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

access-token

AuthorizationstringRequired

Bearer key

Body

application/json

modelstring · enumRequiredPossible values:

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. Instructions can indeed be very large and complex, including full action frameworks, example messages, response formatting guidelines, topic restrictions, and stylistic rules.

namestring | nullableOptional

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

reasoning_effortstring · enum | nullableOptional

Constrains effort on reasoning for reasoning models.

Possible values:

response_formatany ofOptional

Specifies the format that the model must output.

string · enumOptionalPossible values:

or

anyOptional

or

or

or

any | nullableOptional

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.

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

default

application/json

post

/assistants

HTTPcURLJavaScriptPython

POST /assistants HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 462

{
  "model": "openai/gpt-4o",
  "description": "text",
  "instructions": "text",
  "metadata": {
    "ANY_ADDITIONAL_PROPERTY": "text"
  },
  "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": "text"
          }
        }
      ]
    }
  },
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "top_p": 1
}

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": "text"
          }
        }
      ]
    }
  },
  "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

access-token

AuthorizationstringRequired

Bearer key

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

default

application/json

get

/assistants

HTTPcURLJavaScriptPython

GET /assistants HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

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

access-token

AuthorizationstringRequired

Bearer key

Path parameters

assistantIdstringRequired

Responses

default

application/json

get

/assistants/{assistantId}

HTTPcURLJavaScriptPython

GET /assistants/{assistantId} HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

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": "text"
          }
        }
      ]
    }
  },
  "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

access-token

AuthorizationstringRequired

Bearer key

Path parameters

assistantIdstringRequired

Body

application/json

anyOptional

Responses

default

application/json

post

/assistants/{assistantId}

HTTPcURLJavaScriptPython

POST /assistants/{assistantId} HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 462

{
  "model": "openai/gpt-4o",
  "description": "text",
  "instructions": "text",
  "metadata": {
    "ANY_ADDITIONAL_PROPERTY": "text"
  },
  "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": "text"
          }
        }
      ]
    }
  },
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "top_p": 1
}

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": "text"
          }
        }
      ]
    }
  },
  "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

access-token

AuthorizationstringRequired

Bearer key

Path parameters

assistantIdstringRequired

Responses

default

application/json

delete

/assistants/{assistantId}

HTTPcURLJavaScriptPython

DELETE /assistants/{assistantId} HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

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)