A WireMock simulation of OpenAI's REST API — covering the Chat Completions API, assistants, audio, message batches, embeddings, and evals.
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
GET List available OpenAI models
curl -s -X GET 'https://o9d7e.wiremockapi.cloud/models'POST Create a chat completion
curl -s -X POST 'https://o9d7e.wiremockapi.cloud/chat/completions' \
-H 'Content-Type: application/json' \
-d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'Spec catalog — OpenAI API (2.3.0) · 237 endpoints
| Method | Path | Summary |
|---|---|---|
| GET | /assistants | Returns a list of assistants. |
| POST | /assistants | Create an assistant with a model and instructions. |
| DELETE | /assistants/{assistant_id} | Delete an assistant. |
| GET | /assistants/{assistant_id} | Retrieves an assistant. |
| POST | /assistants/{assistant_id} | Modifies an assistant. |
| POST | /audio/speech | Generates audio from the input text. Returns the audio file content, or a stream of audio events. |
| POST | /audio/transcriptions | Transcribes audio into the input language. Returns a transcription object in json, diarized_json, or verbose_json format, or a stream of transcript events. |
| POST | /audio/translations | Translates audio into English. |
| GET | /audio/voice_consents | Returns a list of voice consent recordings. |
| POST | /audio/voice_consents | Upload a voice consent recording. |
| DELETE | /audio/voice_consents/{consent_id} | Deletes a voice consent recording. |
| GET | /audio/voice_consents/{consent_id} | Retrieves a voice consent recording. |
| POST | /audio/voice_consents/{consent_id} | Updates a voice consent recording (metadata only). |
| POST | /audio/voices | Creates a custom voice. |
| GET | /batches | List your organization's batches. |
| POST | /batches | Creates and executes a batch from an uploaded file of requests |
| GET | /batches/{batch_id} | Retrieves a batch. |
| POST | /batches/{batch_id}/cancel | Cancels an in-progress batch. The batch will be in status cancelling for up to 10 minutes, before changing to cancelled, where it will have partial results (if any) available in the output file. |
| GET | /chat/completions | List stored Chat Completions. Only Chat Completions that have been stored with the store parameter set to true will be returned. |
| POST | /chat/completions | Creates a model response for the given chat conversation. |
| DELETE | /chat/completions/{completion_id} | Delete a stored chat completion. Only Chat Completions that have been created with the store parameter set to true can be deleted. |
| GET | /chat/completions/{completion_id} | Get a stored chat completion. Only Chat Completions that have been created with the store parameter set to true will be returned. |
| POST | /chat/completions/{completion_id} | Modify a stored chat completion. |
| GET | /chat/completions/{completion_id}/messages | Get the messages in a stored chat completion. Only Chat Completions that have been created with the store parameter set to true will be returned. |
| POST | /chatkit/sessions | Create a ChatKit session. |
| POST | /chatkit/sessions/{session_id}/cancel | Cancel an active ChatKit session and return its most recent metadata. Cancelling prevents new requests from using the issued client secret. |
| GET | /chatkit/threads | List ChatKit threads with optional pagination and user filters. |
| DELETE | /chatkit/threads/{thread_id} | Delete a ChatKit thread along with its items and stored attachments. |
| GET | /chatkit/threads/{thread_id} | Retrieve a ChatKit thread by its identifier. |
| GET | /chatkit/threads/{thread_id}/items | List items that belong to a ChatKit thread. |
| POST | /completions | Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed. |
| GET | /containers | List Containers |
| POST | /containers | Create Container |
| DELETE | /containers/{container_id} | Delete Container |
| GET | /containers/{container_id} | Retrieve Container |
| GET | /containers/{container_id}/files | List Container files |
| POST | /containers/{container_id}/files | Create a Container File You can send either a multipart/form-data request with the raw file content, or a JSON request with a file ID. |
| DELETE | /containers/{container_id}/files/{file_id} | Delete Container File |
| GET | /containers/{container_id}/files/{file_id} | Retrieve Container File |
| GET | /containers/{container_id}/files/{file_id}/content | Retrieve Container File Content |
| POST | /conversations | Create a conversation. |
| DELETE | /conversations/{conversation_id} | Delete a conversation. Items in the conversation will not be deleted. |
| GET | /conversations/{conversation_id} | Get a conversation |
| POST | /conversations/{conversation_id} | Update a conversation |
| GET | /conversations/{conversation_id}/items | List all items for a conversation with the given ID. |
| POST | /conversations/{conversation_id}/items | Create items in a conversation with the given ID. |
| DELETE | /conversations/{conversation_id}/items/{item_id} | Delete an item from a conversation with the given IDs. |
| GET | /conversations/{conversation_id}/items/{item_id} | Get a single item from a conversation with the given IDs. |
| POST | /embeddings | Creates an embedding vector representing the input text. |
| GET | /evals | List evaluations for a project. |
| POST | /evals | Create the structure of an evaluation that can be used to test a model's performance. |
| DELETE | /evals/{eval_id} | Delete an evaluation. |
| GET | /evals/{eval_id} | Get an evaluation by ID. |
| POST | /evals/{eval_id} | Update certain properties of an evaluation. |
| GET | /evals/{eval_id}/runs | Get a list of runs for an evaluation. |
| POST | /evals/{eval_id}/runs | Kicks off a new run for a given evaluation, specifying the data source, and what model configuration to use to test. |
| DELETE | /evals/{eval_id}/runs/{run_id} | Delete an eval run. |
| GET | /evals/{eval_id}/runs/{run_id} | Get an evaluation run by ID. |
| POST | /evals/{eval_id}/runs/{run_id} | Cancel an ongoing evaluation run. |
| GET | /evals/{eval_id}/runs/{run_id}/output_items | Get a list of output items for an evaluation run. |
+177 more endpoints in the full spec.
Unauthenticated WireMock Cloud demo sandbox for OpenAI — not an official OpenAI sandbox, and it returns simulated example data only.
OpenAI's platform is far more than chat, and the template reflects that: it is generated from the platform's own OpenAPI description, version 2.3.0, and spans a couple hundred endpoints. Post to /chat/completions and the stub replies with the full completion object — a choices array carrying the assistant message, a finish_reason, and a usage block totalling prompt and completion tokens — the exact structure the openai client libraries deserialize, so nothing downstream needs a special code path for mock mode.
The official openai libraries take a base_url at construction, so the swap is a single argument — plus a key the mock will never actually check:
The same redirect works without touching code: the library reads the OPENAI_BASE_URL environment variable, which is the practical route for pointing a whole agent stack or a third-party tool at the mock.
What you get in exchange is repeatability. Test suites stop failing because a model answered differently, integration branches can hammer the API without a usage bill, and a demo laptop needs no secrets at all.
from openai import OpenAI
# point the client at the sandbox,
# or at your own mock's URL
client = OpenAI(
base_url="https://o9d7e.wiremockapi.cloud",
api_key="any-value",
)
reply = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)It won't — any Authorization header passes, including none. Treat that as a reason to keep production secrets away from the shared sandbox entirely: it's an open endpoint, and a real sk- key has no business in requests to it.
You get the complete chat-completion JSON in one response rather than a token-by-token SSE stream. Non-streaming client code works as-is; to exercise genuine event-by-event delivery, stub a server-sent-events response in a private copy of the template.
No — replies are pre-recorded bodies with production-correct structure. The model id in your request is accepted, but the content string is fixed, which is exactly what makes the mock usable in CI: the same input yields the same bytes every run.
The shared sandbox only serves success responses. Copy the template into WireMock Cloud and add stubs returning OpenAI's error envelope — insufficient_quota on a 429, or a 500 with error.type set to server_error — then aim your retry and backoff logic at those.
Vendor names identify APIs represented by WireMock template sources. This page does not imply vendor endorsement, certification, partnership, or official integration status.