Requesty
DeepInfra Inc. logo
DeepInfra Inc.

meta-llama/Meta-Llama-3.1-405B-Instruct

A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.

JSON schema
CompareDocs

Specifications

Context window131K tokens
Max outputN/A
API typechat
AddedFeb 6, 2025
Model IDdeepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct
Data retentionNo
Used for trainingNo
Provider location🇺🇸 US
Privacy policyDeepInfra Privacy Policy→

Benchmarks

Benchmarks haven't been published yet for this exact variant.

Some variants (region-specific deployments, highspeed tiers) share benchmarks with their base model. Check the base model page or the DeepInfra Inc. models overview.

Pricing

Prices updated July 24, 2026
Input / 1M
$0.80
Output / 1M
$0.80
Cache write
N/A
Cache read
N/A
Estimated cost
100K input + 10K output$0.0880
1M input + 100K output$0.88
10M input + 1M output$8.80

Requesty charges exactly what the upstream provider charges, no markup, no per-request fees. Prompt caching and smart routing can reduce effective cost by 30-80%.

Quickstart

Drop-in compatible with the OpenAI SDK. Change the base URL, swap in your Requesty API key, and set the model to deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

response = client.chat.completions.create(
    model="deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct",
    messages=[
        {"role": "user", "content": "Explain quantum computing in one paragraph."},
    ],
)

print(response.choices[0].message.content)

Other DeepInfra Inc. models

zai-org/GLM-5.1
203K ctx$1.05/1M
Coding 56
nvidia/Nemotron-3-Nano-30B-A3B
262K ctx$0.05/1M
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
262K ctx$0.10/1M
Coding 38
moonshotai/Kimi-K2.6
262K ctx$0.75/1M
Coding 62
gemma-4-31B-it
262K ctx$0.13/1M
deepseek-ai/DeepSeek-V4-Pro
1.0M ctx$1.30/1M
Coding 59

Frequently asked questions

How much does meta-llama/Meta-Llama-3.1-405B-Instruct cost?
meta-llama/Meta-Llama-3.1-405B-Instruct is priced at $0.80 per million input tokens and $0.80 per million output tokens when accessed via Requesty. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of meta-llama/Meta-Llama-3.1-405B-Instruct?
meta-llama/Meta-Llama-3.1-405B-Instruct has a context window of 131K tokens. That's roughly 174 words of input you can fit in a single prompt.
What can meta-llama/Meta-Llama-3.1-405B-Instruct do?
meta-llama/Meta-Llama-3.1-405B-Instruct supports structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use meta-llama/Meta-Llama-3.1-405B-Instruct with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct". The Quickstart above shows Python, JavaScript and cURL snippets.
Can I run meta-llama/Meta-Llama-3.1-405B-Instruct through Requesty?
Yes. meta-llama/Meta-Llama-3.1-405B-Instruct runs through Requesty's OpenAI-compatible API, served from DeepInfra Inc.. You do not host the model yourself: point base_url at Requesty, set the model to "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

Access meta-llama/Meta-Llama-3.1-405B-Instruct through Requesty

One API key, 600+ models, OpenAI-compatible. No markup on provider prices, automatic failover, and smart caching built-in.

All DeepInfra Inc. models