Venice.ai Models

Kimi K3

kimi-k3·Moonshot

Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.

Inkling

inkling·thinkingmachines

Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 1M context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.

GPT-5.6 Luna

openai-gpt-56-luna·OpenAI

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.

GPT-5.6 Luna Pro

openai-gpt-56-luna-pro·OpenAI

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

GPT-5.6 Terra

openai-gpt-56-terra·OpenAI

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.

GPT-5.6 Terra Pro

openai-gpt-56-terra-pro·OpenAI

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

GPT-5.6 Sol

openai-gpt-56-sol·OpenAI

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.

GPT-5.6 Sol Pro

openai-gpt-56-sol-pro·OpenAI

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Aion 3.0

aion-labs-aion-3-0·Aion Labs

Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.

Aion 3.0 Mini

aion-labs-aion-3-0-mini·Aion Labs

Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.

Grok 4.5

grok-4-5·xAI

Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.

Qwen 3.6 27B FP8🔒Private

e2ee-qwen3-6-27b·Alibaba

Qwen 3.6 27B FP8 running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.

DeepSeek V4 Flash🔒Private

e2ee-deepseek-v4-flash·DeepSeek

DeepSeek V4 Flash running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.

Claude Sonnet 5

claude-sonnet-5·Anthropic

Claude Sonnet 5 is Anthropic's latest Sonnet model, substantially improving on Sonnet 4.6 in coding and agentic work and reaching near-Opus quality on many tasks. It features a 1M token context window, adaptive thinking, and strong document and vision understanding.

⭐ VENICEVS PICKBETA

GLM 5.2

zai-org-glm-5-2·Z.ai

GLM-5.2 is the next-generation large language model developed by Zhiyuan AI, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.

GLM 5.2🔒Private

e2ee-glm-5-2-p·Z.ai

GLM 5.2 running in a Trusted Execution Environment (TEE). Z.AI's flagship model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.

VS PICKBETA

Kimi K2.7 Code

kimi-k2-7-code·Moonshot

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.

MiniMax M3 Preview

minimax-m3-preview·MiniMax

MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.

MiMo-V2.5

xiaomi-mimo-v2-5·XiaomiMiMo

MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.

Claude Fable 5

claude-fable-5·Anthropic

Claude Fable 5 is Anthropic's most capable widely released model, designed for demanding reasoning and long-horizon agentic work. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities.

NVIDIA Nemotron 3 Ultra

nvidia-nemotron-3-ultra-550b-a55b·Nvidia

NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.

Qwen 3.7 Plus

qwen-3-7-plus·Alibaba

Qwen 3.7 Plus is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.

⭐ VENICEVS PICK

Claude Opus 4.8

claude-opus-4-8·Anthropic

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

VS PICKBETA

Claude Opus 4.8 Fast

claude-opus-4-8-fast·Anthropic

Claude Opus 4.8 (Fast) is a speed-optimized variant of Anthropic's most capable generally available Opus model, offering the same 1M token context window and strong performance across long-horizon agentic work and complex coding — with lower latency.

Gemma 4 26B A4B Uncensored🔒Private

e2ee-gemma-4-26b-a4b-uncensored-p·Google

Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google's Gemma 4 MoE model with 25.2B total / 3.8B active parameters, supporting multimodal input across text and images, with hardware attestation evidence available for independent verification.

Qwen3.6 35B A3B Uncensored🔒Private

e2ee-qwen3-6-35b-a3b-uncensored-p·Alibaba

Qwen3.6 35B A3B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Alibaba's Qwen3.6 MoE model with 35B total parameters and ~3B active, supporting 262K context and multimodal input across text, images, and video, with hardware attestation evidence available for independent verification.

Qwen 3.7 Max

qwen-3-7-max·Alibaba

Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.

Gemini 3.5 Flash

gemini-3-5-flash·Google

Gemini 3.5 Flash is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.

Grok Build 0.1

grok-build-0-1·xAI

xAI's fast coding model trained specifically for agentic coding, currently in early access.

Qwen 3.6 35B A3B FP8🔒Private

e2ee-qwen3-6-35b-a3b·Alibaba

Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration.

Gemma 4 31B Instruct🔒Private

e2ee-gemma-4-31b·Google

Gemma 4 31B Instruct running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.

Claude Opus 4.7 Fast

claude-opus-4-7-fast·Anthropic

Claude Opus 4.7 (Fast) is a speed-optimized variant of Anthropic's most capable generally available model, offering the same 1M token context window and strong performance across complex reasoning and agentic coding — with lower latency.

Qwen 3.6 27B

qwen3-6-27b·Alibaba

The Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.

DeepSeek V4 Pro

deepseek-v4-pro·DeepSeek

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.

DeepSeek V4 Flash

deepseek-v4-flash·DeepSeek

DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.

GPT-5.5 Pro

openai-gpt-55-pro·OpenAI

GPT-5.5 Pro is OpenAI's most advanced model, building on GPT-5.5's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.

GLM 5.1🔒Private

e2ee-glm-5-1·Z.ai

GLM 5.1 running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.

↑ NEWERVS PICKBETA

GPT-5.5

openai-gpt-55·OpenAI

GPT-5.5 is the latest frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.

Kimi K2.6

kimi-k2-6·Moonshot

Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with 256K context windows.

Grok 4.3

grok-4-3·xAI

Grok 4.3 is xAI's most intelligent and fastest reasoning model with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.

Claude Opus 4.7

claude-opus-4-7·Anthropic

Claude Opus 4.7 is Anthropic's most capable generally available model for complex reasoning and agentic coding. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

Gemma 4 Uncensored

gemma-4-uncensored·Google

Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.

GLM 5.1

zai-org-glm-5-1·Z.ai

GLM-5.1 is the next-generation large language model developed by Zhiyuan AI, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.

Qwen 3.6 Plus Uncensored

qwen-3-6-plus·Alibaba

Qwen 3.6 Plus Uncensored is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.

Google Gemma 4 31B Instruct

google-gemma-4-31b-it·Google

Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.

Google Gemma 4 26B A4B Instruct

google-gemma-4-26b-a4b-it·Google

Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.

GLM 5V Turbo

z-ai-glm-5v-turbo·Z.ai

GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image, video, and text inputs.

Venice Uncensored 1.2

venice-uncensored-1-2·Venice

Venice Uncensored 1.2 is designed for maximum creative freedom and authentic interaction. Built for open-ended exploration, roleplay, and unfiltered dialogue with improved capabilities over 1.1.

GPT-5.4 Mini

openai-gpt-54-mini·OpenAI

GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.

Nemotron Cascade 2 30B A3B

nvidia-nemotron-cascade-2-30b-a3b·Nvidia

Nemotron Cascade 2 30B A3B is a reasoning-optimized language model from NVIDIA, designed for efficient inference with strong reasoning capabilities across complex tasks.

MiniMax M2.7

minimax-m27·MiniMax

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity with advanced agentic capabilities through multi-agent collaboration.

Venice Uncensored 1.1🔒Private

e2ee-venice-uncensored-24b-p·Venice

Venice Uncensored 1.1 running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.

Gemma 3 27B🔒Private

e2ee-gemma-3-27b-p·Google

Gemma 3 27B running in a Trusted Execution Environment (TEE). Google's multimodal model supporting vision-language input with 140+ language understanding, with hardware attestation evidence available for independent verification.

GLM 4.7🔒Private

e2ee-glm-4-7-p·Z.ai

GLM 4.7 running in a Trusted Execution Environment (TEE). Z.AI's flagship model with enhanced programming capabilities and stable multi-step reasoning, with hardware attestation evidence available for independent verification.

GPT OSS 20B🔒Private

e2ee-gpt-oss-20b-p·OpenAI

GPT OSS 20B running in a Trusted Execution Environment (TEE). OpenAI's compact open-weight 21B MoE model with 3.6B active parameters, optimized for lower-latency inference, with hardware attestation evidence available for independent verification.

GPT OSS 120B🔒Private

e2ee-gpt-oss-120b-p·OpenAI

GPT OSS 120B running in a Trusted Execution Environment (TEE). OpenAI's open-weight 117B-parameter MoE model with configurable reasoning depth and native tool use, with hardware attestation evidence available for independent verification.

Qwen 2.5 7B🔒Private

e2ee-qwen-2-5-7b-p·Alibaba

Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.

Qwen3 30B A3B🔒Private

e2ee-qwen3-30b-a3b-p·Alibaba

Qwen3 30B A3B running in a Trusted Execution Environment (TEE). A MoE model with 30.5B total parameters and 3.3B activated per inference, supporting ultra-long 256K context, with hardware attestation evidence available for independent verification.

Qwen3 VL 30B A3B🔒Private

e2ee-qwen3-vl-30b-a3b-p·Alibaba

Qwen3 VL 30B A3B running in a Trusted Execution Environment (TEE). A multimodal model unifying text generation with visual understanding for images and videos, with hardware attestation evidence available for independent verification.

Mistral Small 4

mistral-small-2603·Mistral AI

Mistral Small 4 unifies instruction following, reasoning, coding, and vision in a single 119B MoE model with 256K context and configurable reasoning effort.

GLM 5 Turbo

z-ai-glm-5-turbo·Z.ai

GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.

VS PICK

Grok 4.20

grok-4-20·xAI

Grok 4.20 is xAI's latest multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.

Grok 4.20 Multi-Agent

grok-4-20-multi-agent·xAI

Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.

Qwen 3.5 9B

qwen3-5-9b·Alibaba

A 9B dense model with 262K native context window (extendable to 1M). Features Gated DeltaNet hybrid attention architecture for efficient long-context processing. Supports 201 languages, thinking/reasoning mode, and function calling.

GPT-5.4

openai-gpt-54·OpenAI

GPT-5.4 is the latest frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.

GPT-5.4 Pro

openai-gpt-54-pro·OpenAI

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.

GPT-4o

openai-gpt-4o-2024-11-20·OpenAI

OpenAI's multimodal flagship model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.

GPT-4o Mini

openai-gpt-4o-mini-2024-07-18·OpenAI

OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.

Qwen 3.5 35B A3B

qwen3-5-35b-a3b·Alibaba

Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.

GPT-5.3 Codex

openai-gpt-53-codex·OpenAI

GPT-5.3 Codex is OpenAI specialized coding model built on GPT-5.3, optimized for advanced software development, code generation, and technical problem-solving.

Venice Role Play Uncensored

venice-uncensored-role-play·Venice

Optimized for creative roleplay scenarios with maximum freedom. Designed for immersive storytelling, character interactions, and open-ended creative writing.

Mercury 2

mercury-2·Inception Labs

Mercury 2 is a diffusion-based reasoning LLM from Inception, delivering over 1,000 tokens per second — 5x faster than leading speed-optimized models — with strong reasoning, tool use, and structured output capabilities.

Gemini 3.1 Pro Preview

gemini-3-1-pro-preview·Google

Gemini 3.1 Pro is the latest evolution of Google flagship frontier model with 1M context, advancing high-precision multimodal reasoning across text, image, and code.

↑ NEWER⭐ VENICEVS PICKBETA

Claude Sonnet 4.6

claude-sonnet-4-6·Anthropic

Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.

Qwen 3.5 397B

qwen3-5-397b-a17b·Alibaba

Qwen 3.5 is Alibaba flagship reasoning model featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.

MiniMax M2.5

minimax-m25·MiniMax

MiniMax-M2.5 is a state-of-the-art large language model optimized for coding, agentic workflows, and modern application development with enhanced reasoning capabilities.

GLM 5

zai-org-glm-5·Z.ai

GLM-5 is the next-generation large language model developed by Zhiyuan AI, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis.

Claude Opus 4.6

claude-opus-4-6·Anthropic

Claude Opus 4.6 is Anthropic's most capable reasoning model, building on Opus 4.5 with enhanced performance across complex software engineering, agentic workflows, and long-horizon tasks. It features a 1M token context window, improved multimodal capabilities, and stronger robustness to prompt injection.

GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.

GLM 4.7 Flash

zai-org-glm-4.7-flash·Z.ai

GLM-4.7-Flash is a fast inference variant of GLM-4.7, optimized for speed while maintaining strong reasoning capabilities. Ideal for applications requiring quick responses with good quality.

Kimi K2.5

kimi-k2-5·Moonshot

Kimi K2.5 is Moonshot AIs most advanced open reasoning model, featuring trillion-parameter Mixture-of-Experts architecture with 32B active parameters and 256K context windows.

Qwen 3 Coder 480B Turbo

qwen3-coder-480b-a35b-instruct-turbo·Alibaba

Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.

NVIDIA Nemotron 3 Nano 30B

nvidia-nemotron-3-nano-30b-a3b·Nvidia

NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.

Qwen3 VL 235B

qwen3-vl-235b-a22b·Alibaba

Qwen3-VL 235B vision-language model with MoE architecture. The most powerful VL model in the Qwen series with superior visual perception, OCR, and multimodal reasoning.

Mistral Small 3.2 24B Instruct

mistral-small-3-2-24b-instruct·Mistral AI

Mistral Small 3.2 is a 24B parameter model optimized for efficiency and performance. Ideal for general-purpose tasks with balanced speed and capability.

GLM 4.7

zai-org-glm-4.7·Z.ai

GLM-4.7 is a large language model developed by Zhiyuan AI, featuring strong reasoning capabilities and support for multiple languages. Supports the largest context window for processing extensive text and detailed analysis.

Gemini 3 Flash Preview

gemini-3-flash-preview·Google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.

GPT-5.2

openai-gpt-52·OpenAI

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context performance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.

Claude Opus 4.5

claude-opus-4-5·Anthropic

Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.

DeepSeek V3.2

deepseek-v3.2·DeepSeek

DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.

OpenAI GPT OSS 120B

openai-gpt-oss-120b·OpenAI

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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation

Google Gemma 3 27B Instruct

google-gemma-3-27b-it·Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.

Hermes 3 Llama 3.1 405b

hermes-3-llama-3.1-405b·Meta

Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.

Qwen 3 235B A22B Thinking 2507

qwen3-235b-a22b-thinking-2507·Alibaba

Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.

Qwen 3 235B A22B Instruct 2507

qwen3-235b-a22b-instruct-2507·Alibaba

Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.

Qwen 3 Next 80b

qwen3-next-80b·Alibaba

Optimized for speed and efficiency.

Llama 3.3 70B

llama-3.3-70b·Meta

Meta's Llama 3.3 70B — open-source large model with strong general-purpose reasoning and instruction following.

Claude Sonnet 4.5

claude-sonnet-4-5·Anthropic

Claude Sonnet 4.5 is Anthropic's balanced model offering strong performance on coding, reasoning, and general tasks with good speed and cost efficiency.

GPT-5.2 Codex

openai-gpt-52-codex·OpenAI

GPT-5.2 Codex is OpenAI specialized coding model built on GPT-5.2, optimized for advanced software development, code generation, and technical problem-solving.

Llama 3.2 3B

llama-3.2-3b·Meta

Meta's compact Llama 3.2 3B — efficient open-source model for fast inference and on-device workloads.

GLM 4.6

zai-org-glm-4.6·Z.ai

GLM-4.6 is a large language model developed by Zhiyuan AI, featuring strong reasoning capabilities and support for multiple languages. Supports the largest context window for processing extensive text and detailed analysis.

Seedream V5 Pro

seedream-v5-pro·ByteDance

ByteDance's Seedream family — creative stylized outputs with strong illustrative range.

Try in Venice.ai ↗

Nano Banana 2 Lite

nano-banana-2-lite·Google

Google's Nano Banana family — cinematic aesthetic with reliable prompt following across styles.

Try in Venice.ai ↗

Grok Imagine High Quality (SOTA)

grok-imagine-image-quality·xAI

xAI's Grok Imagine for images — distinctive creative style, strong for imaginative and expressive scenes.

Try in Venice.ai ↗

Grok Imagine

grok-imagine-image·xAI

xAI's Grok Imagine for images — distinctive creative style, strong for imaginative and expressive scenes.

Try in Venice.ai ↗

Wan 2.7

wan-2-7-text-to-image·Alibaba

Alibaba's Wan text-to-image family — photorealistic outputs with strong detail preservation.

Try in Venice.ai ↗

Wan 2.7 Pro

wan-2-7-pro-text-to-image·Alibaba

Alibaba's Wan text-to-image family — photorealistic outputs with strong detail preservation.

Try in Venice.ai ↗

Community-tuned SD-based model specialized in photorealistic character rendering.

Try in Venice.ai ↗HF ↗

Qwen Image 2

qwen-image-2·Alibaba

Alibaba's Qwen Image — top-tier text rendering inside images and strong compositional control.

Try in Venice.ai ↗

⭐ VENICEVS PICK

Qwen Image 2 Pro

qwen-image-2-pro·Alibaba

Alibaba's Qwen Image — top-tier text rendering inside images and strong compositional control.

Try in Venice.ai ↗

Hunyuan Image 3.0

hunyuan-image-v3·Tencent

Tencent's Hunyuan image model — photorealistic generation with broad aesthetic range.

Try in Venice.ai ↗

⭐ VENICEVS PICK

Nano Banana 2

nano-banana-2·Google

Google's Nano Banana family — cinematic aesthetic with reliable prompt following across styles.

Try in Venice.ai ↗

Background Remover

bria-bg-remover·Bria AI

Bria AI's background removal — precise subject isolation with clean edge preservation.

Try in Venice.ai ↗

VS PICK

Seedream V5 Lite

seedream-v5-lite·ByteDance

ByteDance's Seedream family — creative stylized outputs with strong illustrative range.

Try in Venice.ai ↗

VS PICK

Recraft V4

recraft-v4·Recraft

Recraft's design-focused image model — strong typography, brand layouts, and vector-style output.

Try in Venice.ai ↗

VS PICK

Recraft V4 Pro

recraft-v4-pro·Recraft

Recraft's design-focused image model — strong typography, brand layouts, and vector-style output.

Try in Venice.ai ↗

Open-source image model tuned for vivid color saturation and controlled palettes.

Try in Venice.ai ↗HF ↗

ImagineArt 1.5 Pro

imagineart-1.5-pro·ImagineArt

ImagineArt's image model — stylized outputs focused on illustrative and artistic compositions.

Try in Venice.ai ↗

GPT Image 1.5

gpt-image-1-5·OpenAI

OpenAI's GPT Image — text-aware image generation with strong typography and diagram rendering.

Try in Venice.ai ↗

Z-Image Turbo

z-image-turbo·Z.ai

Zhipu AI's Z-Image Turbo — fast inference with competitive quality for quick iterations.

Try in Venice.ai ↗HF ↗

Flux 2 Pro

flux-2-pro·Black Forest Labs

Black Forest Labs' Flux 2 family — photorealistic generation with strong prompt fidelity and complex scene composition.

Try in Venice.ai ↗

⭐ VENICEVS PICK

Flux 2 Max

flux-2-max·Black Forest Labs

Black Forest Labs' Flux 2 family — photorealistic generation with strong prompt fidelity and complex scene composition.

Try in Venice.ai ↗

VS PICK

Nano Banana Pro

nano-banana-pro·Google

Google's Nano Banana family — cinematic aesthetic with reliable prompt following across styles.

Try in Venice.ai ↗

VS PICK

Seedream V4.5

seedream-v4·ByteDance

ByteDance's Seedream family — creative stylized outputs with strong illustrative range.

Try in Venice.ai ↗

Venice SD35

venice-sd35·Stability AI

Venice's self-hosted Stable Diffusion 3.5 build — open-source, privacy-preserving image generation.

Try in Venice.ai ↗HF ↗

Lustify SDXL

lustify-sdxl·Stability AI

SDXL-tuned community model focused on photorealistic characters and natural lighting.

Try in Venice.ai ↗HF ↗

Community-tuned SD-based model specialized in photorealistic character rendering.

Try in Venice.ai ↗HF ↗

Qwen Image

qwen-image·Alibaba

Alibaba's Qwen Image — top-tier text rendering inside images and strong compositional control.

Try in Venice.ai ↗HF ↗

Specialized SDXL variant for anime and illustration — strong character fidelity and line art.

Try in Venice.ai ↗HF ↗

Kling V3 Turbo Pro

kling-v3-turbo-pro-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Turbo Pro

kling-v3-turbo-pro-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Turbo Standard

kling-v3-turbo-standard-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Turbo Standard

kling-v3-turbo-standard-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Wan 2.7 Enhanced

wan-2-7-enhanced-text-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Kling V3 Pro Motion Control

kling-v3-pro-motion-control·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Standard Motion Control

kling-v3-standard-motion-control·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Wan 2.7 Enhanced

wan-2-7-enhanced-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Kling V3 4K

kling-v3-4k-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 4K R2V

kling-v3-4k-reference-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 4K

kling-o3-4k-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 4K

kling-o3-4k-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 4K R2V

kling-o3-4k-reference-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Grok Imagine Private

grok-imagine-image-to-video-private·xAI

xAI's Grok Imagine for images — distinctive creative style, strong for imaginative and expressive scenes.

Try in Venice.ai ↗

PixVerse C1

pixverse-c1-text-to-video·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

PixVerse C1

pixverse-c1-image-to-video·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

PixVerse C1 R2V

pixverse-c1-reference-to-video·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

PixVerse C1 Transition

pixverse-c1-transition·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

Topaz Video Upscale

topaz-video-upscale·Topaz Labs

Topaz Video AI upscaler — enhances video resolution and frame quality through AI super-resolution.

Try in Venice.ai ↗

Wan 2.7

wan-2-7-text-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.7

wan-2-7-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.7 Reference

wan-2-7-reference-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.7 Edit

wan-2-7-video-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Kling O3 Standard R2V

kling-o3-standard-reference-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 Pro R2V

kling-o3-pro-reference-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

LTX Video 2.3 Fast

ltx-2-v2-3-fast-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.3 Fast

ltx-2-v2-3-fast-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.3 Full Quality

ltx-2-v2-3-full-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.3 Full Quality

ltx-2-v2-3-full-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

⭐ VENICEVS PICK

Kling O3 Pro

kling-o3-pro-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

⭐ VENICEVS PICK

Kling O3 Pro

kling-o3-pro-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 Standard

kling-o3-standard-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling O3 Standard

kling-o3-standard-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Pro

kling-v3-pro-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Pro

kling-v3-pro-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Standard

kling-v3-standard-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling V3 Standard

kling-v3-standard-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Vidu Q3

vidu-q3-text-to-video·Shengshu

Shengshu's Vidu — efficient video generation with strong anime and stylized-output support.

Try in Venice.ai ↗

Vidu Q3

vidu-q3-image-to-video·Shengshu

Shengshu's Vidu — efficient video generation with strong anime and stylized-output support.

Try in Venice.ai ↗

PixVerse v5.6

pixverse-v5.6-text-to-video·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

PixVerse v5.6

pixverse-v5.6-image-to-video·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

PixVerse v5.6 Transition

pixverse-v5.6-transition·Pixverse

Pixverse's video family — stylized generation with broad aspect ratio and resolution options.

Try in Venice.ai ↗

Wan 2.6 Flash

wan-2.6-flash-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

LTX Video 2.0 19B

ltx-2-19b-full-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 19B

ltx-2-19b-full-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 19B Distilled

ltx-2-19b-distilled-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 19B Distilled

ltx-2-19b-distilled-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

Wan 2.6

wan-2.6-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.6

wan-2.6-text-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Longcat Distilled

longcat-distilled-image-to-video·Meituan

Meituan's Longcat family — long-duration video generation with consistent subject coherence.

Try in Venice.ai ↗HF ↗

Longcat Distilled

longcat-distilled-text-to-video·Meituan

Meituan's Longcat family — long-duration video generation with consistent subject coherence.

Try in Venice.ai ↗HF ↗

Longcat Full Quality

longcat-image-to-video·Meituan

Meituan's Longcat family — long-duration video generation with consistent subject coherence.

Try in Venice.ai ↗HF ↗

Longcat Full Quality

longcat-text-to-video·Meituan

Meituan's Longcat family — long-duration video generation with consistent subject coherence.

Try in Venice.ai ↗HF ↗

Wan 2.5 Preview

wan-2.5-preview-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.5 Preview

wan-2.5-preview-text-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.2 A14B

wan-2.2-a14b-text-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Wan 2.1 Pro

wan-2.1-pro-image-to-video·Alibaba

Alibaba's Wan video family — photorealistic generation with strong subject coherence across frames.

Try in Venice.ai ↗

Ovi image-to-video — animates still images with natural motion and subtle camera dynamics.

Try in Venice.ai ↗HF ↗

Kling 2.5 Turbo Pro

kling-2.5-turbo-pro-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling 2.5 Turbo Pro

kling-2.5-turbo-pro-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Veo 3 Fast

veo3-fast-text-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Veo 3 Fast

veo3-fast-image-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Veo 3 Full Quality

veo3-full-text-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Veo 3 Full Quality

veo3-full-image-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Sora 2

sora-2-image-to-video·OpenAI

OpenAI's Sora 2 — long-horizon scenes with prompt complexity and realistic physics.

Try in Venice.ai ↗

VS PICK

Sora 2 Pro

sora-2-pro-image-to-video·OpenAI

OpenAI's Sora 2 — long-horizon scenes with prompt complexity and realistic physics.

Try in Venice.ai ↗

Sora 2

sora-2-text-to-video·OpenAI

OpenAI's Sora 2 — long-horizon scenes with prompt complexity and realistic physics.

Try in Venice.ai ↗

VS PICK

Sora 2 Pro

sora-2-pro-text-to-video·OpenAI

OpenAI's Sora 2 — long-horizon scenes with prompt complexity and realistic physics.

Try in Venice.ai ↗

Kling 2.6 Pro

kling-2.6-pro-text-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

Kling 2.6 Pro

kling-2.6-pro-image-to-video·Kuaishou

Kuaishou's Kling family — cinematic quality, strong for human motion and editorial scenes.

Try in Venice.ai ↗

LTX Video 2.0 Fast

ltx-2-fast-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 Fast

ltx-2-fast-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 Full Quality

ltx-2-full-image-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

LTX Video 2.0 Full Quality

ltx-2-full-text-to-video·Lightricks

Lightricks LTX family — fast open-source video generation optimized for iterative workflows.

Try in Venice.ai ↗

Veo 3.1 Fast

veo3.1-fast-text-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Veo 3.1 Fast

veo3.1-fast-image-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

VS PICK

Veo 3.1 Full Quality

veo3.1-full-text-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

VS PICK

Veo 3.1 Full Quality

veo3.1-full-image-to-video·Google

Google DeepMind's Veo — narrative-driven video with strong realism, physics, and cinematography.

Try in Venice.ai ↗

Seed Audio 1.0

seed-audio-1-0·ByteDance Seed

Generate expressive speech and audio from a text prompt with BytePlus Seed Audio 1.0.

Try in Venice.ai ↗

Lyria 3 Pro

lyria-3-pro·Google

Google's Lyria 3 Pro generates full-length, structured songs up to 3 minutes long from a single text prompt. Supports vocals, lyrics, and multi-language generation across genres.

Try in Venice.ai ↗

VS PICK

MiniMax Music 2.5

minimax-music-v25·MiniMax

Advanced song generation with vocals, lyrics optimizer, and instrumental mode. Supports structure tags and up to 3500 character lyrics.

Try in Venice.ai ↗

VS PICK

MiniMax Music 2.6

minimax-music-v26·MiniMax

Latest MiniMax song generation with vocals, instrumental mode, and support for rich structure tags in lyrics.

Try in Venice.ai ↗

VS PICK

ElevenLabs Sound Effects

elevenlabs-sound-effects-v2·ElevenLabs

Generate high-quality sound effects from text descriptions using ElevenLabs. Ideal for films, games, and digital content with configurable duration.

Try in Venice.ai ↗

MMAudio V2

mmaudio-v2-text-to-audio·Sony AI

Generate synchronized audio and sound effects from text prompts with MMAudio V2.

Try in Venice.ai ↗

ElevenLabs TTS v3

elevenlabs-tts-v3·ElevenLabs

Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization.

Try in Venice.ai ↗

ElevenLabs Multilingual v2

elevenlabs-tts-multilingual-v2·ElevenLabs

Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy.

Try in Venice.ai ↗

ACE-Step 1.5

ace-step-15·ACE Studio

Feature-rich song generation with optional lyrics and detailed musical controls.

Try in Venice.ai ↗

VS PICK

ElevenLabs Music

elevenlabs-music·ElevenLabs

High-quality instrumental music generation with configurable duration. Best for polished, production-ready tracks across a wide range of genres.

Try in Venice.ai ↗

MiniMax Music 2.0

minimax-music-v2·MiniMax

Full song generation with vocals and lyrics. Provide your own lyrics with verse/chorus structure for complete songs with singing.

Try in Venice.ai ↗

Stable Audio 2.5

stable-audio-25·Stability AI

Fast, lightweight audio generation for sound effects, ambient textures, and short musical clips. Flexible duration from 5 seconds to over 3 minutes.

Try in Venice.ai ↗

Seedream V5 Pro

seedream-v5-pro-edit·ByteDance

Editing variants of ByteDance's Seedream — stylized inpainting with the family's illustrative range.

Try in Venice.ai ↗

Nano Banana 2 Lite

nano-banana-2-lite-edit·Google

Editing variants of Google's Nano Banana — precise inpainting with identity and detail preservation.

Try in Venice.ai ↗

GPT Image 2

gpt-image-2-edit·OpenAI

Editing variant of OpenAI's GPT Image — text-aware inpainting with strong typography handling.

Try in Venice.ai ↗

FireRed Edit

firered-image-edit·FireRed

FireRed image editor — localized inpainting focused on portrait retouching and detail refinement.

Try in Venice.ai ↗

Qwen Image 2

qwen-image-2-edit·Alibaba

Editing variants of Alibaba's Qwen Image — high-fidelity inpainting with strong text rendering.

Try in Venice.ai ↗

VS PICK

Qwen Image 2 Pro

qwen-image-2-pro-edit·Alibaba

Editing variants of Alibaba's Qwen Image — high-fidelity inpainting with strong text rendering.

Try in Venice.ai ↗

VS PICK

Nano Banana 2

nano-banana-2-edit·Google

Editing variants of Google's Nano Banana — precise inpainting with identity and detail preservation.

Try in Venice.ai ↗

Seedream V5 Lite

seedream-v5-lite-edit·ByteDance

Editing variants of ByteDance's Seedream — stylized inpainting with the family's illustrative range.

Try in Venice.ai ↗

VS PICK

Grok Imagine

grok-imagine-edit·xAI

Image-editing variant of xAI's Grok Imagine — inpainting with the family's distinctive style.

Try in Venice.ai ↗

Flux 2 Max

flux-2-max-edit·Black Forest Labs

Editing variant of Black Forest Labs' Flux — inpainting and scene edits with photorealistic fidelity.

Try in Venice.ai ↗

GPT Image 1.5

gpt-image-1-5-edit·OpenAI

Editing variant of OpenAI's GPT Image — text-aware inpainting with strong typography handling.

Try in Venice.ai ↗

Seedream V4.5

seedream-v4-edit·ByteDance

Editing variants of ByteDance's Seedream — stylized inpainting with the family's illustrative range.

Try in Venice.ai ↗

VS PICK

Nano Banana Pro

nano-banana-pro-edit·Google

Editing variants of Google's Nano Banana — precise inpainting with identity and detail preservation.

Try in Venice.ai ↗

MiniMax Speech-02 HD

tts-minimax-speech-02-hd·MiniMax

Clone your voice from a short recording and generate natural speech in it across 30+ languages.

Try in Venice.ai ↗

Qwen 3 TTS 0.6B

tts-qwen3-0-6b·Alibaba

Alibaba's compact Qwen 3 TTS — small model suitable for fast, low-latency speech synthesis.

Try in Venice.ai ↗HF ↗

Qwen 3 TTS 1.7B

tts-qwen3-1-7b·Alibaba

Alibaba's Qwen 3 TTS at larger scale — improved voice naturalness over the 0.6B variant.

Try in Venice.ai ↗HF ↗

VS PICK

Kokoro Text to Speech

tts-kokoro·Hexgrad

Open-source TTS with natural-sounding voices and efficient inference — popular community baseline.

Try in Venice.ai ↗HF ↗

Parakeet ASR

nvidia/parakeet-tdt-0.6b-v3·Nvidia

Nvidia's Parakeet ASR — optimized for low-latency transcription with competitive accuracy.

Try in Venice.ai ↗HF ↗

VS PICK

Whisper Large V3

openai/whisper-large-v3·OpenAI

OpenAI's open-source speech recognition — multilingual, robust to accents, noise, and technical content.

Try in Venice.ai ↗

BGE-M3

text-embedding-bge-m3·BAAI

BAAI's BGE-M3 — multilingual embedding model supporting dense, sparse, and multi-vector retrieval.

Try in Venice.ai ↗HF ↗

General-purpose image upscaler — enhances resolution and detail across a wide range of image types.

Try in Venice.ai ↗