Model Directory

The AI Model Center

Explore 50+ AI models for text, image, audio, code, and multimodal tasks — all in one place.

Advertisement

Gemma 3 12B

Google DeepMind

Open-weight instruction-tuned model. Excellent reasoning at small sizes, runs comfortably on consumer GPUs.

Text12BOpen

Llama 3.1 70B

Meta AI

Frontier-class open model. Strong on coding, reasoning, and long-context tasks.

Text70BOpen

Claude 3.5 Sonnet

Anthropic

Industry-leading model for coding, analysis, and long-context (200K) tasks. Top of HumanEval and SWE-Bench.

Text200K ctxAPI

GPT-4o

OpenAI

Multimodal flagship — text, vision, and audio in a single model with low latency.

Multi128K ctxAPI

Mistral 7B

Mistral AI

Compact and fast. Apache 2.0 licensed — great for production deployment on consumer hardware.

Text7BApache 2.0

Phi-3 Mini

Microsoft

3.8B parameter model that punches well above its weight. Designed for edge and mobile deployment.

Text3.8BMIT

Qwen 2.5 72B

Alibaba Cloud

Multilingual frontier-class open model. Strong on Chinese, English, code, and math.

Text72BApache 2.0

DeepSeek-V3

DeepSeek AI

671B MoE model with frontier-level reasoning. Open weights, exceptional cost-to-performance ratio.

Text671B MoEOpen

Flux.1 Dev

Black Forest Labs

State-of-the-art text-to-image generation with photorealistic output and precise prompt adherence.

Image12BOpen

Stable Diffusion XL

Stability AI

Most popular open image-generation model with massive community of fine-tunes and LoRAs.

Image3.5BOpen

DALL-E 3

OpenAI

High-quality text-to-image with strong prompt understanding. Available via OpenAI and ChatGPT.

ImageAPI

Whisper Large v3

OpenAI

Open-source speech-to-text model. Best-in-class transcription across 99 languages.

Audio1.5BMIT

Code Llama 70B

Meta AI

Fine-tuned for code generation, completion, and infilling. Strong on Python, C++, JavaScript.

Code70BOpen

Qwen 2.5 Coder

Alibaba

Best open-source code model — competitive with GPT-4 on coding benchmarks.

Code32BApache 2.0

Gemini 1.5 Pro

Google

Multimodal model with 2M context window — process entire codebases or hour-long videos.

Multi2M ctxAPI

More models being added every week. Know one we're missing? Submit it →