impulse

Llama3.1 405B Instruct

Open weights
API id llama3.1-405b-instruct-fp8
Input / 1M
$0.80
at Lambda AI
Output / 1M
$0.80
at Lambda AI
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

List prices at Lambda AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.80$0.80

What it costs a month

At Lambda AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$300
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$413
  • Coding agent1,000 requests a day, 40K in / 2K out$1,008
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,112
Use your own numbers

Where to run it

2 hosts serve Llama3.1 405B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Lambda AIInference
llama3.1-405b-instruct-fp8
$0.80 / $0.80
meta.llama3-1-405b-instruct-v1:0
$2.40 / $2.40
+200% vs headline
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
us
us.meta.llama3-1-405b-instruct-v1:0
$2.40 / $2.40
+200% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Parallel tool calls
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Lambda AI.

Smaller Meta models

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    42% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    75% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    75% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    67% less

Open-weight picks

  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    1% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    14% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    20% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    40% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedLlama 3.1 405B InstructLatest$3.00 / $3.00
  2. UndatedLlama3.1 405B InstructThis page$0.80 / $0.80
  3. UndatedLlama3 405B InstructNot listed

Call it

Using Lambda AI's API.

Python
from litellm import completion

response = completion(
    model="lambda_ai/llama3.1-405b-instruct-fp8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama3.1 405B Instruct cost?

On Lambda AI, Llama3.1 405B Instruct costs $0.80 per million input tokens and $0.80 per million output tokens.

Which APIs offer Llama3.1 405B Instruct?

Llama3.1 405B Instruct runs on 2 APIs: Lambda AI and Amazon Bedrock.

What is Llama3.1 405B Instruct's context window?

131K tokens, with up to 131K tokens in one reply.

Is Llama3.1 405B Instruct being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Llama3.1 405B Instruct?

Yes. Llama 3.1 405B Instruct is the newest model in this line.

What are cheaper alternatives to Llama3.1 405B Instruct?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (84% less), GPT-5.4 Nano on OpenAI (42% less), Claude Haiku 5.5 on Anthropic (75% less) and DeepSeek V4 Pro on CLF AI Gateway (1% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Llama3.1 405B Instruct's API model id?

Use llama3.1-405b-instruct-fp8 with Lambda AI. Other hosts use their own ids: meta.llama3-1-405b-instruct-v1:0 on Amazon Bedrock.

Sources

Raw catalog entry for llama3.1-405b-instruct-fp8 on Lambda AI
{
  "input_cost_per_token": 8e-7,
  "litellm_provider": "lambda_ai",
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 8e-7,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}