NAnano-gpt

POST /v1/memory

Compress a conversation with Context Memory and return compressed messages and usage (no model inference)

Request

  • Base URL
    https://api.nano-gpt.com/api
  • URL
    https://api.nano-gpt.com/api/v1/memory
  • Auth
    • HTTP bearer
    • or API key in header x-api-key

Request body

expiration_daysinteger

Retention in days (1..365). Defaults to 30 if not provided.

model_context_limitinteger

Target context size for compression (minimum enforced 10,000)

Response

Memory compression response

Changes

No recorded changes to this operation across all 2 revisions of this API.