Last refreshed 2026-07-09. Next refresh: weekly.
Why use Llama 3.1 8B Instruct on Replicate API?
Replicate API offers Llama 3.1 8B Instruct with pay-as-you-go pricing at $0.25/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Llama 3.1 8B Instruct across 17 providers to find the best fit for your use caseSetup recipe
Python + curlpip install replicateexport REPLICATE_API_TOKEN=...import replicate
output = replicate.run(
"llama3.1-8b-instruct",
input={"prompt": "Hello"}llama3.1-8b-instructRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# llama3.1-8b-instruct format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"llama3.1-8b-instruct",
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 3.1 8B Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | — | — |
| OctoAI API (Deprecated) | — | — |
| Together AI | $0.18 | $0.18 |
| Fireworks AI | $0.20 | $0.20 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.25 |
| Output tokens | $0.25 |
Capabilities
About Llama 3.1 8B Instruct
The Llama 3.1 8B Instruct model, released on July 23, 2024, is a multilingual large language model with 8 billion parameters, optimized for instruction-following tasks. It features an enhanced transformer architecture, supporting languages like English, German, French, and others. The model excels in dialogue applications, having been fine-tuned using supervised fine-tuning and reinforcement learning with human feedback. Trained on approximately 15 trillion tokens with a December 2023 data cutoff, it outperforms many existing open-source and closed chat models in various benchmarks.