A WireMock simulation of Perplexity's REST API — covering Sonar chat completions (synchronous and async), the Agent API, the Search API, embeddings, decisions, skills, batch processing, and usage analytics.
A shared instance of this template runs on a public endpoint — call it right now from curl, an SDK, or an AI agent. Responses are fixed examples and behavior can't be changed; rate limits apply.
Jump to the endpoints ↓Run this template as a mock API in WireMock Cloud for a private instance you control — edit stubs, add stateful scenarios, use dynamic response templating, and inspect requests in the log.
Open in WireMock Cloud (free) →Live sandbox · no signup, no API key
A running WireMock Cloud instance of this template, callable right now from a terminal, a script, or an AI agent.
Endpoints
POST Create Agent Response
curl -s -X POST 'https://r0k7om.wiremockapi.cloud/v1/agent' \
-H 'Content-Type: application/json' \
-d '{}'GET List Models
curl -s -X GET 'https://r0k7om.wiremockapi.cloud/v1/models'POST Create Async Chat Completion
curl -s -X POST 'https://r0k7om.wiremockapi.cloud/v1/async/sonar' \
-H 'Content-Type: application/json' \
-d '{}'Spec catalog — Perplexity AI API (1.0.0) · 35 endpoints
| Method | Path | Summary |
|---|---|---|
| POST | /generate_auth_token | Generate Auth Token |
| POST | /revoke_auth_token | Revoke Auth Token |
| POST | /search | Search the Web |
| GET | /v1/admin/audit-events | List audit events |
| POST | /v1/agent | Create Agent Response |
| GET | /v1/agent/{id} | Retrieve Agent Response |
| POST | /v1/agent/{id}/cancel | Cancel Agent Response |
| GET | /v1/agent/{id}/files | List Agent Response Files |
| GET | /v1/agent/{id}/files/{file_id}/content | Download Agent Response File |
| GET | /v1/analytics/computer/usage | Usage Analytics |
| GET | /v1/async/sonar | List Async Chat Completions |
| POST | /v1/async/sonar | Create Async Chat Completion |
| GET | /v1/async/sonar/{api_request} | Get Async Chat Completion |
| GET | /v1/batches | List batches |
| POST | /v1/batches | Create a batch |
| GET | /v1/batches/{batch_id} | Retrieve a batch |
| POST | /v1/batches/{batch_id}/cancel | Cancel a batch |
| POST | /v1/contextualizedembeddings | Create Contextualized Embeddings |
| POST | /v1/decisions | Answer questions |
| POST | /v1/embeddings | Create Embeddings |
| GET | /v1/files | List files |
| POST | /v1/files | Upload a file |
| DELETE | /v1/files/{file_id} | Delete a file |
| GET | /v1/files/{file_id} | Retrieve a file |
| GET | /v1/files/{file_id}/content | Download file content |
| GET | /v1/models | List Models |
| GET | /v1/skills | List skills |
| POST | /v1/skills | Create a skill |
| DELETE | /v1/skills/{skill_id} | Delete a skill |
| GET | /v1/skills/{skill_id} | Get a skill |
| PUT | /v1/skills/{skill_id} | Add a skill revision |
| GET | /v1/skills/{skill_id}/download | Get a skill download URL |
| GET | /v1/skills/{skill_id}/revisions | List skill revisions |
| POST | /v1/sonar | Create Chat Completion |
| GET | /v2/analytics/computer/usage | Usage Analytics per Member |
Unauthenticated WireMock Cloud demo sandbox for Perplexity — not an official Perplexity sandbox, and it returns simulated example data only.
The template covers Perplexity's API platform apart from the Orchestrator, which has a page of its own. A Sonar request answers with a chat.completion object whose usage block includes the search context size, plus citations and search results built around your question. The Agent API stores each response under a resp_ id, so a background run starts in_progress and reads back completed. Clients that render citations or poll for agent output follow the same code path they use in production.
No search runs behind the mock. Answers, citations and search results follow a fixed pattern that quotes your question, which keeps assertions stable from one run to the next.
Each retrieve moves the job one step forward. An Agent API background run completes on its first retrieve, and an async Sonar request takes two to reach COMPLETED, so a polling loop finishes in a known number of calls without real waiting.
The Agent API does: stream set to true returns server-sent events, one text delta per word, ending in response.completed. Sonar ignores the flag and answers JSON, because Perplexity's spec documents only a JSON response for that route.
No. Vectors have the right length and encoding for the model and dimensions you request, but their values are random, so the same text gives a different vector each time. Use them to test storage and parsing, not ranking.
Vendor names identify APIs represented by WireMock template sources. This page does not imply vendor endorsement, certification, partnership, or official integration status.