--- title: "Chat Completions" method: POST path: "/v1beta/chat/completions" tags: ["Chat API (Beta)"] --- # Chat Completions `POST /v1beta/chat/completions` ## Request - Base URL: `https://api.parallel.ai` - URL: `https://api.parallel.ai/v1beta/chat/completions` - Auth: API key in header `x-api-key` 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. ## Request body - ChatCompletionRequest: Request for the chat completions endpoint. Note that all parameters except for `model`, `stream`, and `response_format` are ignored. - `model` string, required: The model to use for chat completions. - `messages` ChatMessage[], required: The messages to use for chat completions. - `role` 'system' | 'user' | 'assistant', required: The role of the chat message. - `content` string, required: The content of the chat message. - `name` string, nullable: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - `stream` boolean, nullable: Whether to stream the chat completions. - `response_format` union: The response format to use for chat completions. OpenAI compatible. - OpenaiTypesSharedParamsResponseFormatTextResponseFormatText: Default response format. Used to generate text responses. - `type` 'text', required - ResponseFormatJSONSchema: JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - `json_schema` JSONSchema, required: Structured Outputs configuration options, including a JSON Schema. - `name` string, required - `description` string - `schema` object - `strict` boolean, nullable - `type` 'json_schema', required - OpenaiTypesSharedParamsResponseFormatJsonObjectResponseFormatJSONObject: 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` 'json_object', required - `max_tokens` integer, nullable: The maximum number of tokens to generate. Unsupported. - `temperature` number, nullable: The temperature to use for chat completions. Unsupported. - `top_p` number, nullable: The top p to use for chat completions. Unsupported. - `n` integer, nullable: The number of chat completions to generate. Unsupported. - `presence_penalty` number, nullable: The presence penalty to use for chat completions. Unsupported. - `frequency_penalty` number, nullable: The frequency penalty to use for chat completions. Unsupported. - `previous_interaction_id` string, nullable: Interaction ID from a previous chat completion to use as context. ## Response `200` 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. - ChatCompletion: Chat completion response. - `id` string, required: The id of the chat completion. - `choices` Choice[], required - `delta` ChoiceDelta, required: A chat completion delta generated by streamed model responses. - `content` string, nullable - `function_call` ChoiceDeltaFunctionCall: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. - `arguments` string, nullable - `name` string, nullable - `refusal` string, nullable - `role` 'developer' | 'system' | 'user' | 'assistant' | 'tool', nullable - `tool_calls` ChoiceDeltaToolCall[], nullable - `index` integer, required - `id` string, nullable - `function` ChoiceDeltaToolCallFunction - `arguments` string, nullable - `name` string, nullable - `type` 'function', nullable - `finish_reason` 'stop' | 'length' | 'tool_calls' | 'content_filter' | 'function_call', nullable - `index` integer, required - `logprobs` ChoiceLogprobs: Log probability information for the choice. - `content` ChatCompletionTokenLogprob[], nullable - `token` string, required - `bytes` integer[], nullable - `logprob` number, required - `top_logprobs` TopLogprob[], required - `token` string, required - `bytes` integer[], nullable - `logprob` number, required - `refusal` ChatCompletionTokenLogprob[], nullable - `token` string, required - `bytes` integer[], nullable - `logprob` number, required - `top_logprobs` TopLogprob[], required - `token` string, required - `bytes` integer[], nullable - `logprob` number, required - `created` integer, required - `model` string, required - `object` 'chat.completion', required - `moderation` OpenaiTypesChatChatCompletionModeration: Moderation results for the request input and generated output, if moderated completions were requested. - `input` union, required - ModerationInputModerationResults: Successful moderation results for the request input or generated output. - `model` string, required - `results` ModerationInputModerationResultsResult[], required - `categories` object, required - `category_applied_input_types` object, required - `category_scores` object, required - `flagged` boolean, required - `model` string, required - `type` 'moderation_result', required - `type` 'moderation_results', required - OpenaiTypesChatChatCompletionModerationInputError: An error produced while attempting moderation. - `code` string, required - `message` string, required - `type` 'error', required - `output` union, required - ModerationOutputModerationResults: Successful moderation results for the request input or generated output. - `model` string, required - `results` ModerationOutputModerationResultsResult[], required - `categories` object, required - `category_applied_input_types` object, required - `category_scores` object, required - `flagged` boolean, required - `model` string, required - `type` 'moderation_result', required - `type` 'moderation_results', required - OpenaiTypesChatChatCompletionModerationOutputError: An error produced while attempting moderation. - `code` string, required - `message` string, required - `type` 'error', required - `service_tier` 'auto' | 'default' | 'flex' | 'scale' | 'priority', nullable - `system_fingerprint` string, nullable - `usage` CompletionUsage: Usage statistics for the completion request. - `completion_tokens` integer, required - `prompt_tokens` integer, required - `total_tokens` integer, required - `completion_tokens_details` CompletionTokensDetails: Breakdown of tokens used in a completion. - `accepted_prediction_tokens` integer, nullable - `audio_tokens` integer, nullable - `reasoning_tokens` integer, nullable - `rejected_prediction_tokens` integer, nullable - `prompt_tokens_details` PromptTokensDetails: Breakdown of tokens used in the prompt. - `audio_tokens` integer, nullable - `cached_tokens` integer, nullable - `basis` FieldBasis[]: Basis for the chat completion, including citations and reasoning supporting the output. - `field` string, required: Name of the output field. - `citations` Citation[]: List of citations supporting the output field. - `title` string, nullable: Title of the citation. - `url` string, required: URL of the citation. - `excerpts` string[], nullable: Excerpts from the citation supporting the output. Only certain processors provide excerpts. - `reasoning` string, required: Reasoning for the output field. - `confidence` string, nullable: Confidence level for the output field. Only certain processors provide confidence levels. - `interaction_id` string, nullable: Identifier for this interaction. Pass as previous_interaction_id for follow-ups. ## Other responses - `422`: Validation Error ## Changes - **2026-10-16** `fc4858951ccf`: 1 info - endpoint added [Operation history](https://skmtc.dev/parallel-web/apis/parallel-api/changes/v1beta/chat/completions/post.md) --- [API](https://skmtc.dev/parallel-web/apis/parallel-api.md) - [All operations](https://skmtc.dev/parallel-web/apis/parallel-api/llms.txt) - [OpenAPI document](https://skmtc.dev/parallel-web/apis/parallel-api/revisions/eae6def9641f?raw)