Last refreshed 2026-07-09. Next refresh: weekly.
Why use Llama 3.1-405B on Replicate API?
Replicate API offers Llama 3.1-405B with pay-as-you-go pricing at $3.75/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Llama 3.1-405B across 2 providers to find the best fit for your use caseInput / 1M
$3.75
Output / 1M
$3.75
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"llama-3-1-405b",
input={"prompt": "Hello"}Model ID
llama-3-1-405bRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# llama-3-1-405b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"llama-3-1-405b",
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 3.1-405B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| GCP Vertex AI | $5.00 | $16.00 |
| Replicate API | $3.75 | $3.75 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $3.75 |
| Output tokens | $3.75 |
Capabilities
JSON / Tool useStructured OutputsFine-tuning
About Llama 3.1-405B
Meta's flagship Llama 3.1 model with 405B parameters and 128K context window. Open-weights model with strong reasoning and coding capabilities.
Get Started
Model Specs
Released2024-07-23
Parameters405B
Context128k
Knowledge cutoff2024-04