Skip to content
Llama 3.1 405B Instruct Bf16 logo

Llama 3.1 405B Instruct Bf16

Meta

Key facts · verified Oct 29, 2026

Llama 3.1 405B Instruct Bf16 is a Meta model released on 23 Jul 2024. Its API price is $4 per million input tokens and $4 per million output tokens. Its context window is 128K tokens. It ranks #245 on LMArena's text leaderboard (Elo 1335, read 1 Nov 2026). Source: ai.meta.com.

Llama 3.1 405B Instruct BF16 is the BF16 build of Meta's Llama 3.1 405B instruction-tuned model, released on July 23, 2024 with open weights under the Llama 3.1 Community licence, so it can be self-hosted. Meta's model card lists a 128K-token context window. arena.ai lists pricing of $4 per million input tokens and $4 per million output tokens, not confirmed as first-party. On LMArena's text leaderboard: 1335 Elo (rank 245).

Pricing & specs checkedSource: vendor documentation · checked Oct 29, 2026LMArena: 1335 Elo (rank 245) · source · retrieved Nov 1, 2026
Pricing

$4 / $4 per million tokens

Context

128K tokens

LMArena Elo

1335

LMArena rank

#245

Full Specifications

$4 / $4 per million tokens
Identity
DeveloperMeta
ReleasedJul 2024
LicenceLlama 3.1 Community
Self-hostableYes
Cost
Blended $/1M tokensinput × 0.75 + output × 0.25$4.000 / 1M tokens
Input price$4.000 / 1M tokens
Output price$4.000 / 1M tokens
Capacity
Context window128K tokens
Measured quality
LMArena Elo1335 (checked Nov 2026)
LMArena rankRank 245
Elo per dollarLMArena Elo ÷ blended $/1M tokens334