Llama 3.1 405B (Fireworks)

This model is not part of the weekly automatic sync. The figures below were confirmed on 2026-08-13.

Fireworks AI Optimized Llama 3.1 405B. Low-cost large model inference

Llama 3.1 405B (Fireworks) — Fireworks AI. Context window 131,072 tokens. API pricing (per 1M tokens): Input $3, Output $3. License: Open-Weight.

Benchmarks · API pricing (per 1M tokens)

ProviderFireworks AI
TierFrontier
Context window131,072 tokens
Max output8,192 tokens
LicenseOpen-Weight
API pricing (per 1M tokens) · Input$3
API pricing (per 1M tokens) · Output$3
Compare in the full catalog