No KYC
No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.
Navigation
MODEL REFERENCE
Hermes 4 70B
Creative conversation, roleplay and reasoning with configurable instructions, published by Nous Research.
No added content filters
WeightsAPI adds no content filter at the gateway. A model’s own training can still lead it to refuse a request.
INPUT / 1M$0.13
OUTPUT / 1M$0.40
SERVICE CONTEXT*128K
MEASURED SPEED— not measured
API model IDNousResearch/Hermes-4-70B
Published context131,072 tokens
QuantizationNot verified
LicenseMeta Llama Community ↗
Best for#
Creative writing, roleplay and assistants that combine conversation with reasoning or structured outputs. Nous Research emphasizes configurable behavior and reduced refusals.
Choose another model when#
You need image or audio input, or a smaller model for tighter hardware budgets. Hermes 4 70B is text-only, and its published positioning does not guarantee answers without refusals.
Deployment details#
The published configuration supports 131,072 positions and the original weights use BF16. Confirm WeightsAPI’s serving context and precision for the deployment. Measured throughput is not available. Validate reasoning and tool calls before enabling them.
Shared inference is billed at the input and output prices shown on this page, in USD per million tokens. The same rates apply throughout WeightsAPI’s service context window; no cache or batch discount applies to this standard rate. Confirm the deployed context before using the listed 131,072-token service ceiling. See pricing and service status before use.
License and provenance#
Nous publishes these weights as a derivative of Llama 3.1 70B. The model card labels its license llama3; the repository has no standalone license file clarifying that label. Review the underlying Llama 3.1 terms, including attribution and use conditions.
Call this model#
Once a priced deployment is enabled, use NousResearch/Hermes-4-70B with Chat Completions. WeightsAPI adds no gateway content filter. Refusals may still occur, and the published model's chat template and supported features must match the serving configuration.
Sign-in, one confirmed top-up of at least USD 100 and enough available credit are required for AI access. Published prices do not activate a model: check service status for deployment availability.
Request example
curl https://weightsapi.com/v1/chat/completions \
-H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "NousResearch/Hermes-4-70B",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'