Model Library

Llama

Llama 4 Maverick 17B (128E) Instruct

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Featured Popular

High-capacity multimodal language model built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters. Supports multilingual text and image input.

DeepSeek

Deepseek V3 03-24

deepseek-ai/DeepSeek-V3-0324

Popular

An iteration of the DeepSeek V3 model with notable improvements in reasoning capabilities across various benchmarks, including MMLU-Pro, GPQA, and AIME.

Llama

Llama 4 Scout 17B (16E) Instruct

meta-llama/Llama-4-Scout-17B-16E-Instruct

Popular

A mixture-of-experts (MoE) language model activating 17 billion parameters out of a total of 109B. Designed for assistant-style interaction and visual reasoning.

DeepSeek

DeepSeek R1 (Basic)

deepseek-ai/DeepSeek-R1

Popular

DeepSeek R1 is a powerful reasoning model designed for complex problem-solving and advanced coding tasks.

Llama

Llama 3.2 11B Vision Instruct

Part of Meta's vision family, designed for a wide array of vision-language tasks including visual recognition, image reasoning, and captioning.

Read More
DeepSeek

DeepSeek R1 (Basic)

DeepSeek R1 is a powerful reasoning model designed for complex problem-solving and advanced coding tasks.

Serverless

Read More
Previous
1

2

Next

Get started

Let's make your LLM better!

Book a Demo