How much does Llama 3.1 405B cost?

Meta has not published per-token API pricing for Llama 3.1 405B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Llama 3.1 405B's context window?

Llama 3.1 405B supports a context window of 128K tokens.

Is Llama 3.1 405B open source?

Llama 3.1 405B ships with open weights under the Llama 3 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Llama 3.1 405B released?

Llama 3.1 405B was released on Jul 23, 2024 by Meta.

How much does Llama 3.1 405B cost?

Meta has not published per-token API pricing for Llama 3.1 405B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Llama 3.1 405B's context window?

Llama 3.1 405B supports a context window of 128K tokens.

Is Llama 3.1 405B open source?

Llama 3.1 405B ships with open weights under the Llama 3 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Llama 3.1 405B released?

Llama 3.1 405B was released on Jul 23, 2024 by Meta.

Open weightsMetaopentext

Llama 3.1 405B

First open-weight model to match GPT-4-class quality on standard benchmarks.

UpdatedApr 30, 2026

Quick facts

Released: Jul 2024
Context: 128K tokens
Output / 1M: Pricing not published
License: Llama 3 Community License

About Llama 3.1 405B

Llama 3.1 405B was the headline release of mid-2024, the first openly-released model that matched closed frontier models on MMLU and coding benchmarks. It made open-weight serving a real production option for the first time.

Benchmarks

Published scores from Meta's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval

89.0

Python coding pass@1

MMLU

88.6

Broad academic knowledge

GPQA

Graduate-level reasoning

SWE-bench

Real software-engineering tasks

MMLU88.6
HumanEval89.0

Capabilities

Strengths

Historic milestone for open-weight quality
Wide hosting availability

Tracked weaknesses

Heavy to serve
Superseded by Llama 4 405B

Pricing

Per-million-token rates as published by Meta.

Per-token pricing not yet published for Llama 3.1 405B. Check the official provider site for current tiers.

Call Llama 3.1 405B from your code

Drop-in snippet for the Meta SDK. Set your API key in the environment and run.

typescript

import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "llama-3-1-405b",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Compare Llama 3.1 405B with…

Frequently asked

How much does Llama 3.1 405B cost?
Meta has not published per-token API pricing for Llama 3.1 405B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.
What is Llama 3.1 405B's context window?
Llama 3.1 405B supports a context window of 128K tokens.
Is Llama 3.1 405B open source?
Llama 3.1 405B ships with open weights under the Llama 3 Community License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.
When was Llama 3.1 405B released?
Llama 3.1 405B was released on Jul 23, 2024 by Meta.

Friday digest

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.