> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. # Chat Completions > Chat completions. This endpoint can be used to get realtime chat completions. It can also be used with the Task API processors to get structured, research outputs via a chat interface. ## OpenAPI ````yaml openapi/zh/parallel.ai.json POST /apis/v1/parallel/chat/completions openapi: 3.1.0 info: description: '' title: Parallel.ai version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-configured-paths: - /apis/v1/parallel/chat/completions - /apis/v1/parallel/extract - /apis/v1/parallel/findall/ingest - /apis/v1/parallel/findall/runs/{findall_id} - /apis/v1/parallel/findall/runs/{findall_id}/cancel - /apis/v1/parallel/findall/runs/{findall_id}/events - /apis/v1/parallel/findall/runs/{findall_id}/result - /apis/v1/parallel/findall/runs/{findall_id}/schema - /apis/v1/parallel/monitors/{monitor_id} - /apis/v1/parallel/monitors/{monitor_id}/cancel - /apis/v1/parallel/monitors/{monitor_id}/events - /apis/v1/parallel/monitors/{monitor_id}/update - /apis/v1/parallel/tasks/groups - /apis/v1/parallel/tasks/groups/{taskgroup_id} - /apis/v1/parallel/tasks/groups/{taskgroup_id}/events - /apis/v1/parallel/tasks/groups/{taskgroup_id}/runs/{run_id} - /apis/v1/parallel/tasks/runs/{run_id} - /apis/v1/parallel/tasks/runs/{run_id}/events - /apis/v1/parallel/tasks/runs/{run_id}/input - /apis/v1/parallel/tasks/runs/{run_id}/result - /apis/v1/parallel/v1beta/tasks/runs/{run_id}/events x-aisa-document: facts_hash: 7d3bf2025708131927d3136de215ba314114253046b35f239876910b2481cbd9 generator_version: '2' protocol_version: '1' schema_version: '1' composer_version: '13' response_pending: [] document_hash: sha256:dae9e982424f710c06d9af023168dd26ed96bf5e5b5232e0728c01867d2da7dc x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: parallel.ai x-aisa-catalogs: parallel.ai: title: Parallel.ai description: '' x-aisa-document: facts_hash: 7d3bf2025708131927d3136de215ba314114253046b35f239876910b2481cbd9 generator_version: '2' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /apis/v1/parallel/chat/completions: post: tags: - default summary: Chat Completions description: >- Chat completions. This endpoint can be used to get realtime chat completions. It can also be used with the Task API processors to get structured, research outputs via a chat interface. operationId: post_parallel_ai_apis_v1_parallel_chat_completions requestBody: content: application/json: schema: properties: model: enum: - base - core - lite - speed type: string messages: items: {} minItems: 1 type: array stream: anyOf: - type: boolean - type: 'null' title: Stream description: Whether to stream the chat completions. response_format: anyOf: - properties: type: type: string const: text title: Type type: object required: - type title: ResponseFormatText description: >- Default response format. Used to generate text responses. - properties: json_schema: properties: name: type: string title: Name description: type: string title: Description schema: additionalProperties: false type: object title: Schema strict: anyOf: - type: boolean - type: 'null' title: Strict type: object required: - name title: JSONSchema description: >- Structured Outputs configuration options, including a JSON Schema. type: type: string const: json_schema title: Type type: object required: - json_schema - type title: ResponseFormatJSONSchema description: >- JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - properties: type: type: string const: json_object title: Type type: object required: - type title: ResponseFormatJSONObject description: >- JSON object response format. An older method of generating JSON responses. Using `json_schema` is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so. - type: 'null' title: Response Format description: >- The response format to use for chat completions. OpenAI compatible. max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens description: The maximum number of tokens to generate. Unsupported. temperature: anyOf: - type: number - type: 'null' title: Temperature description: The temperature to use for chat completions. Unsupported. top_p: anyOf: - type: number - type: 'null' title: Top P description: The top p to use for chat completions. Unsupported. 'n': anyOf: - type: integer - type: 'null' title: 'N' description: The number of chat completions to generate. Unsupported. presence_penalty: anyOf: - type: number - type: 'null' title: Presence Penalty description: >- The presence penalty to use for chat completions. Unsupported. frequency_penalty: anyOf: - type: number - type: 'null' title: Frequency Penalty description: >- The frequency penalty to use for chat completions. Unsupported. previous_interaction_id: anyOf: - type: string - type: 'null' title: Previous Interaction Id description: >- Interaction ID from a previous chat completion to use as context. type: object title: ChatCompletionRequest description: >- Request for the chat completions endpoint. Note that all parameters except for `model`, `stream`, and `response_format` are ignored. required: - messages - model required: true responses: '200': description: >- Returns a ChatCompletion object for non-streaming requests (application/json), or a stream of ChatCompletionResponseChunk objects for streaming requests (text/event-stream) when `stream=true` is set in the request. content: application/json: schema: $ref: '#/components/schemas/ResponseB67C75A8Feba_ChatCompletion' text/event-stream: schema: $ref: >- #/components/schemas/ResponseB67C75A8Feba_ChatCompletionResponseChunk default: content: application/json: schema: {} description: >- Error response; upstream passthrough responses may use provider formats components: schemas: ResponseB67C75A8Feba_ChatCompletion: properties: id: type: string title: Id description: The id of the chat completion. choices: items: $ref: '#/components/schemas/ResponseB67C75A8Feba_Choice' type: array title: Choices created: type: integer title: Created model: type: string title: Model object: type: string const: chat.completion title: Object moderation: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_openai__types__chat__chat_completion__Moderation - type: 'null' service_tier: anyOf: - type: string enum: - auto - default - flex - scale - priority - type: 'null' title: Service Tier system_fingerprint: anyOf: - type: string - type: 'null' title: System Fingerprint usage: anyOf: - $ref: '#/components/schemas/ResponseB67C75A8Feba_CompletionUsage' - type: 'null' basis: items: $ref: '#/components/schemas/ResponseB67C75A8Feba_FieldBasis' type: array title: Basis description: >- Basis for the chat completion, including citations and reasoning supporting the output. default: [] interaction_id: anyOf: - type: string - type: 'null' title: Interaction Id description: >- Identifier for this interaction. Pass as previous_interaction_id for follow-ups. additionalProperties: true type: object required: - id - choices - created - model - object title: ChatCompletion description: Chat completion response. ResponseB67C75A8Feba_ChatCompletionResponseChunk: additionalProperties: true description: Chat completion response chunk. properties: id: description: The id of the chat completion response chunk. title: Id type: string choices: items: $ref: '#/components/schemas/ResponseB67C75A8Feba_Choice' type: array title: Choices created: type: integer title: Created model: type: string title: Model object: const: chat.completion.chunk title: Object type: string moderation: anyOf: - $ref: '#/components/schemas/ResponseB67C75A8Feba_Moderation' - type: 'null' default: null service_tier: anyOf: - type: string enum: - auto - default - flex - scale - priority - type: 'null' default: null title: Service Tier system_fingerprint: anyOf: - type: string - type: 'null' default: null title: System Fingerprint usage: anyOf: - $ref: '#/components/schemas/ResponseB67C75A8Feba_CompletionUsage' - type: 'null' default: null type: const: chat.completion.chunk description: >- The type of the chat completion chunk. Always `chat.completion.chunk`. title: Type type: string basis: default: [] description: >- Basis for the chat completion chunk, including citations and reasoning supporting the output. items: $ref: '#/components/schemas/ResponseB67C75A8Feba_FieldBasis' title: Basis type: array interaction_id: anyOf: - type: string - type: 'null' default: null description: >- Identifier for this interaction. Pass as previous_interaction_id for follow-ups. title: Interaction Id required: - id - choices - created - model - object - type title: ChatCompletionResponseChunk type: object ResponseB67C75A8Feba_Choice: additionalProperties: true properties: delta: $ref: '#/components/schemas/ResponseB67C75A8Feba_ChoiceDelta' finish_reason: anyOf: - enum: - stop - length - tool_calls - content_filter - function_call type: string - type: 'null' default: null title: Finish Reason index: title: Index type: integer logprobs: anyOf: - $ref: '#/components/schemas/ResponseB67C75A8Feba_ChoiceLogprobs' - type: 'null' default: null required: - delta - index title: Choice type: object ResponseB67C75A8Feba_openai__types__chat__chat_completion__Moderation: properties: input: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationInputModerationResults - $ref: >- #/components/schemas/ResponseB67C75A8Feba_openai__types__chat__chat_completion__ModerationInputError title: Input output: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationOutputModerationResults - $ref: >- #/components/schemas/ResponseB67C75A8Feba_openai__types__chat__chat_completion__ModerationOutputError title: Output additionalProperties: true type: object required: - input - output title: Moderation description: >- Moderation results for the request input and generated output, if moderated completions were requested. ResponseB67C75A8Feba_CompletionUsage: additionalProperties: true description: Usage statistics for the completion request. properties: completion_tokens: title: Completion Tokens type: integer prompt_tokens: title: Prompt Tokens type: integer total_tokens: title: Total Tokens type: integer completion_tokens_details: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_CompletionTokensDetails - type: 'null' default: null prompt_tokens_details: anyOf: - $ref: '#/components/schemas/ResponseB67C75A8Feba_PromptTokensDetails' - type: 'null' default: null required: - completion_tokens - prompt_tokens - total_tokens title: CompletionUsage type: object ResponseB67C75A8Feba_FieldBasis: description: Citations and reasoning supporting one field of a task output. properties: field: description: Name of the output field. title: Field type: string citations: default: [] description: List of citations supporting the output field. items: $ref: '#/components/schemas/ResponseB67C75A8Feba_Citation' title: Citations type: array reasoning: description: Reasoning for the output field. title: Reasoning type: string confidence: anyOf: - type: string - type: 'null' default: null description: >- Confidence level for the output field. Only certain processors provide confidence levels. examples: - low - medium - high title: Confidence required: - field - reasoning title: FieldBasis type: object ResponseB67C75A8Feba_Moderation: additionalProperties: true description: >- Moderation results for the response input and output, if moderated completions were requested. properties: input: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationInputModerationResult - $ref: '#/components/schemas/ResponseB67C75A8Feba_ModerationInputError' title: Input output: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationOutputModerationResult - $ref: '#/components/schemas/ResponseB67C75A8Feba_ModerationOutputError' title: Output required: - input - output title: Moderation type: object ResponseB67C75A8Feba_ChoiceDelta: additionalProperties: true description: A chat completion delta generated by streamed model responses. properties: content: anyOf: - type: string - type: 'null' default: null title: Content function_call: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ChoiceDeltaFunctionCall - type: 'null' default: null refusal: anyOf: - type: string - type: 'null' default: null title: Refusal role: anyOf: - enum: - developer - system - user - assistant - tool type: string - type: 'null' default: null title: Role tool_calls: anyOf: - items: $ref: '#/components/schemas/ResponseB67C75A8Feba_ChoiceDeltaToolCall' type: array - type: 'null' default: null title: Tool Calls title: ChoiceDelta type: object ResponseB67C75A8Feba_ChoiceLogprobs: additionalProperties: true description: Log probability information for the choice. properties: content: anyOf: - items: $ref: >- #/components/schemas/ResponseB67C75A8Feba_ChatCompletionTokenLogprob type: array - type: 'null' default: null title: Content refusal: anyOf: - items: $ref: >- #/components/schemas/ResponseB67C75A8Feba_ChatCompletionTokenLogprob type: array - type: 'null' default: null title: Refusal title: ChoiceLogprobs type: object ResponseB67C75A8Feba_ModerationInputModerationResults: additionalProperties: true description: Successful moderation results for the request input or generated output. properties: model: type: string title: Model results: items: $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationInputModerationResultsResult title: Results type: array type: const: moderation_results title: Type type: string required: - model - results - type title: ModerationInputModerationResults type: object ResponseB67C75A8Feba_openai__types__chat__chat_completion__ModerationInputError: properties: code: type: string title: Code message: type: string title: Message type: type: string const: error title: Type additionalProperties: true type: object required: - code - message - type title: ModerationInputError description: An error produced while attempting moderation. ResponseB67C75A8Feba_ModerationOutputModerationResults: additionalProperties: true description: Successful moderation results for the request input or generated output. properties: model: type: string title: Model results: items: $ref: >- #/components/schemas/ResponseB67C75A8Feba_ModerationOutputModerationResultsResult title: Results type: array type: const: moderation_results title: Type type: string required: - model - results - type title: ModerationOutputModerationResults type: object ResponseB67C75A8Feba_openai__types__chat__chat_completion__ModerationOutputError: properties: code: type: string title: Code message: type: string title: Message type: type: string const: error title: Type additionalProperties: true type: object required: - code - message - type title: ModerationOutputError description: An error produced while attempting moderation. ResponseB67C75A8Feba_CompletionTokensDetails: additionalProperties: true description: Breakdown of tokens used in a completion. properties: accepted_prediction_tokens: anyOf: - type: integer - type: 'null' default: null title: Accepted Prediction Tokens audio_tokens: anyOf: - type: integer - type: 'null' default: null title: Audio Tokens reasoning_tokens: anyOf: - type: integer - type: 'null' default: null title: Reasoning Tokens rejected_prediction_tokens: anyOf: - type: integer - type: 'null' default: null title: Rejected Prediction Tokens title: CompletionTokensDetails type: object ResponseB67C75A8Feba_PromptTokensDetails: additionalProperties: true description: Breakdown of tokens used in the prompt. properties: audio_tokens: anyOf: - type: integer - type: 'null' default: null title: Audio Tokens cached_tokens: anyOf: - type: integer - type: 'null' default: null title: Cached Tokens title: PromptTokensDetails type: object ResponseB67C75A8Feba_Citation: description: A citation for a task output. properties: title: anyOf: - type: string - type: 'null' default: null description: Title of the citation. title: Title url: description: URL of the citation. title: Url type: string excerpts: anyOf: - items: type: string type: array - type: 'null' default: null description: >- Excerpts from the citation supporting the output. Only certain processors provide excerpts. title: Excerpts required: - url title: Citation type: object ResponseB67C75A8Feba_ModerationInputModerationResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationInputModerationResult type: object ResponseB67C75A8Feba_ModerationInputError: additionalProperties: true description: >- An error produced while attempting moderation for the response input or output. properties: code: type: string title: Code message: type: string title: Message type: type: string const: error title: Type required: - code - message - type title: ModerationInputError type: object ResponseB67C75A8Feba_ModerationOutputModerationResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationOutputModerationResult type: object ResponseB67C75A8Feba_ModerationOutputError: additionalProperties: true description: >- An error produced while attempting moderation for the response input or output. properties: code: type: string title: Code message: type: string title: Message type: type: string const: error title: Type required: - code - message - type title: ModerationOutputError type: object ResponseB67C75A8Feba_ChoiceDeltaFunctionCall: additionalProperties: true description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. properties: arguments: anyOf: - type: string - type: 'null' default: null title: Arguments name: anyOf: - type: string - type: 'null' default: null title: Name title: ChoiceDeltaFunctionCall type: object ResponseB67C75A8Feba_ChoiceDeltaToolCall: additionalProperties: true properties: index: title: Index type: integer id: anyOf: - type: string - type: 'null' default: null title: Id function: anyOf: - $ref: >- #/components/schemas/ResponseB67C75A8Feba_ChoiceDeltaToolCallFunction - type: 'null' default: null type: anyOf: - const: function type: string - type: 'null' default: null title: Type required: - index title: ChoiceDeltaToolCall type: object ResponseB67C75A8Feba_ChatCompletionTokenLogprob: additionalProperties: true properties: token: title: Token type: string bytes: anyOf: - items: type: integer type: array - type: 'null' default: null title: Bytes logprob: title: Logprob type: number top_logprobs: items: $ref: '#/components/schemas/ResponseB67C75A8Feba_TopLogprob' title: Top Logprobs type: array required: - token - logprob - top_logprobs title: ChatCompletionTokenLogprob type: object ResponseB67C75A8Feba_ModerationInputModerationResultsResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationInputModerationResultsResult type: object ResponseB67C75A8Feba_ModerationOutputModerationResultsResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationOutputModerationResultsResult type: object ResponseB67C75A8Feba_ChoiceDeltaToolCallFunction: additionalProperties: true properties: arguments: anyOf: - type: string - type: 'null' default: null title: Arguments name: anyOf: - type: string - type: 'null' default: null title: Name title: ChoiceDeltaToolCallFunction type: object ResponseB67C75A8Feba_TopLogprob: additionalProperties: true properties: token: title: Token type: string bytes: anyOf: - items: type: integer type: array - type: 'null' default: null title: Bytes logprob: title: Logprob type: number required: - token - logprob title: TopLogprob type: object securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.