Models
Explore 166+ production-ready models across language, image, audio, and video. Filter by category, dive into model details, and wire them directly into your workflows.
Staff picks
Our favorite models worth a closer look.
Video Generation
Image Generation
Audio Generation
Language models (LLMs)
All models (a-z)
Browse the complete directory (166) or jump to a category above.
Gemma2 9b It On Groq
Google DeepMind
Gemma 3 27b It
Google DeepMind
Llama3 70b 8192 On Groq
Meta
Llama3.3 70b On Groq
Meta
Llama3 8b 8192 On Groq
Meta
Mixtral 8x7b
Mistral
GPT 4o
OpenAI
GPT 4o 2024 11 20
OpenAI
GPT 4o Mini
OpenAI
GPT 4.1
OpenAI
GPT 5
OpenAI
GPT 5 Mini
OpenAI
GPT 5 Nano
OpenAI
GPT 5 Chat Latest
OpenAI
GPT 5.2
OpenAI
Chatgpt 4o Latest
OpenAI
O3 Mini
OpenAI
Llama 3.3 70b Instruct
Meta
Llama 3.3 70b Instruct On Cerebras
Meta
Llama 3.2 3b Instruct
Meta
Llama 3.2 1b Instruct
Meta
Llama 3.1 405b Instruct
Meta
Llama 3.1 405b Base
Meta
Llama 3 70b Instruct
Meta
Claude 3 Haiku
Anthropic
Claude 3.5 Haiku
Anthropic
Claude 3 Sonnet
Anthropic
Claude 3.5 Sonnet
Anthropic
Claude 3.5 Sonnet 20240620
Anthropic
Claude 3.7 Sonnet
Anthropic
Claude 3 Opus
Anthropic
Claude Sonnet 4
Anthropic
Claude Opus 4
Anthropic
Claude Opus 4.1
Anthropic
Claude Sonnet 4.5
Anthropic
Claude Haiku 4.5
Anthropic
Claude Opus 4.5
Anthropic
Gemini Pro 1.5
Google DeepMind
Gemini 2.0 Flash Exp
Google DeepMind
Gemini 2.0 Flash
Google DeepMind
Gemini Flash 1.5
Google DeepMind
Gemini 2.0 Flash Lite Preview
Google DeepMind
Gemini 2.0 Pro Exp
Google DeepMind
Gemini 2.5 Pro Preview
Google DeepMind
Gemini 3 Pro Preview
Google DeepMind
Perplexity: Sonar
Perplexity
Mistral Large
Mistral
Hermes 3 Llama 3.1 70b
Nous Research
Hermes 3 Llama 3.1 405b
Nous Research
Wizardlm 2 8x22b
Microsoft
GPT 1
OpenAI
GPT 3.5 Turbo
OpenAI
GPT 3.5 Turbo Instruct
OpenAI
GPT 3.5 Turbo 0125
OpenAI
GPT 3.5 Turbo 1106
OpenAI
GPT 3.5 Turbo 0613
OpenAI
GPT 3.5 Turbo 16k
OpenAI
GPT 3.5 Turbo 16k 0613
OpenAI
GPT 4
OpenAI
GPT 4 0613
OpenAI
GPT 4 Turbo Preview
OpenAI
GPT 4 0125 Preview
OpenAI
GPT 4 1106 Preview
OpenAI
Deepseek Chat
Deepseek
Deepseek R1
Deepseek
Deepseek R1 Distill Llama 70b
Deepseek
Deepseek R1 Distill Llama 70b On Groq
Deepseek
Deepseek R1 Distill Llama 70b On Groq With Raw Reasoning
Deepseek
Grok 2 1212
XAI
Qwen Max
Alibaba Cloud
Llama 4 Scout
Meta
Llama 4 Maverick
Meta
Kimi K2
Moonshot AI
Kimi K2 Turbo Preview
Moonshot AI
Kimi K2 On Groq
Moonshot AI
Kimi K2 0905 On Groq
Moonshot AI
GPT Image by OpenAI
OpenAI
Stable Diffusion XL [img2img, controlnet]
Stability AI
Bria Fibo
BRIA AI
Controllism v1 [controlnet]
Stability AI
DALL-E 3 by OpenAI
OpenAI
Flux Pro
Black Forest Labs
Flux Pro v1.1
Black Forest Labs
Flux Pro v1.1 Ultra
Black Forest Labs
Flux Dev
Black Forest Labs
Flux Schnell
Black Forest Labs
Flux SRPO
Black Forest Labs
Fast Flux Dev [+LoRA]
Black Forest Labs
Fast Flux Schnell [+LoRA]
Black Forest Labs
Sana Sprint
NVIDIA
Google Imagen 4
Google DeepMind
Hunyuan Image 3
Tencent
Flux Pro Kontext Editing
Black Forest Labs
Flux Pro Kontext Editing Multi-Image
Black Forest Labs
Seedream V3
ByteDance
Seededit V3
ByteDance
Seedream V4 Image to Image
ByteDance
Seedream V4 Text to Image
ByteDance
Seedream V4.5
ByteDance
Gen-4 Image
Runway
Ideogram V3
Ideogram
Qwen-Image
Alibaba Cloud
Qwen-Image-Edit
Alibaba Cloud
Qwen-Image-Edit-Lora
Alibaba Cloud
Qwen-Image-Edit-Plus-Lora
Alibaba Cloud
Qwen-Image-Lora
Alibaba Cloud
Wan 2.2 Text to Image [+LoRA]
Alibaba Cloud
Clarity Upscaler
General image model guidance: Prompts do not persist across generations鈥攖here is no transfer from one image prompt to the next. Restate all visual attributes in every prompt; do not rely on prior images or memory. When using image models inside agents or chains, include explicit image-prompting instructions in the agent prompt. Otherwise outputs may drift to generic imagery (e.g., 'the ship has arrived' might become a cruise ship instead of a Viking longship).
Crystal Upscaler
General image model guidance: Prompts do not persist across generations鈥攖here is no transfer from one image prompt to the next. Restate all visual attributes in every prompt; do not rely on prior images or memory. When using image models inside agents or chains, include explicit image-prompting instructions in the agent prompt. Otherwise outputs may drift to generic imagery (e.g., 'the ship has arrived' might become a cruise ship instead of a Viking longship).
Recraft Crisp Upscale
Recraft
馃崒 Nano Banana (text to image)
Google DeepMind
馃崒 Nano Banana (edit)
Google DeepMind
馃崒 Nano Banana Pro
Google DeepMind
馃崒 Nano Banana Pro Edit
Google DeepMind
Flux 2 Pro
Black Forest Labs
Flux 2 Flex
Black Forest Labs
Z Image Turbo
Alibaba Cloud
Kokoro
Hexgrad
Music ElevenLabs
ElevenLabs
Music MiniMax v2
MiniMax
Sound Effects ElevenLabs
ElevenLabs
Speech-to-Speech ElevenLabs
ElevenLabs
Voice ElevenLabs
ElevenLabs
Zonos
Zyphra
Fish Audio TTS
Fish Audio
Hailuo 2.3
MiniMax
Hailuo 2.3 Fast
MiniMax
Hailuo V2 Fast
MiniMax
Hailuo V2 Standard
MiniMax
InfiniteTalk
MeiGen AI
Kling 2.1 Pro - Image to Video
Kuaishou Technology
Kling 2.1 Standard - Image to Video
Kuaishou Technology
Kling 2.5 Turbo Pro - Image to Video
Kuaishou Technology
Kling 2.5 Turbo Pro - Text to Video
Kuaishou Technology
Kling 2.6 Pro
Kuaishou Technology
Kling AI Avatar Pro
Kuaishou Technology
Kling AI Avatar Standard
Kuaishou Technology
Kling Omni 1
Kuaishou Technology
LTX 2 Fast
Lightricks
LTX 2 Pro
Lightricks
MMAudio V2
MMAudio
MultiTalk Single Audio
MeiGen AI
OmniHuman
ByteDance
Sora 2
OpenAI
Sora 2 Pro
OpenAI
Ovi
Character AI
Runway Gen-4 Aleph - Video to Video
Runway
Seedance V1 Lite - Image to Video
ByteDance
Seedance V1 Lite - Text to Video
ByteDance
Seedance V1 Pro - Image to Video
ByteDance
Seedance V1 Pro - Text to Video
ByteDance
Sync Lipsync V2 Pro
Lipsync
ThinkSound Vid2Vid
ThinkSound
Veo 3
Google DeepMind
Veo 3 Fast
Google DeepMind
Veo 3 Fast - Image to Video
Google DeepMind
Veo 3.1
Google DeepMind
Veo 3.1 Fast
Google DeepMind
Veo 3.1 - First-Last Frame to Video
Google DeepMind
Wan 2.1 Vace
Alibaba Cloud
Wan 2.2 Animate
Alibaba Cloud
Wan 2.2 Image to Video
Alibaba Cloud
Wan 2.2 Text to Video
Alibaba Cloud
Wan 2.5 Image to Video
Alibaba Cloud
Wan 2.5 Text to Video
Alibaba Cloud
Wavespeed Video Watermark Remover
WaveSpeedAI