Using Llama 3.1-70B on Replicate API

Implementation guide · Llama 3.1 · AI at Meta

ServerlessOpen Weights

Replicate API exposes Llama 3.1-70B through model ID llama-3-1-70b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-18. Next refresh: weekly.

Quick Start

1
Create an account at Replicate API and generate an API key.
2
Use the Replicate API SDK or REST API to call llama-3-1-70b — see the documentation for request format.
3
You'll be billed $1.20/1M input, $1.20/1M output tokens. See full pricing.

API Portal Documentation Pricing

Code Examples

Install

pip install replicate

API key

REPLICATE_API_TOKEN

Model ID

llama-3-1-70b

Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.

import replicate

# reads REPLICATE_API_TOKEN from env
# llama-3-1-70b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "llama-3-1-70b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))