How much does Llama 3.1 405B Instruct cost?

Llama 3.1 405B Instruct costs $3.00 per 1M input tokens and $3.00 per 1M output tokens. Prices are sourced from official Fireworks AI documentation.

Is Llama 3.1 405B Instruct available via API?

Yes. Llama 3.1 405B Instruct is available via the Fireworks AI API. Tickerr monitors its uptime and latency every 5 minutes.

Tickerr / Pricing / Fireworks AI / Llama 3.1 405B Instruct

Operational· provider status page

Input

$3.00

Output

$3.00

Cached input

—

Batch input

—

Effective from Jan 1, 2025. Source: official provider documentation.

Estimated monthly cost · 70% input / 30% output split

cheapestAccounts Fireworks Models Gpt Oss 20b$0.139

Accounts Fireworks Models Deepseek V4 Flash$0.182

Accounts Fireworks Models Minimax M2p7$0.570

Accounts Fireworks Models Kimi K2p6$1.86

Accounts Fireworks Models Kimi K2p7 Code$1.86

Llama 3.1 405B Instruct$3.00