> ## Documentation Index > Fetch the complete documentation index at: https://docs.flextell.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create an agent prompt ## OpenAPI ````yaml /api-referansi/openapi.json post /v1/agent-prompts openapi: 3.1.0 info: title: Flextell API version: 0.0.1 description: >- Flextell REST API referansı. Kimlik doğrulama, scope ve istek kuralları için API sekmesindeki rehberlere bakın. servers: - url: https://app.flextell.ai/api description: Üretim security: - oauth2: [] - bearer: [] paths: /v1/agent-prompts: post: tags: - AgentPrompt summary: Create an agent prompt operationId: agentPrompt.store parameters: - name: X-Tenant in: header required: true description: >- Tenant identifier. Send the Tenant ID in the `X-Tenant` header to scope API requests to a specific tenant. schema: type: number requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AgentPromptStoreRequest' responses: '201': description: '' content: application/json: schema: type: object properties: success: type: string data: $ref: '#/components/schemas/AgentPromptResource' required: - success - data '401': $ref: '#/components/responses/AuthenticationException' '403': $ref: '#/components/responses/AuthorizationException' '422': $ref: '#/components/responses/ValidationException' '428': description: >- Mandatory setup is incomplete. Finish the setup wizard first; `data.next_step` names the step to continue with. content: application/json: schema: type: object properties: success: type: boolean examples: - false error_code: type: string enum: - SETUP_REQUIRED examples: - SETUP_REQUIRED message: type: string examples: - Complete the required setup steps to continue. data: type: object properties: next_step: type: - string - 'null' examples: - clinic_info required: - next_step required: - success - error_code - message - data components: schemas: AgentPromptStoreRequest: type: object properties: type: type: string description: >- The agent type (greeter, booking, info, support, router, spam, ai_report, intake_router, intake). enum: - greeter - booking - info - support - router - spam - ai_report - intake_router - intake prompt: type: string description: The system prompt content for the agent. language: anyOf: - $ref: '#/components/schemas/Language' description: >- The language of the patients this prompt serves (tr or en). Defaults to tr. Each agent type has at most one active prompt per language. - type: 'null' llm_model: type: - string - 'null' description: >- The LLM model name to run this agent with, from the selectable models catalog. Null uses the system default model. enum: - anthropic/claude-opus-5.5 - openai/gpt-5.6-luna - openai/gpt-5.6-terra-pro - openai/gpt-5.6-terra - openai/gpt-5.6-sol-pro - openai/gpt-5.6-sol - anthropic/claude-sonnet-5 - anthropic/claude-fable-5 - anthropic/claude-opus-4.8 - google/gemini-3.5-flash - google/gemini-3.1-flash-lite - x-ai/grok-4.3 - openai/gpt-5.5-pro - anthropic/claude-opus-4.8-fast - openai/gpt-5.5 - anthropic/claude-opus-4.7-fast - openai/gpt-chat-latest - openai/gpt-5-codex - x-ai/grok-4.5 - x-ai/grok-build-0.1 - openai/gpt-5.6-luna-pro - anthropic/claude-opus-4.7 - google/gemma-4-26b-a4b-it - google/gemma-4-26b-a4b-it:free - openai/gpt-5.4-nano - openai/gpt-5.4-pro - openai/gpt-5.4 - google/gemini-3.1-pro-preview - anthropic/claude-sonnet-4.6 - anthropic/claude-opus-4.6 - openai/gpt-5.3-chat - google/gemini-3.1-flash-lite-preview - deepseek/deepseek-v4-flash - x-ai/grok-4.20 - google/gemini-3.1-pro-preview-customtools - openai/gpt-5.3-codex - google/gemma-4-31b-it - google/gemma-4-31b-it:free - openai/gpt-5.2-pro - openai/gpt-5.2 - anthropic/claude-opus-4.5 - openai/gpt-5.1 - anthropic/claude-haiku-4.5 - openai/gpt-5.1-chat - openai/gpt-oss-safeguard-20b - openai/gpt-5-pro - openai/o3-deep-research - openai/o4-mini-deep-research - anthropic/claude-sonnet-4.5 - openai/gpt-5.2-chat - openai/gpt-5.1-codex-max - openai/gpt-5.1-codex - openai/gpt-5.1-codex-mini - deepseek/deepseek-v3.2-exp - openai/gpt-5.4-mini - deepseek/deepseek-chat-v3.1 - openai/gpt-5 - openai/gpt-5-nano - openai/gpt-oss-120b - openai/gpt-oss-20b - google/gemini-2.5-flash-lite - google/gemini-2.5-flash - openai/o3 - openai/o4-mini - openai/gpt-4.1 - openai/o3-pro - deepseek/deepseek-r1-0528 - openai/o4-mini-high - openai/gpt-4.1-mini - openai/gpt-4.1-nano - google/gemini-2.5-pro - deepseek/deepseek-chat-v3-0324 - google/gemma-3-12b-it - google/gemma-3-27b-it - openai/o3-mini-high - google/gemini-3-flash-preview - openai/gpt-4o - openai/o1 - openai/gpt-4-turbo - openai/gpt-3.5-turbo-0613 - openai/gpt-4-turbo-preview - openai/gpt-3.5-turbo-16k - deepseek/deepseek-chat - openai/gpt-4o-2024-11-20 - openai/gpt-4o-2024-08-06 - openai/gpt-4o-mini-2024-07-18 - openai/gpt-4o-2024-05-13 - anthropic/claude-haiku-5.5 - openai/gpt-4 - anthropic/claude-sonnet-5.5 - openai/gpt-6.1-sol-pro - openai/gpt-6.1-sol - openai/gpt-6-luna-pro - openai/gpt-6-luna - openai/gpt-6-sol-pro - openai/gpt-6-sol - deepseek/deepseek-v4.1-flash - openai/gpt-6-astra - x-ai/grok-4.7 - openai/gpt-6-astra-pro - google/gemini-3.8-flash - anthropic/claude-fable-5.1 - google/gemini-3.7-flash - openai/gpt-5-mini - deepseek/deepseek-v4-flash-vision-exp - deepseek/deepseek-v4-pro-0813 - x-ai/grok-4.6 - deepseek/deepseek-v4-flash-0731 - anthropic/claude-opus-5 - google/gemini-3.6-flash - google/gemini-3.5-flash-lite - deepseek/deepseek-v4-pro - openai/gpt-5.2-codex - deepseek/deepseek-v3.2 - deepseek/deepseek-v3.1-terminus - deepseek/deepseek-r1 - openai/o3-mini - openai/gpt-4o-mini - openai/gpt-3.5-turbo - null is_active: type: boolean description: Whether the agent prompt is active. required: - type - prompt - is_active title: AgentPromptStoreRequest AgentPromptResource: type: object properties: id: type: integer tenant_id: type: - integer - 'null' type: type: string type_label: type: - string - 'null' language: type: string llm_model: type: - string - 'null' prompt: type: string is_active: type: boolean can_activate: type: boolean description: >- Whether this agent type may be activated in the tenant's current conversation mode. activation_restriction_reason: type: - string - 'null' description: >- Why this agent type cannot be activated in the current mode; null when it can. stable_version_id: type: - integer - 'null' tenant: $ref: '#/components/schemas/RelatedTenantResource' created_at: type: - string - 'null' format: date-time updated_at: type: - string - 'null' format: date-time deleted_at: type: - string - 'null' format: date-time required: - id - tenant_id - type - type_label - language - llm_model - prompt - is_active - can_activate - activation_restriction_reason - stable_version_id - created_at - updated_at - deleted_at title: AgentPromptResource Language: type: string enum: - tr - en title: Language RelatedTenantResource: type: object properties: id: type: integer name: type: string required: - id - name title: RelatedTenantResource responses: AuthenticationException: description: Unauthenticated content: application/json: schema: type: object properties: message: type: string description: Error overview. required: - message AuthorizationException: description: Authorization error content: application/json: schema: type: object properties: message: type: string description: Error overview. required: - message ValidationException: description: Validation error content: application/json: schema: type: object properties: message: type: string description: Errors overview. errors: type: object description: A detailed description of each field that failed validation. additionalProperties: type: array items: type: string required: - message - errors securitySchemes: oauth2: type: oauth2 flows: authorizationCode: authorizationUrl: https://dev.flextell.ai/oauth/authorize tokenUrl: https://dev.flextell.ai/oauth/token scopes: '*': all bearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.