> ## Documentation Index > Fetch the complete documentation index at: https://docs.tokensmind.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create completion ## OpenAPI ````yaml create-completion.yaml POST /v1/completions openapi: 3.0.1 info: title: '' version: 1.0.0 servers: - url: https://tokensmind.ai description: Production security: - bearer: [] paths: /v1/completions: post: tags: [] summary: Native OpenAI format description: Generates a model completion from the given prompt and parameters operationId: createCompletion parameters: - name: Content-Type in: header description: '' required: true example: application/json schema: type: string - name: Authorization in: header description: '' required: true example: 'Bearer authentication: Bearer {{API key}}.' schema: type: string requestBody: content: application/json: schema: type: object x-apifox-refs: {} x-apifox-orders: - model - prompt - stream - stream_options - max_tokens - 'n' - seed - frequency_penalty - presence_penalty - repetition_penalty - stop - temperature - top_p - top_k - min_p - logit_bias - logprobs - best_of - 01KP5NABP505Q46C0NW8XXAPCD properties: model: type: string description: >- Model name to use. See the model catalog on [TokensMind AI](https://tokensmind.ai/pricing) for available names prompt: type: string description: > Prompt used to generate the completion (may be a string, array of strings, array of tokens, or array of token arrays). max_tokens: type: integer description: >- Maximum number of tokens to generate. The sum of prompt tokens and max_tokens must not exceed the model's context length. temperature: type: number description: > Sampling temperature; default is 1, between 0 and 2. Higher values (e.g. 0.8) make output more random; lower values (e.g. 0.2) make it more focused and deterministic. We generally recommend changing either this or top_p, not both. minimum: 0 maximum: 2 nullable: true top_p: type: number minimum: 0 maximum: 1 exclusiveMinimum: true description: >- An alternative to temperature, called nucleus sampling: the model considers tokens whose cumulative probability mass is top_p. So 0.1 means only the top 10% probability mass is considered. We generally recommend changing either this or temperature, not both. nullable: true 'n': type: integer description: > Note: This parameter can generate many completions and may consume your token quota quickly. Use with care and set max_tokens and stop to reasonable values. minimum: 0 maximum: 128 exclusiveMinimum: true exclusiveMaximum: true nullable: true stream: type: boolean description: > Whether to stream tokens. Defaults to false. When enabled, tokens are sent as data-only server-sent events (SSE), ending with a data: [DONE] message. nullable: true stop: type: string description: >- Up to 4 sequences where the API will stop generating further tokens. Returned text includes the stop sequence. stream_options: type: object properties: include_usage: type: boolean description: > When set, an additional chunk is streamed before the data: [DONE] message. That chunk's usage field shows token usage for the entire request, while choices is always an empty array. Other chunks may also include a usage field set to null. x-apifox-orders: - include_usage description: | Streaming options. Only set when stream is true. required: - include_usage seed: type: integer description: >- If specified, the system will try to sample deterministically so repeated requests with the same seed and parameters return the same result. nullable: true frequency_penalty: type: number description: > Default 0. Positive values penalize new tokens based on their frequency in the text so far, reducing repetition. For mild repetition reduction, try roughly 0.1 to 1. For strong suppression, you can increase toward 2, but quality may drop. Negative values encourage repetition. See also presence_penalty for a fixed penalty on tokens that appear at least once default: 0 minimum: -2 maximum: 2 exclusiveMinimum: true exclusiveMaximum: true nullable: true presence_penalty: type: number description: >- Default 0. Positive values penalize new tokens based on whether they appear in the text so far, encouraging new topics. For mild repetition reduction, try roughly 0.1 to 1. For strong suppression, you can increase toward 2, but quality may drop significantly. Negative values encourage repetition. See also frequency_penalty for frequency-based penalization minimum: -2 maximum: 2 exclusiveMinimum: true exclusiveMaximum: true nullable: true repetition_penalty: type: number description: >- Penalty applied to repeated tokens to discourage or encourage repetition. 1.0 means no penalty and free repetition. Values above 1.0 penalize repetition. Values between 0.0 and 1.0 reward repetition. A balanced value is often around 1.2. On decoder-only models, the penalty applies to both the prompt and the generated output. minimum: 0 maximum: 2 exclusiveMinimum: true exclusiveMaximum: true nullable: true top_k: type: number minimum: 1 maximum: 128 exclusiveMinimum: true exclusiveMaximum: true description: >- Top-k sampling keeps only the k most likely next tokens and redistributes probability mass among them. k controls how many candidates are considered per step. nullable: true min_p: type: number description: > Minimum relative probability for a token to be considered, compared to the most likely token. nullable: true logit_bias: type: object properties: {} x-apifox-orders: [] description: > Defaults to null. Modifies likelihood of specified tokens in the completion. Accepts a JSON object mapping token IDs to bias values from -100 to 100. 01KP5NABP505Q46C0NW8XXAPCD: x-tmp-pending-properties: true logprobs: type: integer description: > Returns log probabilities for the top logprobs output tokens at each step, including the probability of the selected token. For example, if logprobs is 5, the API returns the top 5 tokens' logprobs per step. The maximum value for logprobs is 5. nullable: true best_of: type: integer description: > Defaults to 1. Generates best_of completions on the server and returns the "best" one (highest per-token log probability). Cannot be used with streaming. When used with n, best_of is the number of candidate completions and n is how many to return. best_of must be greater than n. Note: This can consume your token quota quickly. Use with care and set max_tokens and stop reasonably. required: - model - prompt - best_of example: |- curl --request POST \ --url https: //api.jiekou.ai/openai/v1/completions \ --header 'Authorization: ' \ --header 'Content-Type: ' \ --data ' { "model": "", "prompt": "", "max_tokens": 123, "stream": {}, "stream_options": { "include_usage": true }, "n": {}, "seed": {}, "frequency_penalty": {}, "presence_penalty": {}, "repetition_penalty": {}, "stop": {}, "temperature": {}, "top_p": {}, "top_k": {}, "min_p": {}, "logit_bias": {}, "logprobs": {}, "best_of": 123 } ' required: true responses: '200': description: Completion created successfully content: application/json: schema: $ref: '#/components/schemas/CompletionResponse' example: choices: - finish_reason: index: 123 logprobs: text_offset: - {} token_logprobs: - {} tokens: - {} top_logprobs: - '{key}': 123 text: created: 123 id: model: object: usage: completion_tokens: 123 prompt_tokens: 123 total_tokens: 123 headers: {} x-apifox-name: Success x-apifox-ordering: 0 deprecated: false security: [] components: schemas: CompletionResponse: type: object properties: id: type: string object: type: string example: text_completion created: type: integer model: type: string choices: type: array items: type: object properties: text: type: string index: type: integer finish_reason: type: string x-apifox-orders: - text - index - finish_reason x-apifox-ignore-properties: [] usage: $ref: '#/components/schemas/Usage' x-apifox-orders: - id - object - created - model - choices - usage x-apifox-ignore-properties: [] x-apifox-folder: '' Usage: type: object properties: prompt_tokens: type: integer description: Prompt tokens completion_tokens: type: integer description: Completion tokens total_tokens: type: integer description: Total tokens prompt_tokens_details: type: object properties: cached_tokens: type: integer text_tokens: type: integer audio_tokens: type: integer image_tokens: type: integer x-apifox-orders: - cached_tokens - text_tokens - audio_tokens - image_tokens x-apifox-ignore-properties: [] completion_tokens_details: type: object properties: text_tokens: type: integer audio_tokens: type: integer reasoning_tokens: type: integer x-apifox-orders: - text_tokens - audio_tokens - reasoning_tokens x-apifox-ignore-properties: [] x-apifox-orders: - prompt_tokens - completion_tokens - total_tokens - prompt_tokens_details - completion_tokens_details x-apifox-ignore-properties: [] x-apifox-folder: '' securitySchemes: bearer: type: http scheme: bearer ````