3. Writing blog articles
One topic, one article, in the background.
Permissions: blog:generate
- 1Your system
GET /v1/blog/modelsOptional: the models that can write. Without a choice, the default is used.
- 2Your system
POST /v1/blog/generationsSend "prompt" (up to 2,000 characters), and if you want "provider" and "model". Response 202 with an id, status pending. An insufficient balance or no model is refused right then.
- 3Tekomata
AI writes. Done: webhook blog_generation.succeeded with generationId. Failed: blog_generation.failed with errorCode.
- 4Your system
GET /v1/blog/generations/{id}Get the article: ordered blocks (h1 title, h2, h3, p), the model that wrote it, and its cost.
- POST /v1/blog/generate is still there if you want to wait for the answer directly in one call.
- The content is plain text, never HTML or markdown.