> ## Documentation Index > Fetch the complete documentation index at: https://docs.swarms.ai/llms.txt > Use this file to discover all available pages before exploring further. # Execute Reasoning Agent Completion > Execute a reasoning agent with advanced cognitive capabilities for complex problem-solving tasks. This is a premium-only feature. ## OpenAPI ````yaml https://api.swarms.world/openapi.json post /v1/reasoning-agent/completions openapi: 3.1.0 info: title: Swarms API description: >- The Swarms API delivers a high-performance, enterprise-grade platform for orchestrating advanced multi-agent systems. Built on a Rust-powered agent runtime, it enables scalable, robust, and secure agent collaboration, supporting complex workflows and dynamic agent communication. The API exposes a comprehensive suite of RESTful endpoints for the management, execution, and monitoring of agents, swarms, and related resources, empowering organizations to automate and optimize mission-critical processes. To access the API, obtain your API key from the [Swarms API Keys page](https://swarms.world/platform/api-keys). For detailed integration guides, best practices, and reference material, consult the [Swarms API Documentation](https://docs.swarms.ai). version: 1.0.0 servers: - url: https://api.swarms.world description: Swarms Production API security: [] paths: /v1/reasoning-agent/completions: post: tags: - Reasoning Agents summary: Execute Reasoning Agent Completion description: >- Execute a reasoning agent with advanced cognitive capabilities for complex problem-solving tasks. This is a premium-only feature. operationId: run_reasoning_agent_completions_v1_reasoning_agent_completions_post parameters: - name: x-api-key in: header required: true schema: type: string title: X-Api-Key requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ReasoningAgentSpec' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ReasoningAgentCompletionOutput' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ReasoningAgentSpec: properties: agent_name: anyOf: - type: string - type: 'null' title: Agent Name description: The unique name assigned to the reasoning agent. default: reasoning-agent description: anyOf: - type: string - type: 'null' title: Description description: >- A detailed explanation of the reasoning agent's purpose and capabilities. default: A reasoning agent that can answer questions and help with tasks. model_name: anyOf: - type: string - type: 'null' title: Model Name description: The name of the AI model that the reasoning agent will utilize. default: claude-sonnet-4-20250514 system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: The initial instruction or context provided to the reasoning agent. max_loops: anyOf: - type: integer - type: 'null' title: Max Loops description: >- The maximum number of times the reasoning agent is allowed to repeat its task. default: 1 swarm_type: anyOf: - type: string enum: - reasoning-duo - self-consistency - ire - reasoning-agent - consistency-agent - ire-agent - ReflexionAgent - GKPAgent - AgentJudge - type: 'null' title: Swarm Type description: >- The type of reasoning swarm to use (e.g., reasoning duo, self-consistency, IRE). default: reasoning_duo num_samples: anyOf: - type: integer - type: 'null' title: Num Samples description: The number of samples to generate for the reasoning agent. default: 1 output_type: anyOf: - type: string enum: - list - dict - dictionary - string - str - final - last - json - all - yaml - xml - dict-all-except-first - str-all-except-first - basemodel - dict-final - list-final - type: 'null' title: Output Type description: The type of output format for the reasoning agent. default: dict-all-except-first num_knowledge_items: anyOf: - type: integer - type: 'null' title: Num Knowledge Items description: The number of knowledge items to use for the reasoning agent. memory_capacity: anyOf: - type: integer - type: 'null' title: Memory Capacity description: The memory capacity for the reasoning agent. task: anyOf: - type: string - type: 'null' title: Task description: The task to be completed by the reasoning agent. type: object title: ReasoningAgentSpec ReasoningAgentCompletionOutput: properties: job_id: type: string title: Job Id description: Unique identifier for the reasoning agent run. status: type: string title: Status description: Status of the reasoning agent run. default: success outputs: title: Outputs description: >- The output generated by the reasoning agent. Shape varies by reasoning type. timestamp: type: string title: Timestamp description: ISO-formatted timestamp of when the run was executed. agent_name: type: string title: Agent Name description: Name of the agent. agent_type: type: string title: Agent Type description: Type of the agent (swarm type). agent_id: type: string title: Agent Id description: Unique identifier for the agent instance. usage: additionalProperties: type: integer type: object title: Usage description: Token usage statistics including input, output, and total tokens. type: object required: - job_id - outputs - timestamp - agent_name - agent_type - agent_id - usage title: ReasoningAgentCompletionOutput HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError ````