> ## Documentation Index > Fetch the complete documentation index at: https://radarkit.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create article > Has the Content agent write an article for one of your prompts. The agent reads the pages AI models cite for that prompt, builds an outline and writes in your brand's voice. The draft lands in your editor. Writing takes a few minutes, so keep the run `id` and poll Get article run. If an article for the same prompt, type and keyword is already being written or is done, you get that run back with `meta.reused: true` and no content credit is spent. Send `force: true` to write another. Articles started here appear in the project's Agents section on a sheet named API. Cost: 1 API credit plus 1 AI content credit from the project owner. Nothing is charged when the request is refused. Limits: 10 calls per minute per key. Needs: Agents. Your seat must be allowed to manage content. ## OpenAPI ````yaml /openapi.yaml post /projects/{project}/content/articles openapi: 3.1.0 info: title: Radarkit API version: 1.0.0 summary: Your AI visibility data, outside the dashboard. description: > Radarkit tracks how AI assistants answer the questions your customers ask, and what each answer says about your brand. This API gives you that data as JSON. Every request needs an API key in the `Authorization` header. Every response has the same shape: `data`, `meta`, `credits` and `request_id`. Most calls cost 1 API credit. Heavier calls cost 2. Exports spend Export rows instead, one per row. contact: name: Radarkit support email: mail@radarkit.ai url: https://radarkit.ai servers: - url: https://api.radarkit.ai/v1 description: Production security: - bearerAuth: [] tags: - name: Account description: Your key, your plan and both balances. Free. - name: Projects description: One project is one brand or website. Every other call needs a project id. - name: Topics description: Topics group prompts. Every prompt belongs to one topic. - name: Prompts description: The questions Radarkit asks every AI model on a schedule. - name: Visibility description: The daily visibility score per model, precomputed. - name: Responses description: One row per AI answer, with everything Radarkit found in it. - name: Sources description: The web pages AI answers cite or consult. - name: Competitors description: Who the answers recommend and how often. - name: Rankings description: Recommended domains with their position in the answer. - name: Query fanout description: The web searches a model ran before answering, one row per answer. - name: Web search description: How often the models searched and what they searched for, summarised. - name: Sentiment description: How the answers talk about your brand. - name: Exports description: > Thousands of rows as one gzip file. Four calls in order: estimate, create, poll, download. Estimate is free and returns the exact row count. Create charges that many Export rows and queues the job. Poll the export until its status is `ready`. Download follows a redirect to a signed link that works for 30 minutes. Files are kept for 7 days. - name: Content description: Have the Content agent write an article for a prompt, then poll the run. paths: /projects/{project}/content/articles: post: tags: - Content summary: Create article description: > Has the Content agent write an article for one of your prompts. The agent reads the pages AI models cite for that prompt, builds an outline and writes in your brand's voice. The draft lands in your editor. Writing takes a few minutes, so keep the run `id` and poll Get article run. If an article for the same prompt, type and keyword is already being written or is done, you get that run back with `meta.reused: true` and no content credit is spent. Send `force: true` to write another. Articles started here appear in the project's Agents section on a sheet named API. Cost: 1 API credit plus 1 AI content credit from the project owner. Nothing is charged when the request is refused. Limits: 10 calls per minute per key. Needs: Agents. Your seat must be allowed to manage content. operationId: createArticle parameters: - $ref: '#/components/parameters/project' requestBody: required: true content: application/json: schema: type: object required: - prompt_id - keyword properties: prompt_id: type: integer description: The prompt the article targets. article_type: type: string enum: - blog_post - listicle - comparison - alternatives - faq - first_person_review description: >- The article format. Default is the format the cited pages use most. keyword: type: string maxLength: 255 description: >- The keyword the article should rank for, as in the Create Content dialog. country: type: string minLength: 2 maxLength: 2 description: >- Two-letter country the article should rank in; drives the SERP research. Default is the project region. language: type: string enum: - en - da - de - es - fr - it - pt - nl - pl - ru description: >- Language of the SERP research and of the article. Default is English. additional_details: type: string maxLength: 1500 description: Instructions for the writer. force: type: boolean description: >- Write a new article even if one for the same prompt, type and keyword exists. sheet: type: string maxLength: 80 description: >- Name of the content sheet the article row goes on, under Agents → Sheets. Default is the project's "API" sheet. A sheet holds 50 rows; a full one rolls over to "Name 2" and `meta.sheet` tells you where the row landed. example: prompt_id: 2048 article_type: comparison keyword: best crm for startups country: US language: en additional_details: Lead with pricing. Mention the free tier for teams under 3. responses: '202': description: The run has started. content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/ContentRun' meta: type: object properties: project: type: string reused: type: boolean description: >- True when an existing run was returned instead of starting a new one. ai_content_credits_remaining: type: integer next_step: type: string credits: $ref: '#/components/schemas/Credits' request_id: $ref: '#/components/schemas/RequestId' example: data: id: 551 project: 64f1a2b3c4d5e6f708192a3b status: processing current_step: creating error: null retryable: false prompt: id: 2048 article: id: 812 title: null keyword: best crm for startups article_type: comparison write_mode: ai status: draft crawl_status: pending outline_status: pending word_count: null scores: radarkit: null seo: null geo: null readability: null editor_url: >- https://radarkit.ai/dashboard/64f1a2b3c4d5e6f708192a3b/content/812 created_at: '2026-09-03T10:30:00+00:00' updated_at: '2026-09-03T10:30:00+00:00' started_at: '2026-09-03T10:30:00+00:00' completed_at: null meta: project: 64f1a2b3c4d5e6f708192a3b reused: false ai_content_credits_remaining: 19 next_step: >- Poll GET /v1/content/runs/{id} until status is completed, then open editor_url or fetch the body with include=body. credits: charged: 1 remaining: 2941 request_id: req_01j9x519n0o1p2q3r4s5t6u7v8 '401': $ref: '#/components/responses/Unauthenticated' '402': description: >- `INSUFFICIENT_CONTENT_CREDITS`: the owner has no AI content credits. `INSUFFICIENT_CREDITS`: no API credits left. `PLAN_INACTIVE` or `OWNER_PLAN_INACTIVE`: a plan is not active. content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: >- `SCOPE_MISSING`: the key has no Agents permission. `PROJECT_FORBIDDEN`: the key cannot reach this project. `PERMISSION_DENIED`: your seat cannot manage content. content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: >- `PROJECT_NOT_FOUND`: no project with that id. `PROMPT_NOT_FOUND`: no active prompt with that id in this project. content: application/json: schema: $ref: '#/components/schemas/Error' '422': description: >- `VALIDATION_FAILED`: a field is wrong, `details` says which. `CONTENT_REJECTED`: the Content agent refused the request, the message says why. content: application/json: schema: $ref: '#/components/schemas/Error' '429': $ref: '#/components/responses/RateLimited' components: parameters: project: name: project in: path required: true description: The project id. 24 characters. From List projects. schema: type: string pattern: ^[0-9a-f]{24}$ example: 64f1a2b3c4d5e6f708192a3b schemas: ContentRun: type: object properties: id: type: integer project: type: string status: type: string enum: - processing - completed - failed - cancelled current_step: type: - string - 'null' error: type: - string - 'null' retryable: type: boolean description: True for failed and cancelled runs. prompt: type: object properties: id: type: - integer - 'null' article: type: - object - 'null' properties: id: type: integer title: type: - string - 'null' keyword: type: - string - 'null' article_type: type: - string - 'null' write_mode: type: - string - 'null' status: type: - string - 'null' crawl_status: type: - string - 'null' outline_status: type: - string - 'null' word_count: type: - integer - 'null' scores: type: object properties: radarkit: type: - number - 'null' seo: type: - number - 'null' geo: type: - number - 'null' readability: type: - number - 'null' editor_url: type: - string - 'null' description: Open this in the dashboard to edit and publish. created_at: type: - string - 'null' format: date-time updated_at: type: - string - 'null' format: date-time started_at: type: - string - 'null' format: date-time completed_at: type: - string - 'null' format: date-time body_markdown: type: string description: The article as Markdown. Only with `include=body`. Credits: type: object description: >- What this call cost and what is left. Also in the `X-RadarKit-Credits-Charged` and `X-RadarKit-Credits-Remaining` headers. properties: charged: type: integer description: API credits spent on this call. remaining: type: - integer - 'null' description: API credits left on the billed account. Null on free calls. RequestId: type: string description: >- A unique id for this call. Also in the `X-Request-Id` header. Quote it when you contact support. example: req_01j9x4m2p7q8r9s0t1u2v3w4x5 Error: type: object description: Every failed call has this shape and no `data`. properties: error: type: object properties: code: type: string description: Stable. Build on this, not on the message. message: type: string description: For people. May change. details: description: >- More when there is more to say. Which field failed, how long to wait, which id already exists. oneOf: - type: object - type: array items: type: object request_id: $ref: '#/components/schemas/RequestId' responses: Unauthenticated: description: >- `UNAUTHENTICATED`: no key, a wrong key, or a revoked or expired key. `KEY_IN_QUERY` (400) if the key was in the URL. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: UNAUTHENTICATED message: >- Missing or invalid API key. Send it as: Authorization: Bearer rk_live_YOUR_KEY request_id: req_01j9x4q7z8y9x0w1v2u3t4s5r6 RateLimited: description: >- `RATE_LIMITED`: too many calls. Wait the seconds in `Retry-After` and send the same request again. Nothing was charged. headers: Retry-After: description: Seconds to wait. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: RATE_LIMITED message: Too many requests. Slow down and retry. details: retry_after: 21 request_id: req_01j9x4r2s3t4u5v6w7x8y9z0a1 securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your API key. Create one in Settings, API keys. Send it as `Authorization: Bearer rk_live_YOUR_KEY`. ````