> ## Documentation Index > Fetch the complete documentation index at: https://docs.atoma.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create completions > This function processes completion requests by using the chat completions endpoint. ## Returns Returns a Response containing either: - A streaming SSE connection for real-time completions - A single JSON response for non-streaming completions ## Errors Returns an error status code if: - The request processing fails - The streaming/non-streaming handlers encounter errors - The underlying inference service returns an error ## OpenAPI ````yaml cloud-api-reference/openapi.yml post /v1/completions openapi: 3.1.0 info: title: atoma-proxy description: '' license: name: Apache-2.0 identifier: Apache-2.0 version: 0.1.0 servers: - url: https://api.atoma.network security: [] tags: - name: Completions description: OpenAI's API completions v1 endpoint - name: Confidential Completions description: Atoma's API confidential completions v1 endpoint - name: Chat description: OpenAI's API chat completions v1 endpoint - name: Confidential Chat description: Atoma's API confidential chat completions v1 endpoint - name: Confidential Embeddings description: Atoma's API confidential embeddings v1 endpoint - name: Confidential Images description: Atoma's API confidential images v1 endpoint - name: Embeddings description: OpenAI's API embeddings v1 endpoint - name: Health description: Health check - name: Images description: OpenAI's API images v1 endpoint - name: Models description: OpenAI's API models v1 endpoint - name: Nodes description: Nodes Management - name: Node Public Key Selection description: Node public key selection paths: /v1/completions: post: tags: - Completions summary: Create completions description: >- This function processes completion requests by using the chat completions endpoint. ## Returns Returns a Response containing either: - A streaming SSE connection for real-time completions - A single JSON response for non-streaming completions ## Errors Returns an error status code if: - The request processing fails - The streaming/non-streaming handlers encounter errors - The underlying inference service returns an error operationId: completions_create requestBody: content: application/json: schema: $ref: '#/components/schemas/CompletionsRequest' required: true responses: '200': description: Chat completions content: application/json: schema: $ref: '#/components/schemas/CompletionsResponse' '400': description: Bad request '401': description: Unauthorized '500': description: Internal server error security: - bearerAuth: [] x-codeSamples: - lang: typescript label: default source: |- import { AtomaSDK } from "atoma-sdk"; const atomaSDK = new AtomaSDK({ bearerAuth: process.env["ATOMASDK_BEARER_AUTH"] ?? "", }); async function run() { const completion = await atomaSDK.completions.completionsCreate({ model: "meta-llama/Llama-3.3-70B-Instruct", prompt: "Hello, world!", }); console.log(completion.choices[0]); } run(); - lang: typescript label: streaming source: |- import { AtomaSDK } from "atoma-sdk"; const atomaSDK = new AtomaSDK({ bearerAuth: process.env["ATOMASDK_BEARER_AUTH"] ?? "", }); async function run() { const completion = await atomaSDK.completions.completionsCreateStream({ model: "meta-llama/Llama-3.3-70B-Instruct", prompt: "Hello, world!", }); for await (const chunk of completion) { console.log(chunk.choices[0].text); } } run(); - lang: python label: default source: |- from atoma_sdk import AtomaSDK import os with AtomaSDK( bearer_auth=os.getenv("ATOMASDK_BEARER_AUTH", ""), ) as atoma_sdk: completion = atoma_sdk.completions.create( model="meta-llama/Llama-3.3-70B-Instruct", prompt="Hello, how are you?" ) print(completion.choices[0].text) - lang: python label: streaming source: |- from atoma_sdk import AtomaSDK import os with AtomaSDK( bearer_auth=os.getenv("ATOMASDK_BEARER_AUTH", ""), ) as atoma_sdk: completion = atoma_sdk.completions.create_stream( model="meta-llama/Llama-3.3-70B-Instruct", prompt="Hello, how are you?" ) for chunk in completion: print(chunk.data.choices[0].text) components: schemas: CompletionsRequest: type: object required: - model - prompt properties: best_of: type: - integer - 'null' format: int32 default: 1 example: 1 echo: type: - boolean - 'null' default: false example: false frequency_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far example: 0 logit_bias: type: - object - 'null' description: >- Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. additionalProperties: type: number format: float propertyNames: type: string example: '1234567890': 0.5 '1234567891': -0.5 logprobs: type: - integer - 'null' format: int32 description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. example: 1 max_tokens: type: - integer - 'null' format: int32 description: The maximum number of tokens to generate in the chat completion default: 16 example: 4096 model: type: string description: ID of the model to use example: meta-llama/Llama-3.3-70B-Instruct 'n': type: - integer - 'null' format: int32 description: How many chat completion choices to generate for each input message example: 1 presence_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far example: 0 prompt: $ref: '#/components/schemas/CompletionsPrompt' description: The prompt to generate completions for seed: type: - integer - 'null' format: int64 description: >- If specified, our system will make a best effort to sample deterministically example: 123 stop: type: - array - 'null' items: type: string description: Up to 4 sequences where the API will stop generating further tokens example: json(["stop", "halt"]) default: '[]' stream: type: - boolean - 'null' description: Whether to stream back partial progress example: false stream_options: oneOf: - type: 'null' - $ref: '#/components/schemas/StreamOptions' description: >- Options for streaming response. Only set this when you set stream: true. suffix: type: - string - 'null' description: The suffix that comes after a completion of inserted text. example: json("\n") temperature: type: - number - 'null' format: float description: What sampling temperature to use, between 0 and 2 example: 0.7 top_p: type: - number - 'null' format: float description: An alternative to sampling with temperature example: 1 user: type: - string - 'null' description: A unique identifier representing your end-user example: user-1234 CompletionsResponse: type: object required: - choices - usage - created - id - model - object - system_fingerprint properties: choices: type: array items: $ref: '#/components/schemas/CompletionChoice' description: Array of completion choices response example: - text: This is a test index: 0 logprobs: null finish_reason: stop created: type: integer format: int64 description: The creation time of the request example: '2021-01-01T00:00:00.000Z' id: type: string description: The ID of the request example: cmpl-1234567890 model: type: string description: The model used for the request example: meta-llama/Llama-3.3-70B-Instruct object: type: string description: The object type example: text_completion system_fingerprint: type: string description: The system fingerprint example: system-fingerprint usage: $ref: '#/components/schemas/Usage' description: The usage information for the request CompletionsPrompt: oneOf: - type: string description: A single string prompt - type: array items: type: string description: An array of strings prompts - type: array items: type: integer format: int32 minimum: 0 description: An array of tokens - type: array items: type: array items: type: integer format: int32 minimum: 0 description: An array of token arrays StreamOptions: type: object description: Specifies the stream options for the request. properties: include_usage: type: - boolean - 'null' description: >- If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array. All other chunks will also include a usage field, but with a null value. CompletionChoice: type: object description: A completion choice response required: - text - index - finish_reason properties: finish_reason: type: string description: The reason the model stopped generating tokens example: stop index: type: integer format: int32 description: The index of the choice in the list of choices example: 0 logprobs: oneOf: - type: 'null' - $ref: '#/components/schemas/LogProbs' description: The log probabilities of the chosen tokens text: type: string description: The generated text example: This is a test Usage: type: object required: - prompt_tokens - completion_tokens - total_tokens - completion_tokens_details - prompt_tokens_details properties: completion_tokens: type: integer format: int32 description: The number of completion tokens used example: 10 minimum: 0 completion_tokens_details: $ref: '#/components/schemas/CompletionTokensDetails' description: The details of the completion tokens prompt_tokens: type: integer format: int32 description: The number of prompt tokens used example: 10 minimum: 0 prompt_tokens_details: $ref: '#/components/schemas/PromptTokensDetails' description: The details of the prompt tokens total_tokens: type: integer format: int32 description: The total number of tokens used example: 20 minimum: 0 LogProbs: type: object required: - tokens - token_logprobs - top_logprobs - text_offset properties: text_offset: type: array items: type: integer format: int32 minimum: 0 description: The text offset of the tokens example: - 0 - 10 token_logprobs: type: array items: type: number format: float description: The log probabilities of the tokens example: - 0.5 - -0.5 tokens: type: array items: type: string description: The tokens example: - 'Hello ' - world top_logprobs: type: array items: type: object additionalProperties: type: number format: float propertyNames: type: string description: The top log probabilities example: - 'Hello ': -0.2 world: -0.8 CompletionTokensDetails: type: object description: The details of the completion tokens required: - accepted_prediction_tokens - audio_tokens - reasoning_tokens - rejected_prediction_tokens properties: accepted_prediction_tokens: type: integer format: int32 description: The number of tokens in the completion example: 10 minimum: 0 audio_tokens: type: integer format: int32 description: The number of audio tokens example: 0 minimum: 0 reasoning_tokens: type: integer format: int32 description: The number of reasoning tokens example: 10 minimum: 0 rejected_prediction_tokens: type: integer format: int32 description: The number of rejected prediction tokens example: 0 minimum: 0 PromptTokensDetails: type: object required: - audio_tokens - cached_tokens properties: audio_tokens: type: integer format: int32 description: The number of audio tokens example: 0 minimum: 0 cached_tokens: type: integer format: int32 description: The number of cached tokens example: 10 minimum: 0 securitySchemes: bearerAuth: type: http scheme: bearer ````