Hermes Medium API

Nanogpt's Hermes Medium, 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.

Facts

Model name
hermes-medium
Maker
Nanogpt
Context window
1M tokens
Input price
$0.600 per million tokens
Output price
$1.100 per million tokens
Providers
1 independent provider
Regions
us

Providers

Request

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

Questions

What is Hermes Medium?
Hermes Medium is a model from Nanogpt.
How much does Hermes Medium cost?
Offers now ask $0.600 per million input tokens and $1.100 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 Medium?
The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Hermes Medium 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 Medium support?
Text → Text.
Which providers serve Hermes Medium?
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 Medium?
Send "hermes-medium" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Hermes Medium listed?
The exchange first listed it on 10/5/2026. This is not its release date.

Related pages