LLaMA 3.1 405B — pricing & specs
LLaMA 3.1 405B is a flagship model from Meta, at capability tier 7 of 8. Live $/M-token pricing and specs from the Mintok catalog.
$/M-token pricing
Open-weights model — no per-token list price. Size your self-host $/M-token →
Specifications
- Vendor
- Meta
- Family
- LLaMA
- Capability tier
- 7 / 8
- Size class
- FLAGSHIP
- Category
- GENERAL
- Parameters
- 405B total · 405B active (MoE)
- Context window
- 131,072 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference Cerebras Cerebras WSE-3 Turbo at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 7
Same capability tier, sorted by output price — the cheaper-capable options.
- Gemini 3.1 Pro PreviewGoogle$12/M out
- Kimi K3Moonshot$15/M out
- GPT-5.6 SolOpenAI$20/M out
- Claude Opus 4.8Anthropic$25/M out
- Claude Opus 4.7Anthropic$25/M out
- Claude Opus 4.6Anthropic$25/M out
FAQ
How much does LLaMA 3.1 405B cost per token?
LLaMA 3.1 405B is distributed as open weights — there is no per-token list price; you self-host it. Use the Mintok sizing report to estimate your $/M-token at your volume.
What is LLaMA 3.1 405B's context window?
LLaMA 3.1 405B supports a 131,072-token context window.
What capability tier is LLaMA 3.1 405B?
LLaMA 3.1 405B sits at capability tier 7 of 8 on the Mintok scale (FLAGSHIP size class).
Is LLaMA 3.1 405B open-source or proprietary?
LLaMA 3.1 405B is a proprietary model from Meta, accessed via API.
Put LLaMA 3.1 405B to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.