> ## 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 chat completions > This function processes chat completion requests by determining whether to use streaming or non-streaming response handling based on the request payload. For streaming requests, it configures additional options to track token usage. ## 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/chat/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/chat/completions: post: tags: - Chat summary: Create chat completions description: >- This function processes chat completion requests by determining whether to use streaming or non-streaming response handling based on the request payload. For streaming requests, it configures additional options to track token usage. ## 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: chat_completions_create requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' required: true responses: '200': description: Chat completions content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' '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.chat.create({ messages: [ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ], model: "meta-llama/Llama-3.3-70B-Instruct" }); 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.chat.createStream({ messages: [ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ], model: "meta-llama/Llama-3.3-70B-Instruct" }); for await (const chunk of completion) { console.log(chunk.choices[0].delta.content); } } 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.chat.createStream({ messages: [ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ], model: "meta-llama/Llama-3.3-70B-Instruct" }); for await (const chunk of completion) { console.log(chunk.choices[0].delta.content); } } 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.chat.create( model="meta-llama/Llama-3.3-70B-Instruct", messages=[ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] ) print(completion.choices[0].message) - 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.chat.create( model="meta-llama/Llama-3.3-70B-Instruct", messages=[ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] ) print(completion.choices[0].message) - 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.chat.create_stream( model="meta-llama/Llama-3.3-70B-Instruct", messages=[ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] ) for chunk in completion: print(chunk.data.choices[0].delta) - 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.chat.create_stream( model="meta-llama/Llama-3.3-70B-Instruct", messages=[ {"role": "developer", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] ) for chunk in completion: print(chunk.data.choices[0].delta) components: schemas: CreateChatCompletionRequest: allOf: - $ref: '#/components/schemas/ChatCompletionRequest' - type: object properties: stream: type: - boolean - 'null' description: >- Whether to stream back partial progress. Must be false for this request type. default: false description: >- Represents the create chat completion request. This is used to represent the create chat completion request in the chat completion request. It can be either a chat completion or a chat completion stream. ChatCompletionResponse: type: object description: >- Represents the chat completion response. This is used to represent the chat completion response in the chat completion request. It can be either a chat completion or a chat completion stream. required: - id - created - model - choices - object properties: choices: type: array items: $ref: '#/components/schemas/ChatCompletionChoice' description: A list of chat completion choices. example: >- [{"index": 0, "message": {"role": "assistant", "content": "Hello! How can you help me today?"}, "finish_reason": null, "stop_reason": null}] created: type: integer format: int64 description: >- The Unix timestamp (in seconds) of when the chat completion was created. example: 1677652288 id: type: string description: A unique identifier for the chat completion. example: chatcmpl-123 model: type: string description: The model used for the chat completion. example: meta-llama/Llama-3.3-70B-Instruct object: type: string description: The object of the chat completion. example: chat.completion service_tier: type: - string - 'null' description: The service tier of the chat completion. example: auto system_fingerprint: type: - string - 'null' description: The system fingerprint for the completion, if applicable. example: fp_44709d6fcb usage: oneOf: - type: 'null' - $ref: '#/components/schemas/CompletionUsage' description: Usage statistics for the completion request. ChatCompletionRequest: type: object description: >- Represents the chat completion request. This is used to represent the chat completion request in the chat completion request. It can be either a chat completion or a chat completion stream. required: - model - messages properties: 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 function_call: description: Controls how the model responds to function calls functions: type: - array - 'null' items: {} description: A list of functions the model may generate JSON inputs for example: - name: get_current_weather description: Get the current weather in a location parameters: type: object properties: location: type: string description: The location to get the weather for required: - location 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: integer format: int32 minimum: 0 example: '1234567890': 0.5 '1234567891': -0.5 max_completion_tokens: type: - integer - 'null' format: int32 description: The maximum number of tokens to generate in the chat completion example: 4096 max_tokens: type: - integer - 'null' format: int32 description: The maximum number of tokens to generate in the chat completion deprecated: true example: 4096 messages: type: array items: $ref: '#/components/schemas/ChatCompletionMessage' description: A list of messages comprising the conversation so far example: - role: system content: You are a helpful AI assistant - role: user content: Hello! - role: assistant content: >- I'm here to help you with any questions you have. How can I assist you today? 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 parallel_tool_calls: type: - boolean - 'null' description: Whether to enable parallel tool calls. example: true 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 response_format: oneOf: - type: 'null' - $ref: '#/components/schemas/ResponseFormat' description: The format to return the response in seed: type: - integer - 'null' format: int64 description: >- If specified, our system will make a best effort to sample deterministically example: 123 service_tier: type: - string - 'null' description: >- Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. When not set, the default behavior is 'auto'. example: auto 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. temperature: type: - number - 'null' format: float description: What sampling temperature to use, between 0 and 2 example: 0.7 tool_choice: oneOf: - type: 'null' - $ref: '#/components/schemas/ToolChoice' description: Controls which (if any) tool the model should use tools: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionToolsParam' description: A list of tools the model may call example: - type: function function: name: get_current_weather description: Get the current weather in a location parameters: type: object properties: location: type: string description: The location to get the weather for required: - location top_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. logprobs must be set to true if this parameter is used. example: 1 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 ChatCompletionChoice: type: object description: >- Represents the chat completion choice. This is used to represent the chat completion choice in the chat completion request. It can be either a chat completion message or a chat completion chunk. required: - index - message properties: finish_reason: type: - string - 'null' description: The reason the chat completion was finished. example: stop index: type: integer format: int32 description: The index of this choice in the list of choices. example: 0 logprobs: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionLogProbs' description: Log probability information for the choice, if applicable. message: $ref: '#/components/schemas/ChatCompletionMessage' description: The chat completion message. CompletionUsage: type: object description: >- Represents the completion usage. This is used to represent the completion usage in the chat completion request. It can be either a completion usage or a completion chunk usage. required: - prompt_tokens - completion_tokens - total_tokens properties: completion_tokens: type: integer format: int32 description: Number of tokens in the completion. example: 12 prompt_tokens: type: integer format: int32 description: Number of tokens in the prompt. example: 9 prompt_tokens_details: oneOf: - type: 'null' - $ref: '#/components/schemas/PromptTokensDetails' description: Details about the prompt tokens. total_tokens: type: integer format: int32 description: Total number of tokens used (prompt + completion). example: 21 ChatCompletionMessage: oneOf: - type: object title: System description: The role of the messages author, in this case system. required: - role properties: content: oneOf: - type: 'null' - $ref: '#/components/schemas/MessageContent' description: The contents of the message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. example: AI expert role: type: string enum: - system - type: object title: User description: The role of the messages author, in this case user. required: - role properties: content: oneOf: - type: 'null' - $ref: '#/components/schemas/MessageContent' description: The contents of the message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. example: John Doe role: type: string enum: - user - type: object title: Assistant description: The role of the messages author, in this case assistant. required: - role properties: content: oneOf: - type: 'null' - $ref: '#/components/schemas/MessageContent' description: The contents of the message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. example: AI refusal: type: - string - 'null' description: The refusal message by the assistant. role: type: string enum: - assistant tool_calls: type: array items: $ref: '#/components/schemas/ToolCall' description: The tool calls generated by the model, such as function calls. - type: object title: Tool description: The role of the messages author, in this case tool. required: - role properties: content: oneOf: - type: 'null' - $ref: '#/components/schemas/MessageContent' description: The contents of the message. role: type: string enum: - tool tool_call_id: type: string description: Tool call that this message is responding to. description: >- A message that is part of a conversation which is based on the role of the author of the message. This is used to represent the message in the chat completion request. It can be either a system message, a user message, an assistant message, or a tool message. ResponseFormat: type: object description: >- The format to return the response in. This is used to represent the format to return the response in in the chat completion request. It can be either text, json_object, or json_schema. required: - type properties: json_schema: oneOf: - type: 'null' - $ref: '#/components/schemas/JsonSchemaResponseFormat' description: The JSON schema of the response format. type: $ref: '#/components/schemas/ResponseFormatType' description: The type of the response format. 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. ToolChoice: oneOf: - $ref: '#/components/schemas/ToolChoiceLiteral' - $ref: '#/components/schemas/ChatCompletionNamedToolChoiceParam' description: >- A tool choice that can be used in a chat completion. This is used to represent the tool choice in the chat completion request. It can be either a literal tool choice or a named tool choice. ChatCompletionToolsParam: type: object description: A tool that can be used in a chat completion. required: - type - function properties: function: $ref: '#/components/schemas/ChatCompletionToolFunctionParam' description: The function that the tool will call. type: type: string description: The type of the tool. ChatCompletionLogProbs: type: object description: >- Represents the chat completion log probs. This is used to represent the chat completion log probs in the chat completion request. It can be either a chat completion log probs or a chat completion log probs choice. properties: content: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionLogProbsContent' description: The log probs of the chat completion. 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 MessageContent: oneOf: - type: string description: The text contents of the message. - type: array items: $ref: '#/components/schemas/MessageContentPart' description: >- An array of content parts with a defined type, each can be of type text or image_url when passing in images. You can pass multiple images by adding multiple image_url content parts. Image input is only supported when using the gpt-4o model. description: >- Represents the content of a message. This is used to represent the content of a message in the chat completion request. It can be either a text or an array of content parts. ToolCall: type: object description: >- Represents the tool call that the model made. This is used to represent the tool call that the model made in the chat completion request. It can be either a function or a tool. required: - id - type - function properties: function: $ref: '#/components/schemas/ToolCallFunction' description: The function that the model called. id: type: string description: The ID of the tool call. type: type: string description: The type of the tool. Currently, only function is supported. JsonSchemaResponseFormat: type: object description: >- The format to return the response in. This is used to represent the format to return the response in in the chat completion request. It can be either text, json_object, or json_schema. required: - name properties: description: type: - string - 'null' description: The description of the response format. name: type: string description: The name of the response format. schema: description: The JSON schema of the response format. strict: type: - boolean - 'null' description: Whether to strictly validate the JSON schema. ResponseFormatType: type: string description: The format to return the response in. enum: - text - json_object - json_schema ToolChoiceLiteral: type: string description: >- A literal tool choice that can be used in a chat completion. This is used to represent the literal tool choice in the chat completion request. It can be either none or auto. enum: - none - auto ChatCompletionNamedToolChoiceParam: type: object description: >- A named tool choice that can be used in a chat completion. This is used to represent the named tool choice in the chat completion request. required: - type - function properties: function: $ref: '#/components/schemas/ChatCompletionNamedFunction' description: The function of the tool choice. type: type: string description: The type of the tool choice. ChatCompletionToolFunctionParam: type: object description: A function that can be used in a chat completion. required: - name properties: description: type: - string - 'null' description: The description of the function. name: type: string description: The name of the function. parameters: type: - object - 'null' description: The parameters of the function. additionalProperties: {} propertyNames: type: string strict: type: - boolean - 'null' description: Whether to strictly validate the parameters of the function. ChatCompletionLogProbsContent: type: object description: >- Represents the chat completion log probs content. This is used to represent the chat completion log probs content in the chat completion request. It can be either a chat completion log probs content or a chat completion log probs content choice. required: - top_logprobs properties: top_logprobs: type: array items: $ref: '#/components/schemas/ChatCompletionLogProb' MessageContentPart: oneOf: - type: object required: - type - text properties: text: type: string description: The text content. type: type: string description: The type of the content part. - type: object required: - type - image_url properties: image_url: $ref: '#/components/schemas/MessageContentPartImageUrl' description: The image URL. type: type: string description: The type of the content part. description: >- Represents a part of a message content. This is used to represent the content of a message in the chat completion request. It can be either a text or an image. ToolCallFunction: type: object description: >- Represents the function that the model called. This is used to represent the function that the model called in the chat completion request. It can be either a function or a tool call. required: - name - arguments properties: arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. ChatCompletionNamedFunction: type: object description: >- A named function that can be used in a chat completion. This is used to represent the named function in the chat completion request. required: - name properties: name: type: string description: The name of the function. ChatCompletionLogProb: type: object description: >- Represents the chat completion log prob. This is used to represent the chat completion log prob in the chat completion request. It can be either a chat completion log prob or a chat completion log prob choice. required: - logprob - token properties: bytes: type: - array - 'null' items: type: integer format: int32 description: >- A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token. logprob: type: number format: float description: The log prob of the chat completion. token: type: string description: The token of the chat completion. MessageContentPartImageUrl: type: object description: >- Represents the image URL of a message content part. This is used to represent the image URL of a message content part in the chat completion request. It can be either a URL or a base64 encoded image data. required: - url properties: detail: type: - string - 'null' description: Specifies the detail level of the image. url: type: string description: Either a URL of the image or the base64 encoded image data. securitySchemes: bearerAuth: type: http scheme: bearer ````