Every model, run privately.

AionLabs' affordable text-only model featuring reasoning, web search, and a 128K context window.

AionLabs' multi-model collaborative text system built on DeepSeek, tuned for immersive roleplay and storytelling with reasoning and tool support.

AionLabs' multi-model collaborative text system for roleplaying and storytelling, built on GLM with tool use and reasoning.

Anthropic's first Mythos-class model for general use — state-of-the-art reasoning, coding, and agentic work with a 1M context window.

Anthropic's frontier coding and reasoning model with vision, tool use, and a 198K context window.

Anthropic's flagship multimodal model with a 1M token context window, state-of-the-art coding and reasoning, and dynamic agentic capabilities.

Anthropic's flagship LLM for agentic coding, long-horizon reasoning, and high-resolution vision with a 1M-token context window.

Anthropic's premier frontier model, optimized for advanced coding, autonomous agentic loops, and deep reasoning with a massive 1M-token context.

Anthropic's mid-tier frontier model — elite coding, agentic tool use, computer control, and reasoning with vision input.

Anthropic's hybrid reasoning mid-tier model with a 1M context window, built for coding, agents, and enterprise workflows.

Anthropic's most agentic Sonnet yet — near-Opus coding and reasoning at mid-tier pricing.

DeepSeek's open-weight reasoning model with sparse attention, native tool-use thinking, and GPT-5-level performance at a fraction of frontier pricing.

DeepSeek's ultra-efficient, open-weights MoE model featuring a 1M context window, hybrid attention, and strong agentic coding capabilities.

DeepSeek's flagship 1.6T parameter Mixture-of-Experts model, delivering frontier-class coding, math, and agentic reasoning with an ultra-efficient 1M context window.

An uncensored, privacy-first Mixture-of-Experts (MoE) model based on Google's Gemma 4, optimized for unbiased reasoning, coding, and search.

An uncensored, highly optimized 35B Mixture-of-Experts model from the Qwen 3.6 family, built for agentic coding and unrestricted reasoning.

A highly steerable, 24B-parameter uncensored model co-developed by Venice and Dolphin, running with end-to-end encryption.

Google’s 1M-context multimodal reasoning model with native tool use, vision, and web search for agentic coding and complex analysis.

Google's fast, agent-first multimodal model, delivering frontier-level reasoning and coding at Flash speeds.

Google's fast, multimodal reasoning model built for agentic coding and high-frequency workflows at a fraction of flagship cost.

Google's 27B open-weight multimodal model with vision, tool use, and 140+ language support — efficient enough for consumer hardware.

Google's highly efficient 26B Mixture-of-Experts (MoE) model with 4B active parameters, offering multimodal reasoning, vision, and tool use under an Apache 2.0 license.

xAI's frontier LLM with a 1M context, built-in reasoning, vision, web search, and tool use — run privately with zero retention.

SpaceXAI's frontier mixture-of-experts model for coding, agentic tool use, and long-context knowledge work.

Nous Research's flagship 405B open-weights model, fine-tuned for advanced agentic reasoning, structured JSON, and unmatched steerability.

A 975B-parameter open-weights MoE multimodal model from Thinking Machines Lab that processes text, images, and audio through a 1M-token context window.

Meta's tiny open-weights workhorse — 3B parameters, 128K context, and tool use for edge and budget inference.

MiniMax's open-weights 428B MoE with native vision, video, and sparse attention for long-context coding and agentic work.

Mistral's open-weight 24B instruction-tuned model with tool use, web search, and structured output — a production-ready upgrade to Small 3.1.

NVIDIA's open hybrid MoE model with Mamba-2 layers, configurable reasoning, and agentic tool use.

NVIDIA's flagship open-weights frontier model — a 550B-parameter hybrid Mamba-MoE architecture built for agentic reasoning, tool use, and long-context throughput.

NVIDIA's open 30B MoE that punches at frontier scale — gold-medal math, coding, and agentic reasoning with only 3B active parameters.

A community-abliterated, open-weights variant of GLM-4.7-Flash built for fast inference, reasoning, and tool use with relaxed refusal behavior.

OpenAI's specialized agentic coding model — long-horizon software engineering, cybersecurity, and tool use with a 256K context window.

OpenAI's flagship reasoning model for professional knowledge work, coding, and agentic tasks with tool use and web search.

OpenAI's most capable agentic coding model — autonomous software engineering with vision, reasoning, and tool use.

OpenAI's highest-performance frontier model — native computer-use, adjustable reasoning, and 1M context for complex professional work.

OpenAI's frontier professional model — 1M context, configurable reasoning, and multimodal agentic capabilities with vision and tool use.

OpenAI's highest-intelligence frontier model with extended test-time compute, multimodal reasoning, and a 1M-token context window for deep research and agentic work.

OpenAI's April 2026 frontier model for agentic coding, research, and multi-step tool use with vision and reasoning.

OpenAI's cost-efficient GPT-5.6 tier with a 1M context, vision, reasoning, and tool use for high-volume workloads.

OpenAI's fastest, most cost-efficient GPT-5.6 model — 1M context, vision, tool use, and web search for high-volume agentic work.

OpenAI's flagship GPT-5.6 model with a 1M context window, native multi-agent reasoning, vision, and tool use for frontier coding and knowledge work.

OpenAI's flagship GPT-5.6 model — multimodal reasoning, agentic coding, and a 1M-token context window for frontier knowledge work.

OpenAI's balanced multimodal workhorse with 1,000K context, reasoning, and tool use for production workflows.

OpenAI's balanced mid-tier frontier model — 1M context, multimodal reasoning, and native tool use for production workloads.

OpenAI's largest open-weight reasoning model — 117B MoE parameters, agentic tool use, and full chain-of-thought under Apache 2.0.

Alibaba's agent-frontier text model with 1M context, tool use, and code-optimized reasoning for long-horizon autonomous workflows.

Alibaba's updated 235B-parameter MoE language model with 22B active params, optimized for reasoning, coding, and long-context instruction following.

Alibaba's flagship open-weight thinking MoE — 235B total, 22B active, reasoning-only mode with tool use and 262K native context.

Alibaba's 9B open-weight multimodal model with hybrid attention, 256K context, and native tool use.

A 27B dense multimodal model from Alibaba's Qwen team, optimized for agentic coding, reasoning, and long-context tasks.

Alibaba's flagship open-weight code model — a 480B-parameter MoE with 35B active, built for agentic coding and 256K-context repo work.

Alibaba's 80B/3B sparse MoE with hybrid attention and 256K context, open-weight under Apache 2.0.

Alibaba's 235B-parameter open-weights vision-language MoE with tool use, web search, and visual agent capabilities.

Venice's flagship 24B uncensored model — built on Mistral architecture with native vision, web search, and zero refusal behavior.

Venice's fine-tuned 24B roleplay model, optimized for highly expressive, low-refusal character interactions with zero retention.

Z.ai's speed-optimized agentic model with selectable reasoning modes, native tool calling, and a 200K context window for OpenClaw workflows.

Zhipu AI's native multimodal coding model for vision-to-code and agentic workflows.

Z.ai's open-weight flagship MoE model for coding, reasoning, and agentic tasks.

Z.ai's lightweight 30B MoE text model built for fast coding, tool use, and agentic tasks.

Z.AI's open-weight coding and reasoning model that runs privately on Venice with tool use and zero retention.

Z.AI's open-weights flagship LLM for agentic engineering and long-horizon coding tasks.

Z.ai's flagship open-weights MoE with 1M context, reasoning, and tool use for long-horizon coding.

Zhipu AI's 744B-parameter open-weight MoE flagship built for agentic engineering, reasoning, and long-horizon coding tasks.

Open-weights text-to-image model at $0.01 per image with zero-retention privacy.

Black Forest Labs' flagship FLUX.2 image model — top-tier photorealism, multi-reference editing, and up to 4MP output.

Black Forest Labs' flagship commercial model — 4MP photorealism, advanced prompt understanding, and precise design control.

OpenAI's flagship text-to-image model with built-in reasoning, near-perfect in-image text, and up to 4K output.

xAI's state-of-the-art Quality Mode model delivering photorealistic textures, clean multilingual text rendering, and advanced multi-image composition.

xAI's unified image generation and editing API for product placement, restyling, and precision edits up to 2K.

Ideogram's premier 9.3B open-weight image model — the gold standard for in-image typography, structured layout control, and 2K design assets.

The ultimate uncensored SDXL checkpoint for photorealistic character rendering and native 1536px support.

Google's fast, knowledgeable image model that blends Pro-grade quality with Flash-tier speed and precise text rendering.

Alibaba's unified image generation and editing model with professional bilingual typography and native 2K output.

Recraft's premium design-centric model — delivering art-directed, print-ready raster images at 2048px resolution with exceptional visual taste.

Recraft’s design-first image model — art-directed raster and editable vector SVG generation with strong typographic accuracy.

ByteDance's production-grade image model for complex layouts, infographics, and native multilingual text rendering.

Venice's custom-configured Stable Diffusion 3.5 engine, delivering high-fidelity photorealism and creative freedom with zero prompt retention.

xAI's premier video model family — text-, image- and reference-to-video generation at 720p with native synchronized audio, sound effects, and music.

Kuaishou's premium unified multimodal video model — cinematic 3–15s clips with native audio from text, images, or references.

Meituan's 13.6B open-source video model — generating coherent, high-quality private clips up to 30 seconds on Venice.

Lightricks' open-source video engine — speed-optimized, native 4K, portrait framing, and synchronized audio.

ByteDance's unified multimodal video model generating cinematic 1080p clips up to 15 seconds with synchronized audio.

Alibaba's flagship 27B open-weight video model — uncensored, featuring native audio synchronization and exceptional character consistency.

A highly efficient open-source music foundation model combining a planning Language Model with a Diffusion Transformer for rapid, high-quality track generation.

Resemble AI's high-definition text-to-speech model, delivering highly expressive, natural voice synthesis with zero-shot cloning.

An ultra-lightweight, open-weight text-to-speech model delivering studio-quality synthesis with incredible speed and efficiency.