API for Open-Source LLMs

Llama 4 API available

DeepSeek R1 API available

Function Calling: AI That Interacts
With The External World

Llama 4

META'S LLAMA-4

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

Overview

MODELS SIZE: Llama 4 Maverick and Scout

LLM API was the first platform to implement functions for Llama-2 right when it was first launched. After that we never stopped to release easy-to-use open-source models for all.

Overview

MODELS SIZE: Llama 3.3 90B, 70B, 11B, 8B, 3B, 1B

LLM API was the first platform to implement functions for Llama-2 right when it was first launched. After that we never stopped to release easy-to-use open-source models for all.

Llama 3.3

META'S LLAMA-3.3

LLM 3.3 70B Instruct is the December update of Llama 3.1 70B. The model improves upon LLM 3.1 70B (released July 2024) with advances in tool calling, multilingual text support, math and coding. The model achieves industry leading results in reasoning, math and instruction following and provides similar performance as 3.1 405B but with significant speed and cost improvements.

Llama 3.2

META'S LLAMA-3.2

Meta's Llama 3.2 sets a new standard for open source AI. Llama-3.2 11B, Llama-3.2 90B, are the first highly capable open-source vision model in the Llama Family.

Overview

MODELS SIZE: Llama 3.2 Vision 90B and 11B, Llama 3.2 Text 3B and 1B

LLM API was the first platform to implement functions for Llama-2 right when it was first launched. After that we never stopped to release easy-to-use open-source models for all.