> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create completion > For sending requests to legacy completion models ## OpenAPI ````yaml post /v2/router/completions openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - name: Guardrail Rules - name: Policies - name: Routing Rules - name: Files description: File upload and retrieval operations. - name: FilesService - name: Projects description: Projects organize resources within a workspace - name: ProjectsService - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: SkillsService - name: Responses - description: >- Run agents on a cadence — cron, interval, or one-off. Minimum firing interval is 1 hour. name: Agent Schedules - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: ReportingService description: |- ReportingService exposes a single QueryReport RPC that maps allowlisted analytics payloads onto safe rollup queries. Callers never send SQL; the backend picks the rollup family and grain from the metric catalogue, the requested range, and the requested grouping. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/router/completions: post: tags: - Completions summary: Create completion description: For sending requests to legacy completion models operationId: createCompletion requestBody: required: true content: application/json: schema: allOf: - type: object properties: model: type: string description: ID of the model to use prompt: type: string description: >- The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. echo: type: - boolean - 'null' default: false description: Echo back the prompt in addition to the completion frequency_penalty: type: - number - 'null' default: 0 description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. max_tokens: type: - number - 'null' default: 16 description: >- The maximum number of tokens that can be generated in the completion. presence_penalty: type: - number - 'null' minimum: -2 maximum: 2 default: 0 description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. seed: type: - number - 'null' description: >- If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. stop: anyOf: - type: string - type: array items: type: string - type: 'null' default: null description: >- Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. temperature: type: - number - 'null' default: 1 description: >- 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. top_p: type: - number - 'null' default: 1 description: >- 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. 'n': type: - number - 'null' default: 1 description: >- How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. user: type: string description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. name: type: string description: >- The name to display on the trace. If not specified, the default system name will be used. fallbacks: type: array items: type: object properties: model: type: string description: Fallback model identifier required: - model description: Array of fallback models to use if primary model fails retry: type: object properties: count: type: number minimum: 1 maximum: 5 default: 3 description: Number of retry attempts (1-5) example: 3 on_codes: type: array items: type: number minimum: 100 maximum: 599 minItems: 1 default: - 429 description: HTTP status codes that trigger retry logic example: - 429 - 500 - 502 - 503 - 504 description: Retry configuration for the request cache: type: object properties: ttl: type: number minimum: 1 maximum: 259200 default: 1800 description: >- Time to live for cached responses in seconds. Maximum 259200 seconds (3 days). example: 3600 type: type: string enum: - exact_match required: - type description: Cache configuration for the request. load_balancer: oneOf: - type: object properties: type: type: string enum: - weight_based models: type: array items: type: object properties: model: type: string description: Model identifier for load balancing example: openai/gpt-4o weight: type: number minimum: 0.001 maximum: 1 default: 0.5 description: >- Weight assigned to this model for load balancing example: 0.7 required: - model required: - type - models description: Load balancer configuration for the request. timeout: type: object properties: call_timeout: type: number minimum: 1 description: Timeout value in milliseconds example: 30000 required: - call_timeout description: >- Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured. thinking: oneOf: - $ref: '#/components/schemas/ThinkingConfigDisabledSchema' - $ref: '#/components/schemas/ThinkingConfigEnabledSchema' - $ref: '#/components/schemas/ThinkingConfigAdaptiveSchema' - type: 'null' description: >- Configuration for the thinking mode capability. Set type to `adaptive` for models that support adaptive thinking (e.g. Claude Opus 4.6, Sonnet 4.6), or `enabled` with `budget_tokens` for manual control. orq: type: object properties: name: type: string description: >- The name to display on the trace. If not specified, the default system name will be used. retry: type: object properties: count: type: number minimum: 1 maximum: 5 default: 3 description: Number of retry attempts (1-5) example: 3 on_codes: type: array items: type: number minimum: 100 maximum: 599 minItems: 1 default: - 429 description: HTTP status codes that trigger retry logic example: - 429 - 500 - 502 - 503 - 504 description: Retry configuration for the request fallbacks: type: array items: type: object properties: model: type: string description: Fallback model identifier example: openai/gpt-4o-mini required: - model description: >- Array of fallback models to use if primary model fails prompt: type: object properties: id: type: string description: Unique identifier of the prompt to use example: prompt_01ARZ3NDEKTSV4RRFFQ69G5FAV version: type: string enum: - latest description: >- Version of the prompt to use (currently only "latest" supported) example: latest required: - id - version description: Prompt configuration for the request identity: $ref: '#/components/schemas/PublicIdentity' contact: $ref: '#/components/schemas/PublicContact' thread: type: object properties: id: type: string description: >- Unique thread identifier to group related invocations. example: thread_01ARZ3NDEKTSV4RRFFQ69G5FAV tags: type: array items: type: string description: >- Optional tags to differentiate or categorize threads example: - customer-support - priority-high required: - id description: Thread information to group related requests inputs: anyOf: - type: object additionalProperties: {} - type: array items: type: object properties: key: type: string value: {} is_pii: type: boolean required: - key deprecated: true description: >- @deprecated Use top-level `variables` field instead. Values to replace in the prompt messages using {{variableName}} syntax. example: customer_name: John Smith product_name: Premium Plan issue_type: billing cache: type: object properties: ttl: type: number minimum: 1 maximum: 259200 default: 1800 description: >- Time to live for cached responses in seconds. Maximum 259200 seconds (3 days). example: 3600 type: type: string enum: - exact_match required: - type description: Cache configuration for the request. knowledge_bases: type: array items: type: object properties: top_k: type: integer minimum: 1 maximum: 100 description: >- The number of results to return. If not provided, will default to the knowledge base configured `top_k`. threshold: type: number minimum: 0 maximum: 1 description: >- The threshold to apply to the search. If not provided, will default to the knowledge base configured `threshold` search_type: type: string enum: - vector_search - keyword_search - hybrid_search default: hybrid_search description: >- The type of search to perform. If not provided, will default to the knowledge base configured `retrieval_type` filter_by: anyOf: - type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists title: Search operator - type: object properties: and: type: array items: type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists required: - and title: and description: And - type: object properties: or: type: array items: type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists required: - or title: or description: Or description: >- The metadata filter to apply to the search. Check the [Searching a Knowledge Base](https://docs.orq.ai/docs/knowledge/api#knowledge-base-search) for more information. search_options: type: object properties: include_vectors: type: boolean description: Whether to include the vector in the chunk include_metadata: type: boolean description: >- Whether to include the metadata in the chunk include_scores: type: boolean description: Whether to include the scores in the chunk description: Additional search options rerank_config: type: object properties: model: type: string description: >- The name of the rerank model to use. Refer to the [model list](https://docs.orq.ai/docs/proxy#/rerank-models). example: cohere/rerank-multilingual-v3.0 threshold: type: number minimum: 0 maximum: 1 default: 0 description: >- The threshold value used to filter the rerank results, only documents with a relevance score greater than the threshold will be returned top_k: type: integer minimum: 1 maximum: 100 default: 10 description: >- The number of top results to return after reranking. If not provided, will default to the knowledge base configured `top_k`. required: - model description: >- Override the rerank configuration for this search. If not provided, will use the knowledge base configured rerank settings. agentic_rag_config: type: object properties: model: type: string description: >- The name of the model for the Agent to use. Refer to the [model list](https://docs.orq.ai/docs/proxy#/chat-models). required: - model description: >- Override the agentic RAG configuration for this search. If not provided, will use the knowledge base configured agentic RAG settings. knowledge_id: type: string description: >- Unique identifier of the knowledge base to search example: customer-knowledge-base query: type: string description: >- The query to use to search the knowledge base. If not provided we will use the last user message from the messages of the requests required: - knowledge_id load_balancer: oneOf: - type: object properties: type: type: string enum: - weight_based models: type: array items: type: object properties: model: type: string description: Model identifier for load balancing example: openai/gpt-4o weight: type: number minimum: 0.001 maximum: 1 default: 0.5 description: >- Weight assigned to this model for load balancing example: 0.7 required: - model required: - type - models description: >- Array of models with weights for load balancing requests example: type: weight_based models: - model: openai/gpt-4o weight: 0.7 - model: anthropic/claude-3-5-sonnet weight: 0.3 timeout: type: object properties: call_timeout: type: number minimum: 1 description: Timeout value in milliseconds example: 30000 required: - call_timeout description: >- Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured. description: >- Leverage Orq's intelligent routing capabilities to enhance your AI application with enterprise-grade reliability and observability. Orq provides automatic request management including retries on failures, model fallbacks for high availability, identity-level analytics tracking, conversation threading, and dynamic prompt templating with variable substitution. deprecated: true example: retry: count: 3 on_codes: - 429 - 500 - 502 fallbacks: - model: openai/gpt-5 - model: anthropic/claude-4-opus identity: id: identity_01ARZ3NDEKTSV4RRFFQ69G5FAV display_name: Jane Doe email: jane.doe@example.com thread: id: thread_01ARZ3NDEKTSV4RRFFQ69G5FAV tags: - customer-support inputs: customer_name: John Smith issue_type: billing cache: ttl: 3600 type: exact_match knowledge_bases: - knowledge_id: knowledge_01ARZ3NDEKTSV4RRFFQ69G5FAV top_k: 5 timeout: call_timeout: 30000 required: - model - prompt - type: object properties: stream: type: boolean default: false responses: '200': description: Represents a completion response from the API. content: application/json: schema: type: object properties: id: type: string description: A unique identifier for the completion. choices: type: array items: type: object properties: finish_reason: type: string enum: - stop - length - content_filter - tool_calls description: The reason the model stopped generating tokens. index: type: number description: The index of the choice in the list of choices. text: type: string required: - finish_reason - index - text description: >- The list of completion choices the model generated for the input prompt. created: anyOf: - type: string - type: number description: >- The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. system_fingerprint: type: string description: >- This fingerprint represents the backend configuration that the model runs with. object: type: string description: The object type usage: type: object properties: completion_tokens: type: number description: Number of tokens in the generated completion. prompt_tokens: type: number description: Number of tokens in the prompt. total_tokens: type: number description: >- Total number of tokens used in the request (prompt + completion). prompt_tokens_details: type: - object - 'null' properties: cached_tokens: type: - integer - 'null' cache_creation_tokens: type: - integer - 'null' audio_tokens: type: - integer - 'null' description: >- The number of audio input tokens consumed by the request. completion_tokens_details: type: - object - 'null' properties: reasoning_tokens: type: - number - 'null' accepted_prediction_tokens: type: - number - 'null' rejected_prediction_tokens: type: - number - 'null' audio_tokens: type: - integer - 'null' description: >- The number of audio output tokens produced by the response. description: Usage statistics for the completion request. required: - id - choices - model - object text/event-stream: schema: type: object properties: id: type: string description: A unique identifier for the completion. choices: type: array items: type: object properties: finish_reason: type: string enum: - stop - length - content_filter - tool_calls description: The reason the model stopped generating tokens. index: type: number description: The index of the choice in the list of choices. text: type: string required: - finish_reason - index - text description: >- The list of completion choices the model generated for the input prompt. created: anyOf: - type: string - type: number description: >- The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. system_fingerprint: type: string description: >- This fingerprint represents the backend configuration that the model runs with. object: type: string description: The object type usage: type: object properties: completion_tokens: type: number description: Number of tokens in the generated completion. prompt_tokens: type: number description: Number of tokens in the prompt. total_tokens: type: number description: >- Total number of tokens used in the request (prompt + completion). prompt_tokens_details: type: - object - 'null' properties: cached_tokens: type: - integer - 'null' cache_creation_tokens: type: - integer - 'null' audio_tokens: type: - integer - 'null' description: >- The number of audio input tokens consumed by the request. completion_tokens_details: type: - object - 'null' properties: reasoning_tokens: type: - number - 'null' accepted_prediction_tokens: type: - number - 'null' rejected_prediction_tokens: type: - number - 'null' audio_tokens: type: - integer - 'null' description: >- The number of audio output tokens produced by the response. description: Usage statistics for the completion request. required: - id - choices - model - object components: schemas: ThinkingConfigDisabledSchema: type: object properties: type: type: string enum: - disabled description: Disables the thinking mode capability required: - type title: Thinking config disabled description: Disables the thinking mode capability ThinkingConfigEnabledSchema: type: object properties: type: type: string enum: - enabled description: Enables or disables the thinking mode capability budget_tokens: type: number description: >- Determines how many tokens the model can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. thinking_level: type: string enum: - low - medium - high description: >- The level of reasoning the model should use. This setting is supported only by `gemini-3` models. If budget_tokens is specified and `thinking_level` is available, `budget_tokens` will be ignored. required: - type - budget_tokens title: Thinking config enabled description: Enables the thinking mode capability ThinkingConfigAdaptiveSchema: type: object properties: type: type: string enum: - adaptive description: >- Lets the model dynamically determine when and how much to use extended thinking based on the complexity of each request. Supported on Claude Opus 4.6 and Sonnet 4.6. required: - type title: Thinking config adaptive description: >- Enables adaptive thinking mode where the model dynamically determines thinking depth PublicIdentity: type: object properties: id: type: string description: Unique identifier for the contact example: contact_01ARZ3NDEKTSV4RRFFQ69G5FAV display_name: type: string description: Display name of the contact example: Jane Doe email: type: string format: email description: Email address of the contact example: jane.doe@example.com metadata: type: array items: type: object additionalProperties: {} description: >- A hash of key/value pairs containing any other data about the contact example: - department: Engineering role: Senior Developer logo_url: type: string description: URL to the contact's avatar or logo example: https://example.com/avatars/jane-doe.jpg tags: type: array items: type: string description: A list of tags associated with the contact example: - hr - engineering required: - id description: >- Information about the identity making the request. If the identity does not exist, it will be created automatically. PublicContact: type: object properties: id: type: string description: Unique identifier for the contact example: contact_01ARZ3NDEKTSV4RRFFQ69G5FAV display_name: type: string description: Display name of the contact example: Jane Doe email: type: string format: email description: Email address of the contact example: jane.doe@example.com metadata: type: array items: type: object additionalProperties: {} description: >- A hash of key/value pairs containing any other data about the contact example: - department: Engineering role: Senior Developer logo_url: type: string description: URL to the contact's avatar or logo example: https://example.com/avatars/jane-doe.jpg tags: type: array items: type: string description: A list of tags associated with the contact example: - hr - engineering required: - id description: >- @deprecated Use identity instead. Information about the contact making the request. deprecated: true securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````