Hermes 3 Llama 3.1 70B API

Nous Research's Hermes 3 Llama 3.1 70B, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send hermes-3-llama-3.1-70b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: hermes-3-llama-3.1-70b
Maker: Nous Research
Context window: 131.1K tokens
Input price: $0.701 per million tokens
Output price: $0.701 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.701 input and $0.701 output per million tokens, $0.701 cache read per million tokens, 131.1K tokens of context

Scores

HLE: 4.0, #240 of 273
GPQA: 40.1, #235 of 250
LiveCodeBench: 18.8, #110 of 130
MMLU-Pro: 57.1, #119 of 133

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hermes-3-llama-3.1-70b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Hermes 3 Llama 3.1 70B?: Hermes 3 Llama 3.1 70B is a model from Nous Research.
How much does Hermes 3 Llama 3.1 70B cost?: Offers now ask $0.701 per million input tokens and $0.701 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Hermes 3 Llama 3.1 70B?: The largest offer takes 131,072 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Hermes 3 Llama 3.1 70B do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Hermes 3 Llama 3.1 70B support?: Text → Text.
Which providers serve Hermes 3 Llama 3.1 70B?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Hermes 3 Llama 3.1 70B?: Send "hermes-3-llama-3.1-70b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Hermes 3 Llama 3.1 70B listed?: The exchange first listed it on 10/14/2026. This is not its release date.