Meta logo

Llama 3.1 405B Instruct

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 3.1 405B Instruct is Meta's language model with a 131K context window and up to 16K output tokens, available from 7 providers, starting at $0.12 / 1M input and $0.3 / 1M output. Meta's 405B instruction-tuned LLM optimized for following complex instructions, with FP8 quantization for efficient large-scale inference.
Specifications
Canonical IDmeta-llama-3-1-405b-instruct
TypeLanguage
StatusDeprecated
CreatorMetaMeta
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters405B
Release Date · 2 years ago
Deprecation Date
Benchmarks
Intelligence Index
#417
Math Index
#262
MMLU-Pro
#204
GPQA
#395
HLE
#482
LiveCodeBench
#220
AIME
#103
IFBench
#274
Time to First Token
#195
SciCode
#324
MATH-500
#140
AIME 2025
#262
LCR
#334
TerminalBench Hard
#252
TAU2
#346
Output TPS
#448

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
meta.llama3-1-405b-instruct-v1:0
$2.40$2.40
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct
$3.00$3.00
Google Vertex AI logo
Google Vertex AI
vertex_ai/meta/llama-3.1-405b-instruct-maas
$5.00$16.00
Hyperbolic logo
Hyperbolic
hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct
$0.12$0.3
Lambda logo
Lambda
lambda_ai/llama3.1-405b-instruct-fp8
$0.8$0.8
Oracle Cloud (OCI) logo
Oracle Cloud (OCI)
oci/meta.llama-3.1-405b-instruct
$10.68$10.68
Together AI logo
Together AI
together_ai/meta-llama/Llama-3.1-405B-Instruct
$3.50$3.50

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3.1 405B Instruct, ranked by cheapest on-demand price. The model needs about 972 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_ND96is_MI300X_v5Azure8× AMD Instinct MI300X GPU (192GB)1536 GB$48.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
p5en.48xlargeAWS8× H2001128 GB$63.30/hr
5 more instances can run Llama 3.1 405B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.120$0.200Deprecated
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.020$0.020Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Current
Llama 3.1 8B Instruct200K$0.020$0.030Deprecated
Llama 3.1 70B Instruct131K$0.100$0.100Deprecated
Llama 3.1 70B128K$0.360$0.360Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Deprecated
Llama 3 8B Instruct32K$0.030$0.040Deprecated
Llama 3.1 Tulu3 405B————Available

Model IDs

accounts/fireworks/models/llama-v3p1-405b-instruct
azure_ai/Meta-Llama-3.1-405B-Instruct
databricks/databricks-meta-llama-3-1-405b-instruct
fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct
hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct
lambda_ai/llama3.1-405b-instruct-fp8
llama-3-1-instruct-405b
meta-llama-3-1-405b-instruct
meta-textgeneration-llama-3-1-405b-instruct-fp8
meta.llama3-1-405b-instruct-v1:0
nebius/meta-llama/Meta-Llama-3.1-405B-Instruct
oci/meta.llama-3.1-405b-instruct
sambanova/Meta-Llama-3.1-405B-Instruct
together_ai/meta-llama/Llama-3.1-405B-Instruct
together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
us.meta.llama3-1-405b-instruct-v1:0
vertex_ai/meta/llama-3.1-405b-instruct-maas