Replicate API exposes Llama 3 8B through model ID meta/meta-llama-3-8b. 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
- 2Use the Replicate API SDK or REST API to call
meta/meta-llama-3-8b— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENmeta/meta-llama-3-8bReplicate 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
# meta/meta-llama-3-8b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"meta/meta-llama-3-8b",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Price (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 .