Create Run

Supported Providers

• OpenAI

Create a run.

post

Authorizations

Portkey-KeyVirtual-KeyProvider-AuthProvider-NameConfigCustom-Host

Path parameters

thread_idstringRequired

The ID of the thread to run.

Body

assistant_idstringRequired

The ID of the assistant to use to execute this run.

modelany of | nullableOptional

The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

Example: gpt-4-turbo

stringOptional

or

string · enumOptionalPossible values:

instructionsstring | nullableOptional

Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.

additional_instructionsstring | nullableOptional

Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.

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. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.

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.

Default: 1Example: 1

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.

Default: 1Example: 1

streamboolean | nullableOptional

If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

max_prompt_tokensinteger | nullableOptional

The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

max_completion_tokensinteger | nullableOptional

The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

tool_choiceone of | nullableOptional

Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

string · enumOptional

none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

Possible values:

or

parallel_tool_callsbooleanOptional

Whether to enable parallel function calling during tool use.

Default: true

response_formatone of | nullableOptional

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_object" } enables JSON mode, which guarantees 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.

string · enumOptional

auto is the default value

Possible values:

or

Responses

200

OK

application/json

200

OK

{
  "id": "text",
  "object": "thread.run",
  "created_at": 1,
  "thread_id": "text",
  "assistant_id": "text",
  "status": "queued",
  "required_action": {
    "type": "submit_tool_outputs",
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "text",
          "type": "function",
          "function": {
            "name": "text",
            "arguments": "text"
          }
        }
      ]
    }
  },
  "last_error": {
    "code": "server_error",
    "message": "text"
  },
  "expires_at": 1,
  "started_at": 1,
  "cancelled_at": 1,
  "failed_at": 1,
  "completed_at": 1,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "model": "text",
  "instructions": "text",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "metadata": {},
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1
  },
  "temperature": 1,
  "top_p": 1,
  "max_prompt_tokens": 1,
  "max_completion_tokens": 1,
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "response_format": "none"
}