LLM ReferenceLLM Reference
Replicate API

Llama 3 8B on Replicate API

Llama 3 · AI at Meta

ServerlessOpen Source

Last refreshed 2026-04-15. Next refresh: weekly.

Why use Llama 3 8B on Replicate API?

Replicate API offers Llama 3 8B with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Llama 3 8B across 2 providers to find the best fit for your use case
Input / 1M
$0.050
Output / 1M
$0.25
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "llama3-8b",
    input={"prompt": "Hello"}
Model ID
llama3-8b

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# llama3-8b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "llama3-8b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • 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.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare Llama 3 8B Across Providers

ProviderInput (per 1M)Output (per 1M)
Fireworks AI$0.20$0.20
Replicate API$0.05$0.25

Pricing

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.25

Capabilities

No model capability flags are currently sourced.

About Llama 3 8B

The Llama 3 8B model, released on April 18, 2024, is Meta's latest large language model featuring 8 billion parameters. It's an auto-regressive transformer optimized for text generation and dialogue applications, particularly suited for assistant-like interactions. Trained on over 15 trillion tokens from diverse public sources, it incorporates advanced techniques like supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). This model is designed to outperform many existing open-source chat models on industry benchmarks, emphasizing helpfulness and safety in its outputs. It's available for commercial and research use in English through the Hugging Face platform .

FAQ

What does Llama 3 8B cost on Replicate API?

On Replicate API, Llama 3 8B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens.

What is the context window for Llama 3 8B on Replicate API?

Llama 3 8B supports a 8,000 token context window on Replicate API.

How does Replicate API compare to other Llama 3 8B providers?

Llama 3 8B is available from 2 providers. The cheapest input pricing is $0.05/1M tokens from Replicate API.

Who created Llama 3 8B?

Llama 3 8B was created by AI at Meta as part of the Llama 3 model family.

Is Llama 3 8B open source?

Llama 3 8B is open source according to the seed data.

Get Started

Model Specs

Released2024-04-18
Parameters8B
Context8K
ArchitectureDecoder Only