> ## Documentation Index > Fetch the complete documentation index at: https://docs.seekr.com/llms.txt > Use this file to discover all available pages before exploring further. # Create completion > Generate a text completion response from a deployed model. ## OpenAPI ````yaml post /v1/inference/completions openapi: 3.1.0 info: title: SeekrFlow API description: SeekrFlow API Documentation termsOfService: http://www.seekr.com/support contact: name: Seekr API Support url: http://www.seekr.com/contact email: contact@seekr.com version: 5.48.1 servers: - url: https://flow.seekr.com description: SeekrBuild server base URL security: [] paths: /v1/inference/completions: post: tags: - Inference summary: Create a completion operationId: route_completion_v1_inference_completions_post requestBody: content: application/json: schema: $ref: '#/components/schemas/CompletionRequest' example: model: meta-llama/Llama-3.1-8B-Instruct prompt: The capital of France is max_tokens: 32 temperature: 0.7 stream: false required: true responses: '200': description: Successful response. content: application/json: schema: $ref: '#/components/schemas/CompletionResponse' text/event-stream: schema: allOf: - $ref: '#/components/schemas/CompletionStreamResponse' description: >- Sent as server-sent events. The body is a sequence of `data: ` lines separated by blank lines and terminated by `data: [DONE]`, where each `` is an object of the shape below. '400': description: Malformed request body, or `model` missing. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '401': description: Missing or invalid API key. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '403': description: >- The requested model is not a base model and is not deployed for your team. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '422': description: Deployment not found, or the request is unprocessable. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '429': description: Rate limit exceeded. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '502': description: Backend disconnected before sending a response. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse '503': description: No healthy backend available for the requested model. content: application/json: schema: oneOf: - properties: error: properties: message: type: string type: type: string code: type: integer param: type: string nullable: true type: object required: - message type: object required: - error title: StructuredError - properties: error: type: string type: object required: - error title: SimpleError title: ErrorResponse security: - APIKeyHeader: [] components: schemas: CompletionRequest: additionalProperties: true properties: model: anyOf: - type: string - type: 'null' default: null title: Model prompt: anyOf: - items: minimum: 0 type: integer type: array - items: items: minimum: 0 type: integer type: array type: array - type: string - items: type: string type: array - type: 'null' default: null title: Prompt echo: anyOf: - type: boolean - type: 'null' default: false title: Echo frequency_penalty: anyOf: - type: number - type: 'null' default: 0 title: Frequency Penalty logit_bias: anyOf: - additionalProperties: type: number type: object - type: 'null' default: null title: Logit Bias logprobs: anyOf: - type: integer - type: 'null' default: null title: Logprobs max_tokens: anyOf: - type: integer - type: 'null' default: 16 title: Max Tokens 'n': default: 1 title: 'N' type: integer presence_penalty: anyOf: - type: number - type: 'null' default: 0 title: Presence Penalty seed: anyOf: - maximum: 9223372036854776000 minimum: -9223372036854776000 type: integer - type: 'null' default: null title: Seed stop: anyOf: - type: string - items: type: string type: array - type: 'null' default: [] title: Stop stream: anyOf: - type: boolean - type: 'null' default: false title: Stream stream_options: anyOf: - $ref: '#/components/schemas/StreamOptions' - type: 'null' default: null suffix: anyOf: - type: string - type: 'null' default: null title: Suffix temperature: anyOf: - type: number - type: 'null' default: null title: Temperature top_p: anyOf: - type: number - type: 'null' default: null title: Top P user: anyOf: - type: string - type: 'null' default: null title: User use_beam_search: default: false title: Use Beam Search type: boolean top_k: anyOf: - type: integer - type: 'null' default: null title: Top K min_p: anyOf: - type: number - type: 'null' default: null title: Min P repetition_penalty: anyOf: - type: number - type: 'null' default: null title: Repetition Penalty length_penalty: default: 1 title: Length Penalty type: number stop_token_ids: anyOf: - items: type: integer type: array - type: 'null' default: [] title: Stop Token Ids include_stop_str_in_output: default: false title: Include Stop Str In Output type: boolean ignore_eos: default: false title: Ignore Eos type: boolean min_tokens: default: 0 title: Min Tokens type: integer skip_special_tokens: default: true title: Skip Special Tokens type: boolean spaces_between_special_tokens: default: true title: Spaces Between Special Tokens type: boolean truncate_prompt_tokens: anyOf: - maximum: 9223372036854776000 minimum: -1 type: integer - type: 'null' default: null title: Truncate Prompt Tokens truncation_side: anyOf: - enum: - left - right type: string - type: 'null' default: null description: >- Which side to truncate from when truncate_prompt_tokens is active. 'right' keeps the first N tokens. 'left' keeps the last N tokens. title: Truncation Side allowed_token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null title: Allowed Token Ids prompt_logprobs: anyOf: - type: integer - type: 'null' default: null title: Prompt Logprobs logprob_token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null description: >- Specific vocab token IDs to return logprobs for at each generated position, in addition to the sampled token. Requires `logprobs` to be set. title: Logprob Token Ids bad_words: items: type: string title: Bad Words type: array add_special_tokens: default: true description: >- If true (the default), special tokens (e.g. BOS) will be added to the prompt. title: Add Special Tokens type: boolean response_format: anyOf: - $ref: '#/components/schemas/ResponseFormat' - $ref: '#/components/schemas/StructuralTagResponseFormat' - $ref: '#/components/schemas/LegacyStructuralTagResponseFormat' - type: 'null' default: null description: >- Similar to chat completion, this parameter specifies the format of output. Only {'type': 'json_object'}, {'type': 'json_schema'}, {'type': 'structural_tag'}, or {'type': 'text'} is supported. title: Response Format structured_outputs: anyOf: - $ref: '#/components/schemas/StructuredOutputsParams' - type: 'null' default: null description: Additional kwargs for structured outputs priority: default: 0 description: >- The priority of the request (lower means earlier handling; default: 0). Any priority other than 0 will raise an error if the served model does not use priority scheduling. maximum: 9223372036854776000 minimum: -9223372036854776000 title: Priority type: integer request_id: anyOf: - type: string - type: 'null' default: null description: >- The request_id related to this request. If the caller does not set it, a random uuid will be generated. title: Request Id return_tokens_as_token_ids: anyOf: - type: boolean - type: 'null' default: null description: >- If specified with 'logprobs', tokens are represented as strings of the form 'token_id:{token_id}' so that tokens that are not JSON-encodable can be identified. title: Return Tokens As Token Ids return_token_ids: anyOf: - type: boolean - type: 'null' default: null description: >- If specified, the result will include token IDs alongside the generated text. title: Return Token Ids cache_salt: anyOf: - type: string - type: 'null' default: null description: >- If specified, the prefix cache will be salted with the provided string to prevent an attacker from guessing prompts in multi-user environments. title: Cache Salt kv_transfer_params: anyOf: - additionalProperties: true type: object - type: 'null' default: null description: KVTransfer parameters used for disaggregated serving. title: Kv Transfer Params vllm_xargs: anyOf: - additionalProperties: anyOf: - type: string - type: integer - type: number - items: anyOf: - type: string - type: integer - type: number type: array type: object - type: 'null' default: null description: >- Additional request parameters with (list of) string or numeric values, used by custom extensions. title: Vllm Xargs repetition_detection: anyOf: - $ref: '#/components/schemas/RepetitionDetectionParams' - type: 'null' default: null description: >- Parameters for detecting repetitive N-gram patterns in output tokens. If such repetition is detected, generation ends early. thinking_token_budget: anyOf: - type: integer - type: 'null' default: null description: >- Maximum number of tokens allowed for thinking operations (reasoning models). Non-negative integer sets the limit; -1 means unlimited (treated as unset). title: Thinking Token Budget title: CompletionRequest type: object CompletionResponse: additionalProperties: true properties: id: type: string title: Id object: const: text_completion default: text_completion title: Object type: string created: type: integer title: Created model: title: Model type: string choices: items: $ref: '#/components/schemas/CompletionResponseChoice' title: Choices type: array service_tier: anyOf: - enum: - auto - default - flex - scale - priority type: string - type: 'null' default: null title: Service Tier system_fingerprint: anyOf: - type: string - type: 'null' default: null title: System Fingerprint usage: $ref: '#/components/schemas/UsageInfo' kv_transfer_params: anyOf: - additionalProperties: true type: object - type: 'null' default: null title: Kv Transfer Params metrics: anyOf: - $ref: '#/components/schemas/PerRequestTimingMetrics' - type: 'null' default: null required: - id - created - model - choices - usage title: CompletionResponse type: object CompletionStreamResponse: additionalProperties: true properties: id: type: string title: Id object: default: text_completion title: Object type: string created: type: integer title: Created model: title: Model type: string choices: items: $ref: '#/components/schemas/CompletionResponseStreamChoice' title: Choices type: array usage: anyOf: - $ref: '#/components/schemas/UsageInfo' - type: 'null' default: null system_fingerprint: anyOf: - type: string - type: 'null' default: null title: System Fingerprint metrics: anyOf: - $ref: '#/components/schemas/PerRequestTimingMetrics' - type: 'null' default: null required: - id - created - model - choices title: CompletionStreamResponse type: object StreamOptions: additionalProperties: true properties: include_usage: anyOf: - type: boolean - type: 'null' default: false title: Include Usage continuous_usage_stats: anyOf: - type: boolean - type: 'null' default: false title: Continuous Usage Stats title: StreamOptions type: object ResponseFormat: additionalProperties: true properties: type: enum: - text - json_object - json_schema title: Type type: string json_schema: anyOf: - $ref: '#/components/schemas/JsonSchemaResponseFormat' - type: 'null' default: null required: - type title: ResponseFormat type: object StructuralTagResponseFormat: additionalProperties: true properties: type: const: structural_tag title: Type type: string format: title: Format required: - type - format title: StructuralTagResponseFormat type: object LegacyStructuralTagResponseFormat: additionalProperties: true properties: type: const: structural_tag title: Type type: string structures: items: $ref: '#/components/schemas/LegacyStructuralTag' title: Structures type: array triggers: items: type: string title: Triggers type: array required: - type - structures - triggers title: LegacyStructuralTagResponseFormat type: object StructuredOutputsParams: additionalProperties: true description: Structured-output constraints. Exactly one constraint may be set. properties: json: anyOf: - type: string - additionalProperties: true type: object - type: 'null' default: null title: Json regex: anyOf: - type: string - type: 'null' default: null title: Regex choice: anyOf: - items: type: string type: array - type: 'null' default: null title: Choice grammar: anyOf: - type: string - type: 'null' default: null title: Grammar json_object: anyOf: - type: boolean - type: 'null' default: null title: Json Object disable_any_whitespace: default: false title: Disable Any Whitespace type: boolean disable_additional_properties: default: false title: Disable Additional Properties type: boolean whitespace_pattern: anyOf: - type: string - type: 'null' default: null title: Whitespace Pattern structural_tag: anyOf: - type: string - type: 'null' default: null title: Structural Tag title: StructuredOutputsParams type: object RepetitionDetectionParams: additionalProperties: true description: Parameters for detecting repetitive N-gram patterns in output tokens. properties: max_pattern_size: default: 0 description: >- Maximum size of N-gram pattern to detect for sequence repetition. Set to 0 to disable. Must be used together with min_count. title: Max Pattern Size type: integer min_pattern_size: default: 0 description: >- Minimum N-gram pattern size to check for sequence repetition. If set to 0, it defaults to 1. Must be <= max_pattern_size. title: Min Pattern Size type: integer min_count: default: 0 description: >- Minimum number of times an N-gram pattern must repeat to trigger detection. Must be >= 2. title: Min Count type: integer title: RepetitionDetectionParams type: object CompletionResponseChoice: additionalProperties: true properties: index: type: integer title: Index text: title: Text type: string logprobs: anyOf: - $ref: '#/components/schemas/CompletionLogProbs' - type: 'null' default: null finish_reason: anyOf: - type: string - type: 'null' default: null title: Finish Reason stop_reason: anyOf: - type: integer - type: string - type: 'null' default: null description: >- The stop string or token id that caused the completion to stop, null if the completion finished for some other reason including encountering the EOS token title: Stop Reason token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null title: Token Ids prompt_logprobs: anyOf: - items: anyOf: - additionalProperties: true type: object - type: 'null' type: array - type: 'null' default: null title: Prompt Logprobs prompt_token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null title: Prompt Token Ids required: - index - text title: CompletionResponseChoice type: object UsageInfo: additionalProperties: true properties: prompt_tokens: default: 0 title: Prompt Tokens type: integer total_tokens: default: 0 title: Total Tokens type: integer completion_tokens: anyOf: - type: integer - type: 'null' default: 0 title: Completion Tokens prompt_tokens_details: anyOf: - $ref: '#/components/schemas/PromptTokenUsageInfo' - type: 'null' default: null title: UsageInfo type: object PerRequestTimingMetrics: additionalProperties: true properties: time_to_first_token_ms: anyOf: - type: number - type: 'null' default: null title: Time To First Token Ms generation_time_ms: anyOf: - type: number - type: 'null' default: null title: Generation Time Ms queue_time_ms: anyOf: - type: number - type: 'null' default: null title: Queue Time Ms mean_itl_ms: anyOf: - type: number - type: 'null' default: null title: Mean Itl Ms tokens_per_second: anyOf: - type: number - type: 'null' default: null title: Tokens Per Second title: PerRequestTimingMetrics type: object CompletionResponseStreamChoice: additionalProperties: true properties: index: type: integer title: Index text: title: Text type: string logprobs: anyOf: - $ref: '#/components/schemas/CompletionLogProbs' - type: 'null' default: null finish_reason: anyOf: - type: string - type: 'null' default: null title: Finish Reason stop_reason: anyOf: - type: integer - type: string - type: 'null' default: null title: Stop Reason prompt_token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null title: Prompt Token Ids token_ids: anyOf: - items: type: integer type: array - type: 'null' default: null title: Token Ids required: - index - text title: CompletionResponseStreamChoice type: object JsonSchemaResponseFormat: additionalProperties: true properties: name: type: string title: Name description: anyOf: - type: string - type: 'null' default: null title: Description schema: anyOf: - additionalProperties: true type: object - type: 'null' default: null title: Schema strict: anyOf: - type: boolean - type: 'null' default: null title: Strict required: - name title: JsonSchemaResponseFormat type: object LegacyStructuralTag: additionalProperties: true properties: begin: title: Begin type: string schema: anyOf: - additionalProperties: true type: object - type: 'null' default: null title: Schema end: title: End type: string required: - begin - end title: LegacyStructuralTag type: object CompletionLogProbs: additionalProperties: true properties: text_offset: items: type: integer title: Text Offset type: array token_logprobs: items: anyOf: - type: number - type: 'null' title: Token Logprobs type: array tokens: items: type: string title: Tokens type: array top_logprobs: items: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Top Logprobs type: array title: CompletionLogProbs type: object PromptTokenUsageInfo: additionalProperties: true properties: cached_tokens: anyOf: - type: integer - type: 'null' default: null title: Cached Tokens created_cache_tokens: anyOf: - type: integer - type: 'null' default: null title: Created Cache Tokens multimodal_tokens: anyOf: - additionalProperties: type: integer type: object - type: 'null' default: null description: >- Prompt tokens contributed by each input modality, keyed by modality name (e.g. `image`, `audio`, `video`). A breakdown of the multimodal placeholder tokens already counted in `prompt_tokens`; null when the request has no multimodal input. title: Multimodal Tokens title: PromptTokenUsageInfo type: object securitySchemes: APIKeyHeader: type: apiKey description: >- Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix. in: header name: Authorization ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.