Meta: Llama 3.1 405B (base)
Analysis Summary
Llama 3.1 405B is Meta's largest open-weight model from the Llama 3.1 generation, with an intelligence index of 8.5 and strong MMLU Pro and GPQA scores. As a base model, it lacks tool use, function calling, and vision support, which limits its direct applicability to business workflows without additional fine-tuning or wrapping.
For businesses, it is best suited to teams with the infrastructure to fine-tune or adapt large open-weight models for specific tasks. Its reasoning capability is competitive with mid-2024 proprietary models, but the 32K context window is a significant constraint for long-document analysis. The absence of agentic tooling means it cannot be dropped into agent pipelines without modification.
At $4 per million tokens for both input and output, it is not cheap for an open-weight model, especially given the infrastructure costs of running 405B parameters. Teams with specific open-weight requirements and the capability to adapt base models will find it powerful; others should consider instruction-tuned alternatives.
Assessed June 17, 2026
Editorial notes
Llama 3.1 405B base from Meta delivers strong reasoning and a broad benchmark profile, but lacks tool use and vision support, and its 32K context window limits long-document applications.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Meta: Llama 3.1 405B (base) compares
Meta: Llama 3.1 405B (base) ranks #256 of 380 AI models we track for overall intelligence, #241 of 292 for agentic tasks. Its 33K-token context window is larger than 31% of the models we list. At $4.00 per million input tokens it is cheaper than 7% of comparable models.
About Meta: Llama 3.1 405B (base)
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version. It has demonstrated strong performance compared to leading closed-source models in human evaluations. Usage of this model is subject to Meta's Acceptable Use Policy.
Architecture Detail
| Instruct Type | none |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Meta: Llama 3.1 405B (base) stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
meta-llama/llama-3.1-405b
|
| Provider | meta-llama |
| Model Family | Llama 3 |
| Release Date | August 2, 2024 |
| Context Length | 32,768 tokens |
| Max Completion | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $4.00 | $0.004000 |
| Output | $4.00 | $0.004000 |
Leaderboard Categories
External Resources
Frequently asked questions about Meta: Llama 3.1 405B (base)
How much does Meta: Llama 3.1 405B (base) cost?
Meta: Llama 3.1 405B (base) costs $4.00 per million input tokens and $4.00 per million output tokens.
What is the context window of Meta: Llama 3.1 405B (base)?
Meta: Llama 3.1 405B (base) has a context window of 32,768 tokens (33K).
Who created Meta: Llama 3.1 405B (base)?
Meta: Llama 3.1 405B (base) is developed by Meta and was released on August 2, 2024.
