Assistants
- GETList assistants
- POSTCreate assistant
- GETRetrieve assistant
- POSTModify assistant
- DELDelete assistant
- POSTCreate thread
- POSTCreate thread and run
- GETRetrieve thread.
- POSTModify thread
- DELDelete thread
- GETList messages
- POSTCreate message
- GETRetrieve message
- POSTModify message
- DELDelete message
- GETList runs
- POSTCreate run
- GETRetrieve run
- POSTModify run
- POSTCancel run
- GETList run steps
- GETRetrieve run step
- POSTThe run step object
Chat
Completions
Embeddings
Evals
Files
Fine-tuning
- GETList checkpoint permissions
- POSTCreate checkpoint permissions
- DELDelete checkpoint permission
- GETList your organization's fine-tuning jobs
- POSTCreate a fine-tuning job
- GETRetrieve fine-tuning job
- POSTImmediately cancel a fine-tune job.
- GETList checkpoints for a fine-tuning job.
- GETGet status updates for a fine-tuning job.
Moderations
API Reference
Audit Logs
Certificates
Usage
Projects
- GETReturns a list of projects.
- POSTCreate project
- GETRetrieves a project.
- POSTModify project
- GETList project API keys
- GETRetrieve project API key
- DELDelete project API key
- POSTArchive project
- GETList project rate limits
- POSTUpdate project rate limit
- GETList project service accounts
- POSTCreate project service account
- GETRetrieve project service account
- DELDelete project service account
- GETReturn project users
- POSTCreate project user
- GETRetrieve project user
- POSTModify project user
- DELDelete project user
Responses
Vector stores
- GETReturns a list of vector stores.
- POSTCreate a vector store.
- GETRetrieves a vector store.
- POSTModifies a vector store.
- DELDelete a vector store.
- POSTCreate a vector store file batch.
- GETRetrieves a vector store file batch.
- POSTCancel vector store file batch
- GETReturns a list of vector store files in a batch.
- GETReturns a list of vector store files.
- POSTCreate vector store file
- GETRetrieves a vector store file.
- POSTUpdate attributes on a vector store file.
- DELDelete vector store file
- GETRetrieve vector store
- POSTSearch vector store
Assistants
Modify run
Modifies a run.
POST
/
threads
/
{thread_id}
/
runs
/
{run_id}
Copy
Ask AI
curl --request POST \
--url https://api.openai.com/v1/threads/{thread_id}/runs/{run_id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"metadata": {}
}'
Copy
Ask AI
{
"id": "<string>",
"object": "thread.run",
"created_at": 123,
"thread_id": "<string>",
"assistant_id": "<string>",
"status": "queued",
"required_action": {
"type": "submit_tool_outputs",
"submit_tool_outputs": {
"tool_calls": [
{
"id": "<string>",
"type": "function",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
]
}
},
"last_error": {
"code": "server_error",
"message": "<string>"
},
"expires_at": 123,
"started_at": 123,
"cancelled_at": 123,
"failed_at": 123,
"completed_at": 123,
"incomplete_details": {
"reason": "max_completion_tokens"
},
"model": "<string>",
"instructions": "<string>",
"tools": [],
"metadata": {},
"usage": {
"completion_tokens": 123,
"prompt_tokens": 123,
"total_tokens": 123
},
"temperature": 123,
"top_p": 123,
"max_prompt_tokens": 257,
"max_completion_tokens": 257,
"truncation_strategy": {
"type": "auto",
"last_messages": 2
},
"tool_choice": "none",
"parallel_tool_calls": true,
"response_format": "auto"
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Path Parameters
The ID of the run to modify.
Body
application/json
Response
200 - application/json
OK
Represents an execution run on a thread.
Was this page helpful?
Copy
Ask AI
curl --request POST \
--url https://api.openai.com/v1/threads/{thread_id}/runs/{run_id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"metadata": {}
}'
Copy
Ask AI
{
"id": "<string>",
"object": "thread.run",
"created_at": 123,
"thread_id": "<string>",
"assistant_id": "<string>",
"status": "queued",
"required_action": {
"type": "submit_tool_outputs",
"submit_tool_outputs": {
"tool_calls": [
{
"id": "<string>",
"type": "function",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
]
}
},
"last_error": {
"code": "server_error",
"message": "<string>"
},
"expires_at": 123,
"started_at": 123,
"cancelled_at": 123,
"failed_at": 123,
"completed_at": 123,
"incomplete_details": {
"reason": "max_completion_tokens"
},
"model": "<string>",
"instructions": "<string>",
"tools": [],
"metadata": {},
"usage": {
"completion_tokens": 123,
"prompt_tokens": 123,
"total_tokens": 123
},
"temperature": 123,
"top_p": 123,
"max_prompt_tokens": 257,
"max_completion_tokens": 257,
"truncation_strategy": {
"type": "auto",
"last_messages": 2
},
"tool_choice": "none",
"parallel_tool_calls": true,
"response_format": "auto"
}
Assistant
Responses are generated using AI and may contain mistakes.