest and cheapest 4.x model. Strong vision and tool use at ultra-low latency, ideal for high-concurrency workloads.

Robust face-restoration model using a transformer-based codebook prior. Handles severe degradation, occlusion, and old-photo restoration with adjustable fidelity-quality tradeoff.

Zhipu/Tsinghua's 5B open text-to-video model. 720x480 @ 8fps, 6s clips, image-to-video variant available.

Tsinghua CogVLM2 19B with Llama-3 8B base plus 11B vision expert. Strong document understanding and visual reasoning, 8k context.

Open-weights multilingual research model from Cohere covering 23 languages. 35B parameters.

Cohere's fast lightweight chat model (deprecated Sep 2025). Kept as comparison tombstone.

Cohere's mid-tier RAG/tool model. Cost-efficient sibling of Command R+ with 128k context.

Cohere's flagship RAG- and tool-optimized chat model. 128k context, refreshed August 2024.

Cohere's multilingual embedding model. Supports 100+ languages with separate search and classification modes.

ControlNet conditioned on Canny edge maps. Preserves composition and outlines while restyling with Stable Diffusion 1.5 or SDXL backbones.

ControlNet conditioned on depth maps. Preserves the 3D scene layout while letting the prompt change style, lighting and content.

OpenAI's latest image generation model. Excellent at following complex prompts with high fidelity.

Deepgram's flagship STT. First to offer realtime multilingual transcription with self-serve customization.

DeepSeek's specialized coding model. Excellent at code generation, debugging, and explanation.

DeepSeek's reasoning model with chain-of-thought capabilities. Excellent for complex problem-solving.

Powerful open-weight model from DeepSeek. Strong at coding, math, and Chinese/English tasks.

Efficiency-optimized variant of DeepSeek V4. 284B MoE / 13B active, 1M context, ultra-low pricing for high-throughput workloads.

DeepSeek-VL 7B chat model. Vision-language model with hybrid vision encoder and strong real-world visual question answering performance.

Meta Detectron2 object-detection and segmentation toolkit. Mask R-CNN, Cascade R-CNN, panoptic FPN and many other model variants in one wrapper.

Meta DINOv2 self-supervised vision backbone. Pretrained features for classification, segmentation and depth without task-specific fine-tuning.

Naver CLOVA Donut OCR-free document-understanding transformer. End-to-end JSON extraction from forms, receipts and invoices without explicit OCR.

Rednote Hilab Dots OCR. End-to-end document parsing model with layout, text and reading-order prediction in one transformer.

Generative Gaussian-splatting model for fast image-to-3D synthesis. Produces textured meshes in two minutes via differentiable rasterization.

4D Gaussian-splatting generator extending DreamGaussian to video. Image-conditioned dynamic 3D scenes with view-consistent motion.

DWPose whole-body 2D pose estimator. Two-stage knowledge-distilled model with strong accuracy on face, hands and body keypoints simultaneously.

Tencent DynamiCrafter. Animates still images into short videos preserving texture and structure, with strong open-domain coverage.

JaidedAI EasyOCR. Simple Python OCR wrapper supporting 80+ languages with deep-learning text detection and recognition.

Ant Group EchoMimic. Lifelike audio-driven portrait animation with editable landmark conditioning for fine-grained motion control.

Microsoft Edge neural voices accessed via the open-source edge-tts wrapper. 400+ voices across 100+ locales, suitable for batch generation.

ElevenLabs' STT. 99 languages, word-level timestamps, speaker diarization, audio-event tagging.

ElevenLabs' v3 alpha TTS. Most expressive voice model with audio tags and laughter, higher latency.

Enhanced Super-Resolution GAN, the original 2018 architecture. Produces sharp 4x upscales with strong perceptual quality on natural images.

Open-source flow-matching TTS with strong zero-shot voice cloning. Code MIT, weights CC-BY-NC.

Google FILM frame interpolation. Synthesizes high-quality intermediate frames between near-duplicate inputs, designed for large motion gaps.

Microsoft Florence-2 Large. Unified prompt-based vision foundation model for captioning, detection, segmentation and OCR with a single 770M-param backbone.

Microsoft Florence-2 unified vision model with referring expression segmentation. Text-prompted region and mask generation in one model.

The fastest Flux model. Generate images in under 2 seconds. Great for prototyping.

Black Forest Labs' fastest open-weights image model. Apache-2.0 licensed, ~1-4 step inference.

FLUX structural control via Canny edge maps. Preserve composition while restyling.

FLUX structural control via depth maps. Keep 3D scene layout while changing style/content.

Black Forest Labs' inpainting/outpainting model for FLUX. Fill masked regions with prompt-guided content.

FLUX image-variation adapter. Generate variations and remixes from a reference image.

Google DeepMind's vision-language-action model based on Gemini 2.0. Generalist robot policy with strong dexterity.

Embodied-reasoning variant of Gemini Robotics. Enhanced 3D spatial reasoning and trajectory planning.

NVIDIA GET3D generative model for textured 3D shapes. Trained on category-specific datasets producing meshes with high-quality textures.

Tencent ARC face-restoration GAN. Reconstructs realistic facial detail in low-quality or compressed photos using a pretrained StyleGAN2 prior.

Global-Local Path Networks depth-estimation model. Combines hierarchical transformer encoder with selective feature fusion for sharp boundaries.

Google's VLA from RT-X collaboration. Trained on Open-X-Embodiment (22 robots, 527 skills), positive transfer.

Faster cheaper Veo 3 with audio

Faster Veo 3.1 with image-to-video and audio

StepFun GOT-OCR 2.0. Unified end-to-end OCR-2.0 model handling text, formulas, charts, sheet music and geometric shapes in one architecture.

Small, fast, and affordable model for lightweight tasks. Great balance of speed and capability.

OpenAI's smallest and cheapest GPT-5.4 variant. Built for high-volume classification, extraction and coding subagents at edge-grade latency.

IBM Granite 20B Code Instruct. Larger Granite code model balancing quality and inference cost for enterprise CI/CD code-review automation.

IBM Granite 34B Code Instruct. Largest Granite code-instruction model. Top-tier among Apache-2.0 code LLMs on HumanEval, MBPP and MultiPL-E.

IBM Granite 3B Code Instruct. Apache-2.0 small code-instruction model. Strong on Python, Java, JavaScript and Go for enterprise IDE integrations.

IBM Granite 8B Code Instruct. Trained on permissively-licensed code, strong on multi-language code completion and instruction-following.

xAI's vision-capable Grok 2 snapshot. Image-in, text-out with strong multilingual instruction following.

xAI's flagship model. Strong at reasoning, coding, and real-time knowledge with web search capabilities.

xAI's cost-efficient high-throughput model. 2M context, optional reasoning, optimized for agentic loops and real-time apps.

xAI video with native audio and lip-sync, up to 15s

Grounding DINO plus SAM. Open-vocabulary text-prompted detection and segmentation in one pipeline for fully-automatic mask generation.

MiniMax's Hailuo video-01. 6s 1280x720 clips with strong cinematic motion and physical realism.

Minimax model for realistic human motion and VFX

Microsoft HRNet high-resolution pose-estimation backbone. Parallel multi-resolution streams yield strong accuracy on COCO keypoint benchmarks.

Tencent's Hunyuan3D 2.0 image-to-3D pipeline. Two-stage shape and texture generation producing high-resolution textured meshes.

Refreshed Hunyuan3D 2.1 with improved texture fidelity and PBR-material support. Image-to-3D with textured GLB output.

Tencent's 13B open-weights video diffusion transformer. SOTA among open video models at release.

Tencent's open-source video generation model. Strong visual quality with diverse style support.

Hugging Face Idefics3 8B. Llama-3 based open-source vision-language model with strong document QA and chart-understanding performance.

Ideogram's fast text-to-image variant. Strong typography and logo rendering at low latency.

Image-to-3D mesh generator from sparse-view diffusion. Produces textured meshes in under one minute on a single A100.

Berkeley InstructPix2Pix. Edits an image from natural-language instructions in a single forward pass. Trained on GPT-3 plus Stable Diffusion synthetic pairs.

OpenGVLab InternVL 2.5 78B. Open-source vision-language model approaching GPT-4o on MMMU, OCRBench and Math-Vista benchmarks.

Tencent's face-identity conditioning adapter for SD/SDXL. Face embedding + CLIP for ID-consistent generation.

DeepSeek's unified multimodal model. Decouples vision encoding for both understanding and generation tasks.

Jina's frontier multilingual embedding model. 570M params, 8192 ctx, 89 languages, Matryoshka dims 128-1024.

Kuaishou's Kling 1.6 Pro. Premium cinematic motion and physics realism, ~$0.07/sec.

Open-weights 82M-parameter TTS. Punches above its size class on naturalness benchmarks at a fraction of the inference cost of larger models.

Kuaishou's bilingual (CN/EN) latent diffusion text-to-image model with strong text rendering.

Microsoft LayoutLMv3 multimodal document model. Unified text/image masking pretraining for form understanding, receipts and document QA.

HuggingFace's 450M VLA pretrained on 487 community LeRobot datasets. Runs on consumer GPUs.

Kuaishou LivePortrait. Efficient portrait animation driven by reference videos with stitching, retargeting and motion-control parameters.

Meta's flagship vision-language model. 90B parameters, image understanding + chat, strong VQA performance.

Meta Llama 3.2 90B Vision. Largest open-weights Llama vision model. Strong visual reasoning, chart, OCR and document understanding.

Meta's open-source 70B parameter model. Strong all-around performance with multilingual support.

LMMs-Lab LLaVA-OneVision 72B. Unified single-image, multi-image and video instruction-tuned VLM with task-transfer across modalities.

Lotus generative depth model. Treats depth as a generation task using a diffusion model, producing higher-fidelity depth on textured surfaces.

Lightricks' 2B DiT video model. Realtime generation on consumer GPUs (~6s @ H100, 24fps).

Luma's Dream Machine 1.6. 720p text/image-to-video with strong motion and camera control.

Fast affordable video with I2V support

Meta M2M-100 12B many-to-many translation model. Direct translation between 100 languages without pivoting through English.

Google MADLAD-400 3B multilingual translation model. 419 languages supported, trained on a 5T-token multilingual corpus with strong low-resource performance.

ByteDance MagicAnimate. Temporally consistent human-image animation driven by a DensePose motion sequence with strong identity preservation.

UIUC Magicoder S CL 7B. CodeLlama-7B fine-tuned with OSS-Instruct synthetic data. Strong HumanEval Plus and MBPP Plus performance per parameter.

Meta MAGNeT non-autoregressive music generator. Up to 7x faster than MusicGen with comparable quality via masked generative transformers.

Detail-hallucinating upscaler in the Magnific style. Adds plausible high-frequency texture using a Stable Diffusion refiner conditioned on the low-res input.

ETH Zurich Marigold. Diffusion-based monocular depth-estimation model fine-tuned from Stable Diffusion with strong fine-detail recovery.

Marker PDF-to-Markdown conversion pipeline. Combines layout, OCR and equation models to produce clean Markdown with preserved tables and formulas.

Meta Mask2Former universal image-segmentation transformer. Single architecture for panoptic, instance and semantic segmentation tasks.

Meta mBART-50 many-to-many translation model. 50 supported languages with strong performance on news and conversational text.

Google MediaPipe Pose. Lightweight on-device-friendly 33-keypoint 3D pose estimator with optional segmentation mask output.

Mixture-of-experts Phi-3.5: 42B total / 6.6B active params. 128k context, multilingual.

Intel MiDaS v3.1 relative depth-estimation model. Robust zero-shot single-image depth across diverse domains and resolutions.

OpenBMB MiniCPM-V 2.6. 8B vision-language model with strong single-image, multi-image and video understanding plus OCR capabilities.

MiniMax's video generation model. Fast, high-quality video output with text-to-video capabilities.

Mistral's flagship model. Strong reasoning, multilingual, and coding capabilities.

Mistral OCR API. Document-understanding model with strong table and equation extraction, and structured JSON output.

Mistral's 124B multimodal flagship. 123B decoder + 1B vision encoder, 128k ctx, up to 30 images per request.

OpenMMLab MMPose toolbox. Wraps RTMPose, HRNet, HigherHRNet and many other pose models behind a unified inference API.

Genmo's 10B open-weights text-to-video model. AsymmDiT architecture, 5.4s @ 480p.

Motion-Field-Adapter video generator. Controllable image animation from trajectories, keypoints or audio with a strong identity preservation prior.

Tencent MuseTalk real-time lip-sync model. Audio-driven mouth-region editing in latent space at 30+ fps on a single GPU.

Meta's 3.3B-parameter MusicGen Large. Text-conditioned music generation with single-stage autoregressive transformer, supports melody conditioning.

Meta MusicGen Medium (1.5B params). Strong quality-to-speed tradeoff for text-to-music with optional melody guidance.

Meta MusicGen Small (300M params). Fast text-to-music generation suitable for prototyping and low-latency demos.

Mixedbread's open-source 335M embedding model. Top MTEB benchmark for English retrieval at release.

Meta's No Language Left Behind 3.3B translation model. Direct translation between any pair of 200+ languages including many low-resource African and Asian languages.

Meta's distilled 600M NLLB. Same 200-language coverage as the 3B model with a fraction of the parameters, ideal for edge or high-throughput deployment.

Full-parameter fine-tune of Llama 3.1 405B by Nous Research. Steerable, uncensored, strong tool use.

Llama-3.1-70B fine-tune from Nous Research with strong tool/agent capabilities and uncensored alignment.

NVIDIA's world foundation model for physical AI. Diffusion-based video prediction for robotics simulation.

Berkeley/Stanford 93M transformer diffusion policy. Pretrained on 800k Open-X-Embodiment episodes.

Compact 27M variant of Octo. Faster inference on consumer GPUs, designed for low-latency control.

Allen AI olmOCR. Open-source 7B vision-language model fine-tuned for high-fidelity document parsing including math, code and tables.

OpenAI's text-to-speech model. Six built-in voices with natural intonation.

OpenAI's high-definition TTS model. Better quality for production use cases.

CMU OpenPose multi-person 2D pose estimator. Real-time keypoint detection for body, hand, face and foot using Part Affinity Fields.

Stanford/Berkeley open VLA trained on 970k Open-X-Embodiment episodes. Supports LoRA fine-tuning.

MyShell OpenVoice v1. Cross-lingual voice cloning with flexible style control: emotion, accent, rhythm, pauses, and intonation.

MyShell OpenVoice v2. Multilingual zero-shot voice cloning with accurate tone-color reproduction and style/emotion control.

Baidu PaddleOCR v3 PP-OCR pipeline. Lightweight detector plus recognizer optimized for production use with 80+ language support.

Hugging Face Parler-TTS Mini. Lightweight TTS conditioned on a natural-language style description for fine-grained control over voice characteristics.

Parler-TTS Large v1. 2.2B parameters, natural-language style prompting and improved prosody over the Mini variant.

Perplexity's fastest and cheapest web-grounded chat model. Live-source citations included.

Perplexity's reasoning model with chain-of-thought and integrated web search.

Microsoft Phi-3.5 Vision Instruct. Small (4.2B) multimodal model with strong document, OCR and multi-image reasoning at low cost.

Phind CodeLlama 34B v2. Highly tuned CodeLlama variant focused on retrieval-augmented developer assistant workflows.

Tencent ARC PhotoMaker. Identity-preserving stylized photo generation from a stacked-ID embedding. Realistic re-styling of a subject in seconds.

Autoregressive π-0 variant using FAST action tokenizer. Faster inference at competitive task success.

Physical Intelligence's flagship VLA flow-matching policy. Generalist robot control, pretrained on 10k+ hrs robot data.

Upgraded π-0 with open-world generalization via knowledge insulation. Weights and fine-tuning open-sourced.

Pika Labs' 2.0 release. Cinematic text/image-to-video with scene composition controls.

Physics-accurate video generation up to 1080p

Playground's text-to-image model focused on graphic design aesthetics and embedded typography.

PlayHT's 2.0 generative voice model. Multi-lingual expressive speech synthesis with sub-second latency and high-fidelity voice cloning.

OpenAI Point-E text-to-point-cloud system. Fast 3D point-cloud generation from text, optionally lifted to a mesh via marching cubes.

Alibaba's powerful open-source model. Excellent at coding, math, and multilingual tasks.

Alibaba's flagship pretrained MoE model. Top-tier reasoning and code performance via DashScope API.

Alibaba's 72B vision-language model with M-RoPE and dynamic resolution. Strong document and video understanding.

Tsinghua's 1B diffusion-transformer bimanual manipulation policy. Predicts next 64 actions per inference.

Real-CUGAN anime-focused upscaler. 2x/3x/4x super-resolution tuned for animation, line-art, and illustrated content.

AI-Upscaler that increases image resolution up to 4x while preserving texture and detail. Trained on synthetic and real data to reduce common ESRGAN artifacts.

Real-ESRGAN variant fine-tuned for anime, manga, and illustrated artwork. 4x upscaling with cartoon-aware artifact suppression.