Question 1

What is Llama 3.1 405B?

Accepted Answer

Llama 3.1 405B is a large language model from Meta, released on 23 July 2024. The original "open-source GPT-4" — largest publicly-released weights.

Question 2

When was Llama 3.1 405B released?

Accepted Answer

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

Question 3

How much does Llama 3.1 405B cost?

Accepted Answer

Llama 3.1 405B costs $2.70 per 1 million input tokens and $2.70 per 1 million output tokens via Meta’s API. At a typical 3:1 input/output ratio the blended cost works out to about $2.70 per 1M tokens.

Question 4

How smart is Llama 3.1 405B?

Accepted Answer

Llama 3.1 405B scores 64 out of 100 on our intelligence index — a capable mid-tier composite of MMLU, MMLU Pro, GPQA, MATH and HumanEval benchmark scores. That places it #16 of 22 language models we track.

Question 5

What is the context window of Llama 3.1 405B?

Accepted Answer

Llama 3.1 405B has a 128k-token context window — roughly 96,000 words of text. That’s what you can fit into a single request (your prompt plus all uploaded documents and the model’s response combined).

Question 6

What is Llama 3.1 405B best for?

Accepted Answer

Llama 3.1 405B is most useful for research, distillation and custom fine-tunes. Its key strengths are open weights at frontier scale and no usage limits.

Question 7

How fast is Llama 3.1 405B?

Accepted Answer

Llama 3.1 405B generates around 32 output tokens per second with a typical time-to-first-token of 700 ms on the major API providers. Reasoning models that "think" before answering will appear slower on tokens-per-second since they spend time on internal chain-of-thought.

Question 8

Is Llama 3.1 405B better than Llama 3.3 70B?

Accepted Answer

Llama 3.3 70B scores higher on our intelligence index (66 vs 64), so on the hardest tasks Llama 3.3 70B typically wins. Llama 3.1 405B can still be the better pick on price, latency or specific capabilities. See our full Llama 3.1 405B vs Llama 3.3 70B comparison at /ai-models/compare/llama-3-3-70b-vs-llama-3-1-405b/.

Question 9

What is the best alternative to Llama 3.1 405B?

Accepted Answer

The closest alternatives to Llama 3.1 405B are Llama 3.3 70B, DeepSeek R1 and DeepSeek V3. Each shares most of Llama 3.1 405B’s use-cases — pick by price, context window or specific capability rather than headline intelligence.

Question 10

Is Llama 3.1 405B open source?

Accepted Answer

Yes. Llama 3.1 405B is open-source — the weights are publicly available, and you can self-host it or use a hosted provider (Together, Fireworks, Groq, Replicate). Some open-source licenses include usage caveats; check the model’s license file before deploying.

Question 11

Can I use Llama 3.1 405B for free?

Accepted Answer

Yes. Llama 3.1 405B is open-weights, so you can download it and run it locally for free (just your hardware cost). Hosted access is paid via providers like Together, Fireworks, Groq and Replicate.

Llama 3.1 405B

At a glance

Benchmark scores

Models you should also evaluate

More from Meta

Llama 3.1 405B — frequently asked questions

Need help choosing between models?