TechPrufer
Get started
Replicate
Replicate logoReplicate · Feature trail

LLM API Access

1 post · Apr 2024 – Oct 2025

What this trail covers

Replicate provides API access to large language models, including Snowflake's Arctic, Meta's Llama 3, IBM's Granite 4.0, and Meta's Llama 3.1 405B. The platform offers client libraries for JavaScript, Python, and other languages, as well as direct HTTP API access. Users can stream output and integrate these models into their applications. The platform also emphasizes responsible AI practices and provides example applications and API playgrounds for various models. Arctic is a 480B parameter model. This post details running Llama 3 with API access, including client libraries for JavaScript and Python, and direct HTTP API calls via cURL. It also outlines the different Llama 3 variants available and provides a link to a demo chat app.

All Replicate trails
  1. IBM's Granite 4.0 is now on ReplicateThis post announces the availability of IBM's Granite 4.0 models on Replicate. It details the hybrid architecture of Granite 4.0, which combines Mamba-2's linear scaling with Transformer precision, and the MoE routing strategy used in some variants. It highlights the practical applications of these models, such as document summarization, RAG systems, and AI agents, and emphasizes their open-source nature under the Apache 2.0 license. Code examples for cURL, JavaScript, and Python are provided to demonstrate API usage.
  2. Run Meta Llama 3.1 405B with an APIThis post details how to run Meta's Llama 3.1 405B model via API using Replicate's JavaScript client, Python client, and cURL. It provides code snippets for each method, including examples of streaming output. It also highlights the model's capabilities, responsible AI features, and links to a demo chat app.
  3. Run Snowflake Arctic with an APIThis post details how to run the Snowflake Arctic LLM via Replicate's API using JavaScript, Python, and cURL. It provides code snippets for each method, including setting up API tokens and streaming output. It also highlights a Streamlit demo application for Arctic.
  4. Run Meta Llama 3 with an APIThis post details how to run Meta's Llama 3 models (70B and 8B, instruct and base variants) via Replicate's API. It provides code examples for using JavaScript and Python client libraries, as well as direct HTTP API calls with cURL. It also highlights the API playground for interactive testing and links to a demo chat app.