Is Llama 3.1 405B Instruct Turbo or GPT-5.1 Codex Max cheaper?

Llama 3.1 405B Instruct Turbo is cheaper on output tokens ($3.50 vs $10.00 per 1M).

Which has the larger context window, Llama 3.1 405B Instruct Turbo or GPT-5.1 Codex Max?

GPT-5.1 Codex Max has the larger context window (400K tokens).

Llama 3.1 405B Instruct Turbo vs GPT-5.1 Codex Max

Llama 3.1 405B Instruct Turbo is cheaper on output tokens, while GPT-5.1 Codex Max offers a larger context window. Choose Llama 3.1 405B Instruct Turbo or GPT-5.1 Codex Max based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 3.1 405B Instruct Turbo	GPT-5.1 Codex Max
Provider	Abacus	Abacus
Input / 1M tokens	$3.50	$1.25
Output / 1M tokens	$3.50	$10.00
Context window	128K	400K
Parameters	—	—
Open weights	Yes	No
Released	Jul 2024	Nov 2025

Llama 3.1 405B Instruct Turbo details →GPT-5.1 Codex Max details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.