Swagger Petstore - OpenAPI 3.0
POST/assistantsDeprecated

Create an assistant

Creates a new assistant with a specified model and optional configuration. Supply model at minimum — all other fields such as name, instructions, tools, and temperature are optional and can be omitted. Returns the created assistant object with its generated identifier.

  • IdempotentThe SDK sends Idempotency-Key, so a retried request is only applied once.

11 body fields

Assistant configuration. Only model is required; all other fields are optional.

modelstringrequired
ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them.
namestringoptional
A human-readable name for the assistant. Maximum 256 characters.
descriptionstringoptional
A description of the assistant's purpose or capabilities. Maximum 512 characters.
instructionsstringoptional
System instructions that guide the assistant's behavior. Maximum 256,000 characters.
reasoning_effortstringoptional
Constrains reasoning effort for reasoning models: none, minimal, low, medium, high, xhigh, or max. Defaults to medium.
Allowed:noneminimallowmediumhighxhighmaxDefault:medium
toolsarray<CodeInterpreterTool>optional
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`.
Default:[]
tool_resourcesobjectoptional
Resources for the assistant's tools, such as file IDs for code_interpreter or vector store IDs for file_search.
metadataobjectoptional
Key-value pairs for storing additional information. Keys are strings up to 64 characters; values are strings.
temperaturenumberoptional
Sampling temperature between 0 and 2. Higher values increase randomness. Defaults to 1 when omitted.
Default:1
top_pnumberoptional
Nucleus sampling parameter between 0 and 1. Defaults to 1 when omitted.
Default:1
response_formatstring | objectoptional
Specifies the output format, such as JSON schema for structured outputs.

2 status codes
200Returns the created assistant object with its unique identifier, model, configuration, and all provided settings.
idstringrequired
The identifier, which can be referenced in API endpoints.
objectstringrequired
The object type, which is always `assistant`.
Allowed:assistant
created_atintegerrequired
The Unix timestamp (in seconds) for when the assistant was created.
namestringrequired
The name of the assistant. The maximum length is 256 characters.
descriptionstringrequired
The description of the assistant. The maximum length is 512 characters.
modelstringrequired
ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them.
instructionsstringrequired
The system instructions that the assistant uses. The maximum length is 256,000 characters.
toolsarray<CodeInterpreterTool>required
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`.
Default:[]
tool_resourcesobjectoptional
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.
metadataobjectrequired
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.
temperaturenumberoptional
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.
Default:1
top_pnumberoptional
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.
Default:1
response_formatstring | objectoptional
Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), 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](/docs/guides/structured-outputs). 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.
429Returned when the request rate limit is exceeded.
errorobjectrequired

Error handling

model is required and must be a valid model identifier. name must not exceed 256 characters, description must not exceed 512 characters, and instructions must not exceed 256,000 characters. temperature must be between 0 and 2, and top_p must be between 0 and 1. A 429 is returned when the request rate limit is exceeded.