Edit images using a prompt. This model extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing

Fast endpoint for Flux Kontext, optimized with pruna framework

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Transform your text into bold, urban graffiti-style fonts instantly.

Transform your selfies into professional headshots using AI.

Transform your ideas into unique tattoo designs using AI.

Use kontext to turn any image into an emoji, using a lora by starsfriday

Transform your photo into a Bratz doll style.

Change your hair to any color you want.

Transform your photos into a Rick and Morty animated style

Transform your photos into an ornate Rococo art style

Transform your photos into a Simpsons cartoon style

Transform your photos into a Barbie doll style

Transform your photos into an exaggerated caricature style

Transform your photos into a hand-drawn sketch style

Transform your photos into a retro pixel game style

Transform your photos into a Disney animated style

Transform your photos into an American comic style

Transform your photos into a Japanese manga style

Transform your photos into a cartoon style

Stable Avatar generates audio-driven video avatars up to five minutes long

The fastest Wan 2.2 text-to-image and image-to-video model

A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video

A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p

Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.

Turns your audio/video/images into professional-quality animated videos

Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.

Wan 2.2's video generation has received a comprehensive upgrade. It now includes both Text-to-Video and Image-to-Video functions and supports cinema-grade aesthetic controls. Users will experience more stable and fluid motion generation, a superior ability to follow instructions with greater real-world realism, and significantly faster generation speeds.

Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Generate 5s and 10s 720p videos fast

Pika v2 Turbo creates videos from a text prompt with high quality output.

Pika v2 Turbo creates videos from images with high quality output.

Pika v2.2 creates videos from a text prompt with high quality output.

Pika Scenes v2.2 creates videos from a images with high quality output.

Pika v2.2 creates videos from images with high quality output.

Pika v2.1 creates videos from a text prompt with high quality output.

Pika v2.1 creates videos from images with high quality output.

Pika Effects are AI-powered video effects designed to modify objects, characters, and environments in a fun, engaging, and visually compelling manner.

Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.

Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.

Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.

Generate expressive, natural speech with Resemble AI's Chatterbox.

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.

YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs.

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts

Generate music from a prompt or melody

Hunyuan3D-2.1 is a scalable 3D asset creation system that advances state-of-the-art 3D generation through Physically-Based Rendering (PBR).

State of the art Multiview to 3D Object generation

State of the art Image to 3D Object generation

A powerful 3D asset generation model

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.

Kimi K2 is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified.

A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks. Trained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.

A simple online recording app.

Draw a mask for use in AI inpainting apps.

Stitch two images together.

Tetris is the iconic puzzle game where differently shaped blocks (tetrominoes) fall from the top of the screen. Players must quickly rotate and position these falling blocks to create solid horizontal lines. When a line is complete, it disappears, scoring points and creating space. The challenge intensifies as the blocks fall faster, demanding quick thinking and strategy to prevent the stack from reaching the top.