Hermes 3 Llama 3.1 70b API

Run nousresearch/hermes-3-llama-3.1-70b through FastInfra's OpenAI-compatible API. Pay per token, no subscription, routed to the cheapest available provider.

Read the docs
Pricing

Hermes 3 Llama 3.1 70b pricing

Billed per token used. Prices sync automatically from wholesale providers.

Direction Price per 1M tokens
Input$0.74
Output$0.74
Availability

Served by 2 providers

Requests route to DeepInfra by default (cheapest). Pin a specific provider with the :provider suffix.

Provider Upstream model ID
openrouter nousresearch/hermes-3-llama-3.1-70b
deepinfra NousResearch/Hermes-3-Llama-3.1-70B
Quickstart

Call Hermes 3 Llama 3.1 70b in 30 seconds

Works with any OpenAI SDK — change the base URL and API key only.

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")

response = client.chat.completions.create(
    model="nousresearch/hermes-3-llama-3.1-70b",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

curl https://api.fastinfra.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nousresearch/hermes-3-llama-3.1-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
FAQ

Hermes 3 Llama 3.1 70b — common questions

How much does the nousresearch/hermes-3-llama-3.1-70b API cost?

On FastInfra, nousresearch/hermes-3-llama-3.1-70b costs $0.735/1M input, $0.735/1M output tokens. Billing is per token used, with no subscription.

Is nousresearch/hermes-3-llama-3.1-70b compatible with the OpenAI SDK?

Yes. FastInfra exposes nousresearch/hermes-3-llama-3.1-70b through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.

Which providers serve nousresearch/hermes-3-llama-3.1-70b?

nousresearch/hermes-3-llama-3.1-70b is available from 2 provider(s): openrouter, deepinfra. Requests route to DeepInfra by default (cheapest); append ":provider" to the model ID to pin one.