SpyBara
Go Premium

resources/beta/subresources/assistants/methods/create/index.md 2026-07-10 23:02 UTC to 2026-07-12 06:58 UTC

36 added, 112 removed.

2026
Fri 17 17:00 Thu 16 20:57 Wed 15 02:58 Tue 14 06:58 Mon 13 15:59 Sun 12 06:58 Fri 10 23:02 Thu 9 20:58 Tue 7 08:02

Create assistant

post /assistants

Create an assistant with a model and instructions.

Body Parameters

  • model: string or "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 39 more

    ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

    • string

    • AssistantSupportedModels = "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 39 more

      ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

      • "gpt-5"

      • "gpt-5-mini"

      • "gpt-5-nano"

      • "gpt-5-2025-08-07"

      • "gpt-5-mini-2025-08-07"

      • "gpt-5-nano-2025-08-07"

      • "gpt-4.1"

      • "gpt-4.1-mini"

      • "gpt-4.1-nano"

      • "gpt-4.1-2025-04-14"

      • "gpt-4.1-mini-2025-04-14"

      • "gpt-4.1-nano-2025-04-14"

      • "o3-mini"

      • "o3-mini-2025-01-31"

      • "o1"

      • "o1-2024-12-17"

      • "gpt-4o"

      • "gpt-4o-2024-11-20"

      • "gpt-4o-2024-08-06"

      • "gpt-4o-2024-05-13"

      • "gpt-4o-mini"

      • "gpt-4o-mini-2024-07-18"

      • "gpt-4.5-preview"

      • "gpt-4.5-preview-2025-02-27"

      • "gpt-4-turbo"

      • "gpt-4-turbo-2024-04-09"

      • "gpt-4-0125-preview"

      • "gpt-4-turbo-preview"

      • "gpt-4-1106-preview"

      • "gpt-4-vision-preview"

      • "gpt-4"

      • "gpt-4-0314"

      • "gpt-4-0613"

      • "gpt-4-32k"

      • "gpt-4-32k-0314"

      • "gpt-4-32k-0613"

      • "gpt-3.5-turbo"

      • "gpt-3.5-turbo-16k"

      • "gpt-3.5-turbo-0613"

      • "gpt-3.5-turbo-1106"

      • "gpt-3.5-turbo-0125"

      • "gpt-3.5-turbo-16k-0613"

  • description: optional string

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

  • instructions: optional string

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

  • metadata: optional Metadata

    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.

  • name: optional string

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

  • reasoning_effort: optional ReasoningEffort

    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

    • "none"

    • "minimal"

    • "low"

    • "medium"

    • "high"

    • "xhigh"

    • "max"

  • response_format: optional AssistantResponseFormatOption

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • "auto"

      auto is the default value

      • "auto"

    • ResponseFormatText object { type }

      Default response format. Used to generate text responses.

      • type: "text"

        The type of response format being defined. Always text.

        • "text"

    • ResponseFormatJSONObject object { type }

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • type: "json_object"

        The type of response format being defined. Always json_object.

        • "json_object"

    • ResponseFormatJSONSchema object { json_schema, type }

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • json_schema: object { name, description, schema, strict }

        Structured Outputs configuration options, including a JSON Schema.

        • name: string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • description: optional string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • schema: optional map[unknown]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • strict: optional boolean

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • type: "json_schema"

        The type of response format being defined. Always json_schema.

        • "json_schema"

  • temperature: optional number

    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_resources: optional object { code_interpreter, file_search }

    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.

    • code_interpreter: optional object { file_ids }

      • file_ids: optional array of string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • file_search: optional object { vector_store_ids, vector_stores }

      • vector_store_ids: optional array of string

        The vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

      • vector_stores: optional array of object { chunking_strategy, file_ids, metadata }

        A helper to create a vector store with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant.

        • chunking_strategy: optional object { type } or object { static, type }

          The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

          • AutoChunkingStrategy object { type }

            The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

            • type: "auto"

              Always auto.

              • "auto"

          • StaticChunkingStrategy object { static, type }

            • static: object { chunk_overlap_tokens, max_chunk_size_tokens }

              • chunk_overlap_tokens: number

                The number of tokens that overlap between chunks. The default value is 400.

                Note that the overlap must not exceed half of max_chunk_size_tokens.

              • max_chunk_size_tokens: number

                The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

            • type: "static"

              Always static.

              • "static"

        • file_ids: optional array of string

          A list of file IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.

        • metadata: optional Metadata

          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.

  • tools: optional array of CodeInterpreterTool or FileSearchTool or FunctionTool

    A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.

    • CodeInterpreterTool object { type }

      • type: "code_interpreter"

        The type of tool being defined: code_interpreter

        • "code_interpreter"

    • FileSearchTool object { type, file_search }

      • type: "file_search"

        The type of tool being defined: file_search

        • "file_search"

      • file_search: optional object { max_num_results, ranking_options }

        Overrides for the file search tool.

        • max_num_results: optional number

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • ranking_options: optional object { score_threshold, ranker }

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • score_threshold: number

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • ranker: optional "auto" or "default_2024_08_21"

            The ranker to use for the file search. If not specified will use the auto ranker.

            • "auto"

            • "default_2024_08_21"

    • FunctionTool object { function, type }

      • function: FunctionDefinition

        • name: string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • description: optional string

          A description of what the function does, used by the model to choose when and how to call the function.

        • parameters: optional FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • strict: optional boolean

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • type: "function"

        The type of tool being defined: function

        • "function"

  • top_p: optional number

    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.

Returns

  • Assistant object { id, created_at, description, 10 more }

    Represents an assistant that can call the model and use tools.

    • id: string

      The identifier, which can be referenced in API endpoints.

    • created_at: number

      The Unix timestamp (in seconds) for when the assistant was created.

    • description: string

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

    • instructions: string

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

    • metadata: Metadata

      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.

    • model: string

      ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

    • name: string

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

    • object: "assistant"

      The object type, which is always assistant.

      • "assistant"

    • tools: array of CodeInterpreterTool or FileSearchTool or FunctionTool

      A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.

      • CodeInterpreterTool object { type }

        • type: "code_interpreter"

          The type of tool being defined: code_interpreter

          • "code_interpreter"

      • FileSearchTool object { type, file_search }

        • type: "file_search"

          The type of tool being defined: file_search

          • "file_search"

        • file_search: optional object { max_num_results, ranking_options }

          Overrides for the file search tool.

          • max_num_results: optional number

            The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

            Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

          • ranking_options: optional object { score_threshold, ranker }

            The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

            See the file search tool documentation for more information.

            • score_threshold: number

              The score threshold for the file search. All values must be a floating point number between 0 and 1.

            • ranker: optional "auto" or "default_2024_08_21"

              The ranker to use for the file search. If not specified will use the auto ranker.

              • "auto"

              • "default_2024_08_21"

      • FunctionTool object { function, type }

        • function: FunctionDefinition

          • name: string

            The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

          • description: optional string

            A description of what the function does, used by the model to choose when and how to call the function.

          • parameters: optional FunctionParameters

            The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

            Omitting parameters defines a function with an empty parameter list.

          • strict: optional boolean

            Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

        • type: "function"

          The type of tool being defined: function

          • "function"

    • response_format: optional AssistantResponseFormatOption

      Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

      Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

      Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

      Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

      • "auto"

        auto is the default value

        • "auto"

      • ResponseFormatText object { type }

        Default response format. Used to generate text responses.

        • type: "text"

          The type of response format being defined. Always text.

          • "text"

      • ResponseFormatJSONObject object { type }

        JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

        • type: "json_object"

          The type of response format being defined. Always json_object.

          • "json_object"

      • ResponseFormatJSONSchema object { json_schema, type }

        JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

        • json_schema: object { name, description, schema, strict }

          Structured Outputs configuration options, including a JSON Schema.

          • name: string

            The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

          • description: optional string

            A description of what the response format is for, used by the model to determine how to respond in the format.

          • schema: optional map[unknown]

            The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

          • strict: optional boolean

            Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

        • type: "json_schema"

          The type of response format being defined. Always json_schema.

          • "json_schema"

    • temperature: optional number

      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_resources: optional object { code_interpreter, file_search }

      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.

      • code_interpreter: optional object { file_ids }

        • file_ids: optional array of string

          A list of file IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool.

      • file_search: optional object { vector_store_ids }

        • vector_store_ids: optional array of string

          The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

    • top_p: optional number

      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.

Example

curl https://api.openai.com/v1/assistants \
    -H 'Content-Type: application/json' \
    -H 'OpenAI-Beta: assistants=v2' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
          "model": "gpt-4o",
          "temperature": 1,
          "top_p": 1
        }'

Response

{
  "id": "id",
  "created_at": 0,
  "description": "description",
  "instructions": "instructions",
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "name": "name",
  "object": "assistant",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "response_format": "auto",
  "temperature": 1,
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  },
  "top_p": 1
}

Code Interpreter

curl "https://api.openai.com/v1/assistants" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "OpenAI-Beta: assistants=v2" \
  -d '{
    "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.",
    "name": "Math Tutor",
    "tools": [{"type": "code_interpreter"}],
    "model": "gpt-4o"
  }'

Response

{
  "id": "asst_abc123",
  "object": "assistant",
  "created_at": 1698984975,
  "name": "Math Tutor",
  "description": null,
  "model": "gpt-4o",
  "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "metadata": {},
  "top_p": 1.0,
  "temperature": 1.0,
  "response_format": "auto"
}

Files

curl https://api.openai.com/v1/assistants \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "OpenAI-Beta: assistants=v2" \
  -d '{
    "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.",
    "tools": [{"type": "file_search"}],
    "tool_resources": {"file_search": {"vector_store_ids": ["vs_123"]}},
    "model": "gpt-4o"
  }'

Response

{
  "id": "asst_abc123",
  "object": "assistant",
  "created_at": 1699009403,
  "name": "HR Helper",
  "description": null,
  "model": "gpt-4o",
  "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.",
  "tools": [
    {
      "type": "file_search"
    }
  ],
  "tool_resources": {
    "file_search": {
      "vector_store_ids": ["vs_123"]
    }
  },
  "metadata": {},
  "top_p": 1.0,
  "temperature": 1.0,
  "response_format": "auto"
}