Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All DeepInfra models
DeepInfra
DeepInfraFrontier

Llama 3.1 405B (DI)

Serverless

Largest dense Llama. Used as a quality benchmark for open weights — heavy to run, often hosted via Together / DeepInfra / Cerebras.

Llama 3.1 405B (DI) is a frontier AI model from DeepInfra. It costs $0.800 per million input tokens and $0.800 per million output tokens (blended $0.800/M), with a 128K-token context window.

Profile inherited from upstream Llama 3.1 405B ↗ — this is a hosted variant of the same open-weights model.

Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.800/M
per million input tokens
OUTPUT
$0.800/M
per million output tokens
BLENDED 70/30
$0.800/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Top open-weights quality
  • Permissive license
  • Strong reasoning
Typical use cases
  • Open-weights quality ceiling
  • Synthetic data generation
  • Distillation source
Benchmarks
vs. best public score
Scores inherited from Llama 3.1 405B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU88%
Multitask academic knowledge across 57 subjects.
GPQA Diamond51%
Graduate-level science questions, "Google-proof".
MATH73%
High-school competition math problems.
HumanEval89%
Python function synthesis from docstrings.
LMArena Elo1290 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from DeepInfra
See all 11 →
Llama 3.3 70B (DI)
Serverless · 128K ctx
in $0.230/Mout $0.400/M
Llama 3.1 70B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Mistral 7B (DI)
Nano · 32K ctx
in $0.070/Mout $0.070/M
Mixtral 8x7B (DI)
MoE · 32K ctx
in $0.240/Mout $0.240/M
DeepSeek-R1 (DI)
Reasoning · 64K ctx
in $0.550/Mout $2.190/M
Qwen2.5-72B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Frequently asked questions

How much does Llama 3.1 405B (DI) cost?

Llama 3.1 405B (DI) costs $0.800 per million input tokens and $0.800 per million output tokens, for a blended reference rate of $0.800 per million tokens.

What is Llama 3.1 405B (DI)'s context window?

Llama 3.1 405B (DI) supports up to 128K tokens of context (128,000 tokens).

What is Llama 3.1 405B (DI) best for?

Llama 3.1 405B (DI) is well suited to Top open-weights quality, Permissive license and Strong reasoning.

Who makes Llama 3.1 405B (DI)?

Llama 3.1 405B (DI) is developed and served by DeepInfra.