Visnea

Visnea API

Overview & quickstart

One HTTP API for the whole Visnea catalog: images, video, voice and chat. Authenticate with an API key and pay in USD from the same balance as the cabinet.

How the API works

Every request goes to a single base URL and is authorized with your key in a header. The format is JSON over HTTPS. One key covers every modality: generation, chat and the editor plugins.

Operations are priced in USD and debited from your account balance. Failed generations are refunded automatically.

Base URL
https://visnea-labs.com/v1

Older examples ended in /v1/usd — a temporary guard while balances moved from cherries to US dollars. The base is plain /v1 now; the old one keeps working too.

Quickstart

  1. Create an API key in the dashboard: API → Keys. The key is shown once — store it safely.

  2. Browse the model catalog and each model's parameters:

    curl
    curl https://visnea-labs.com/v1/models \  -H "Authorization: Bearer sk-visnea-..."

  3. Start a generation: model_id and prompt are enough.

    curl
    curl https://visnea-labs.com/v1/generate \  -H "Authorization: Bearer sk-visnea-..." \  -H "Content-Type: application/json" \  -d '{    "model_id": "z-image",    "prompt": "a neon city in the rain, cinematic light"  }'

  4. If the response comes back with status processing, poll the generation by id until the status becomes succeeded or failed.

    curl
    curl https://visnea-labs.com/v1/generations/GEN_ID \  -H "Authorization: Bearer sk-visnea-..."
Image/video links arrive in results[].url — download the result or use the URL directly.

Next steps

Authenticationsk-visnea-… keys, the Authorization header and safety rules.GenerateRequest body, per-modality params, response and polling.Connect your toolsClaude Code, Claude Desktop, Codex, OpenCode, Grok, Hermes, Cherry Studio; OpenAI- and Anthropic-compatible APIs.Models referenceLive catalog: params, prompt limits, formats.ErrorsThe {error, code} envelope and every error code.