HomeAI Models › Llama 3.1 405B

Llama 3.1 405B API Pricing

Open-weight · 128K context · Available from 7 hosts. Cheapest: Novita at $0.72 input / $0.72 output per 1M tokens.

Llama 3.1 405B price by host (7 providers)

HostInput /1MOutput /1MIn+Out
Novita$0.72$0.72$1.44
DeepInfra$0.765$0.765$1.53
Groq$0.855$0.855$1.71
Meta$0.9$0.9$1.8
Together$0.9$0.9$1.8
OpenRouter$0.9$0.9$1.8
Fireworks$0.945$0.945$1.89

Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.

Llama 3.1 405B cost calculator

Frequently asked

How much does Llama 3.1 405B cost per 1M tokens?

Llama 3.1 405B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens at its cheapest host (Novita).

What is Llama 3.1 405B's context window?

Llama 3.1 405B supports a context window of about 128K tokens. Remember every token in the context is billed on each call.

Where is Llama 3.1 405B cheapest to run?

Across 7 hosts, Novita is currently cheapest at $0.72/$0.72 per 1M tokens, versus Fireworks at $0.945/$0.945. Prices change often — use the comparison table above.

Related models

Compare all 387 models →