AI Model Watch
Models / Meta

Llama 3.1 405B Instruct

GA

Open-weight, text-only, 405B dense, 128k context. License: Llama 3.1 Community License. Released 2024-07-23 alongside 8B/70B. Hosted price NOT reliably extractable in this pass: OpenRouter slug is 'meta-llama/llama-3.1-405b-instruct' (131k ctx) but the per-token figures did not render; Together AI reportedly does NOT serve 405B on its serverless API (their 405B model page states it is not available serverless), and third-party reports put serverless 405B around $3.00-$3.50 per 1M elsewhere (unverified). Prices left null rather than guessed. Source URL repointed on 2026-09-20 to Meta's own Llama-3.1-405B-Instruct card; it previously pointed at the Llama-3.1-8B-Instruct card, which is a different model in the same collection. That card, re-read first-party the same day, states Model Release Date July 23, 2024, a pretraining cutoff of December 2023 and a 128k context length — the three fields carried here. Tail restored 2026-09-20: this note was cut at exactly 600 characters by an ingest truncation present since the initial commit, and the lost text is unrecoverable from git, so the ending is rewritten from a first-party re-read rather than restored (LEARNINGS #135).

Llama 3.1 405B Instruct by Meta is tracked live in our LLM catalog, with a 128K (128.000-token) context window. It is generally available (GA), with a knowledge cutoff of Dec 2023. Its weights are publicly downloadable, so it can be self-hosted on your own infrastructure.

Last verified: 26 Sep 2026 · sourced from official provider documentation

Provider
Meta
Status
GA
Input price
—
Output price
—
Cached input
—
Blended price
—
Context window
128.000 tokens (128K)
Max output
—
Modality
text
Open weights
Yes — self-hostable
Knowledge cutoff
2023-12
Released
23 Jul 2024
API string
meta-llama/Llama-3.1-405B-Instruct

Source: Meta official documentation ↗

See also

Explore more

All Meta models→

Prices, context windows and lifecycle status for every Meta model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Llama 3.1 405B Instruct — questions & answers

What is the context window of Llama 3.1 405B Instruct?

Llama 3.1 405B Instruct has a 128.000-token context window (128K).

Is Llama 3.1 405B Instruct deprecated?

No — Llama 3.1 405B Instruct is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does Llama 3.1 405B Instruct support image or vision input?

Our catalog lists Llama 3.1 405B Instruct's modalities as text; image/vision input is not among them.

Can I self-host Llama 3.1 405B Instruct?

Yes — Llama 3.1 405B Instruct is an open-weight model: its weights are publicly downloadable, so you can run it on your own infrastructure (subject to its license) instead of only calling Meta's API.

What is the API model string for Llama 3.1 405B Instruct?

The API model identifier for Llama 3.1 405B Instruct is "meta-llama/Llama-3.1-405B-Instruct" when calling Meta's API.

What is Llama 3.1 405B Instruct's knowledge cutoff?

Llama 3.1 405B Instruct's training knowledge cutoff is Dec 2023.