Assistant API

Assistants are AI-driven entities with assigned roles and instructions, allowing them to process messages, use tools, and maintain context within threads for structured and interactive responses. One Assistant can be used across multiple Threads and users.

This page provides API schemas for the following methods:

Create an Assistant	https://api.aimlapi.com/assistants
Retrieve a list of Assistants along with their parameters	https://api.aimlapi.com/assistants
Retrieve information about a specific Assistant by its ID	https://api.aimlapi.com/assistants/{assistantId}
Modify a specific Assistant by its ID	https://api.aimlapi.com/assistants/{assistantId}
Delete a specific Assistant by its ID	https://api.aimlapi.com/assistants/{assistantId}

After each API schema, you'll find a short example demonstrating how to correctly call the described method in code using the OpenAI SDK.

Note that the method names in the API schema and the SDK often differ. Accordingly, when calling these methods via the REST API, you should use the names from the API schema, while for calls through the OpenAI SDK, use the names from the examples.

API Schemas

Create an Assistant

Create an Assistant with a model and instructions.

post

Authorizations

Body

modelstring · enumrequired

ID of the model to use

Options: gpt-4o, gpt-4o-2024-08-06, gpt-4o-2024-05-13, gpt-4o-mini, gpt-4o-mini-2024-07-18, chatgpt-4o-latest, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4, gpt-4-0125-preview, gpt-4-1106-preview, gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, o1-preview, o1-preview-2024-09-12, o1-mini, o1-mini-2024-09-12, o3-mini, gpt-4.5-preview

descriptionstring | nullableoptional

The description of the assistant. The maximum length is 512 characters

instructionsstring | nullableoptional

The system instructions that the assistant uses. The maximum length is 256,000 characters

metadataobject | nullableoptional

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

namestring | nullableoptional

The name of the assistant. The maximum length is 256 characters

reasoning_effortstring · enum | nullableoptional

Constrains effort on reasoning for reasoning models

Options: low, medium, high

response_formatany ofoptional

Specifies the format that the model must output

temperaturenumber | nullableoptional

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic

tool_resourcesobject | nullableoptional

A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

toolsone of[]optional

A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant.

top_pnumber | nullableoptional

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/assistants' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-4o",
    "description": "text",
    "instructions": "text",
    "metadata": {
      "ANY_ADDITIONAL_PROPERTY": null
    },
    "name": "text",
    "reasoning_effort": "low",
    "response_format": "auto",
    "temperature": 1,
    "tool_resources": {
      "code_interpreter": {
        "file_ids": []
      },
      "file_search": {
        "vector_store_ids": [
          "text"
        ],
        "vector_stores": [
          {
            "chunking_strategy": {
              "type": "auto"
            },
            "file_ids": [
              "text"
            ],
            "metadata": {
              "ANY_ADDITIONAL_PROPERTY": null
            }
          }
        ]
      }
    },
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "top_p": 1
  }'

default

default

{
  "model": "text",
  "description": "text",
  "instructions": "text",
  "metadata": null,
  "name": "text",
  "reasoning_effort": "low",
  "response_format": "auto",
  "temperature": 1,
  "tool_resources": {
    "code_interpreter": {
      "file_ids": []
    },
    "file_search": {
      "vector_store_ids": [
        "text"
      ],
      "vector_stores": [
        {
          "chunking_strategy": {
            "type": "auto"
          },
          "file_ids": [
            "text"
          ],
          "metadata": {
            "ANY_ADDITIONAL_PROPERTY": null
          }
        }
      ]
    }
  },
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "top_p": 1,
  "id": "text",
  "created_at": 1,
  "object": "assistant"
}

Python + OpenAI SDK Example:

from openai import OpenAI
client = OpenAI()

assistant = client.beta.assistants.create(
  name="Math Tutor",
  instructions="You are a personal math tutor. Write and run code to answer math questions.",
  tools=[{"type": "code_interpreter"}],
  model="gpt-4o",
)

---

Retrieve a list of Assistants along with their parameters

get

Authorizations

Query parameters

limitintegeroptional

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

orderstringoptional

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

beforestringoptional

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

afterstringoptional

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --url 'https://api.aimlapi.com/assistants' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>'

default

default

{
  "object": "list",
  "data": [
    {
      "model": "text",
      "description": "text",
      "instructions": "text",
      "metadata": null,
      "name": "text",
      "id": "text",
      "created_at": 1,
      "object": "assistant"
    }
  ]
}

Python + OpenAI SDK Example:

from openai import OpenAI
client = OpenAI()

my_assistants = client.beta.assistants.list(
    order="desc",
    limit="20",
)
print(my_assistants.data)

---

Retrieve information about a specific Assistant by its ID

get

Authorizations

Path parameters

assistantIdstringrequired

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --url 'https://api.aimlapi.com/assistants/{assistantId}' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>'

default

default

{
  "model": "text",
  "description": "text",
  "instructions": "text",
  "metadata": null,
  "name": "text",
  "reasoning_effort": "low",
  "response_format": "auto",
  "temperature": 1,
  "tool_resources": {
    "code_interpreter": {
      "file_ids": []
    },
    "file_search": {
      "vector_store_ids": [
        "text"
      ],
      "vector_stores": [
        {
          "chunking_strategy": {
            "type": "auto"
          },
          "file_ids": [
            "text"
          ],
          "metadata": {
            "ANY_ADDITIONAL_PROPERTY": null
          }
        }
      ]
    }
  },
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "top_p": 1,
  "id": "text",
  "created_at": 1,
  "object": "assistant"
}

Python + OpenAI SDK Example:

from openai import OpenAI
client = OpenAI()

my_assistant = client.beta.assistants.retrieve("asst_abc123")
print(my_assistant)

---

Modify a specific Assistant by its ID

post

Authorizations

Path parameters

assistantIdstringrequired

Body

all ofoptional

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/assistants/{assistantId}' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-4o",
    "description": "text",
    "instructions": "text",
    "metadata": {
      "ANY_ADDITIONAL_PROPERTY": null
    },
    "name": "text",
    "reasoning_effort": "low",
    "response_format": "auto",
    "temperature": 1,
    "tool_resources": {
      "code_interpreter": {
        "file_ids": []
      },
      "file_search": {
        "vector_store_ids": [
          "text"
        ],
        "vector_stores": [
          {
            "chunking_strategy": {
              "type": "auto"
            },
            "file_ids": [
              "text"
            ],
            "metadata": {
              "ANY_ADDITIONAL_PROPERTY": null
            }
          }
        ]
      }
    },
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "top_p": 1
  }'

default

default

{
  "model": "text",
  "description": "text",
  "instructions": "text",
  "metadata": null,
  "name": "text",
  "reasoning_effort": "low",
  "response_format": "auto",
  "temperature": 1,
  "tool_resources": {
    "code_interpreter": {
      "file_ids": []
    },
    "file_search": {
      "vector_store_ids": [
        "text"
      ],
      "vector_stores": [
        {
          "chunking_strategy": {
            "type": "auto"
          },
          "file_ids": [
            "text"
          ],
          "metadata": {
            "ANY_ADDITIONAL_PROPERTY": null
          }
        }
      ]
    }
  },
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "top_p": 1,
  "id": "text",
  "created_at": 1,
  "object": "assistant"
}

Python + OpenAI SDK Example:

from openai import OpenAI
client = OpenAI()

my_updated_assistant = client.beta.assistants.update(
  "asst_abc123",
  instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
  name="HR Helper",
  tools=[{"type": "file_search"}],
  model="gpt-4o"
)

print(my_updated_assistant)

---

Delete a specific Assistant by its ID

delete

Authorizations

Path parameters

assistantIdstringrequired

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request DELETE \
  --url 'https://api.aimlapi.com/assistants/{assistantId}' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>'

default

default

{
  "id": "text",
  "object": "assistant.deleted",
  "deleted": true
}

Python + OpenAI SDK Example:

from openai import OpenAI
client = OpenAI()

response = client.beta.assistants.delete("asst_abc123")
print(response)