Skip to content

Evanesca opens soon: this page shows how the chat will work.

API reference

Every operation of Evanesca's OpenAI-compatible API: its parameters, the call in cURL, Python, JavaScript and Go, its responses — and, for each one, where it runs and what it costs.

Catalogue checked on 20 Oct 2026

SoonOpening soon: what follows describes the service as it will work.

Base URL and key

https://evanesca.app/api/v1

Send your key in the Authorization: Bearer header; keys start with sk-eva-. The catalogue needs no key (authentication). OpenAI's official SDKs work as they are: give this URL to base_url (baseURL in JavaScript) (first request).

Endpoints

EndpointWhat it doesKey
POST/chat/completionsRuns a chat model; streaming supported.Required
POST/messagesThe same chat models in Anthropic's Messages format; streaming supported.Required
POST/messages/count_tokensEstimates, for free, the input tokens of a Messages request.Required
GET/modelsLists the catalogue: chat, embedding and image models.None
GET/models/{model}Returns one model — what models.retrieve() calls in the OpenAI SDKs.None
POST/embeddingsTurns text into vectors.Required
POST/images/generationsGenerates images from a text prompt.Required
POST/images/editsGenerates portraits from 1 to 4 face photos.Required

Formats served

Evanesca serves OpenAI's Chat Completions format and, on the same models, Anthropic's Messages format (POST /messages, for Claude Code and Anthropic's SDKs). It does not serve OpenAI's newer Responses API (/responses): a tool that defaults to it must be switched to chat completions — the integrations page says where.

Errors

Errors come back as JSON in OpenAI's shape: an error object with a readable message and a stable type (every status).

402 · application/json
{
  "error": {
    "message": "Insufficient credit balance. Add credit to your account to continue.",
    "type": "insufficient_credit"
  }
}