This model was retired on 2025-06-25. The pricing below is the last-known rate, kept for migration reference.

Meta Llama 3.1 405B InstructDeprecated

Meta
Tool useStructured output
Context
128K
Max output
128K
Serving providers
4
Cheapest input
$0.12 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Hyperbolic$0.12$0.301
Nebius$1.00$3.001
SambaNova$5.00$10.001
Azure$5.33$16.001

Price history

input + output $/1M since we started tracking
Input Output
Input down 98% since first tracked
$0.000$5.00$10.00$15.00$20.00Oct 23Dec 18Aug 22Jun 22$0.300$0.120

Cost calculator

estimate your monthly spend on this model
$48
estimated / month

Model IDs

copy the exact identifier for your platform
hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instructnebius/meta-llama/Meta-Llama-3.1-405B-Instructsambanova/Meta-Llama-3.1-405B-Instructazure_ai/Meta-Llama-3.1-405B-Instruct

Frequently asked questions

Meta Llama 3.1 405B Instruct pricing, context and availability

Is Meta Llama 3.1 405B Instruct still available?

Meta Llama 3.1 405B Instruct was retired on 2025-06-25. The pricing on this page is the last-known rate, kept for migration reference.

How much did Meta Llama 3.1 405B Instruct cost?

Meta Llama 3.1 405B Instruct's last-known pricing, before it was retired on 2025-06-25, was $0.12 per 1M input tokens and $0.30 per 1M output tokens.

What was the context window of Meta Llama 3.1 405B Instruct?

Meta Llama 3.1 405B Instruct had a 128K token context window and could return up to 128K output tokens.

What could Meta Llama 3.1 405B Instruct do?

Meta Llama 3.1 405B Instruct supported tool use and structured output.

Other Meta models

compare pricing across the Meta lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI