--- title: "Chat Completions" method: POST path: "/v1/chat/completions" tags: ["chat"] --- # Chat Completions `POST /v1/chat/completions` ## Headers - `Authorization` string, required - `api-subscription-key` string, nullable ## Request body - CreateChatCompletionRequest - `messages` ChatCompletionRequestMessage[], required — A list of messages comprising the conversation so far. - union - object — ChatCompletionRequestAssistantMessage variant - `role` 'assistant', required — Discriminator value: assistant - `content` string, nullable — The contents of the assistant message - `tool_calls` ChatCompletionMessageToolCall[], nullable — The tool calls generated by the model. - `id` string, required — The ID of the tool call. - `type` 'function', required — The type of the tool call, currently only `function`. - `function` FunctionCall, required - `name` string, required — The name of the function to call. - `arguments` string, required — The arguments to call the function with, as a JSON string. - object — ChatCompletionRequestSystemMessage variant - `role` 'system', required — The role of the messages author, in this case `system`. - `content` string, required — The contents of the system message. - object — ChatCompletionRequestToolMessage variant - `role` 'tool', required — The role of the messages author, in this case `tool`. - `content` string, required — The contents of the tool message. - `tool_call_id` string, required — Tool call that this message is responding to. - object — ChatCompletionRequestUserMessage variant - `role` 'user', required — The role of the messages author, in this case `user`. - `content` string, required — The contents of the user message. - `model` 'sarvam-105b' | 'sarvam-30b', required — Supported chat completion model IDs: `sarvam-30b`, `sarvam-105b`. - `temperature` number, double, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, double, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. - `reasoning_effort` 'low' | 'medium' | 'high' - `max_tokens` integer, nullable — The maximum number of tokens that can be generated in the chat completion. - `stream` boolean, nullable — If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). - `stop` union — Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. - string - string[] - `n` integer, nullable — How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. - `seed` integer, nullable — This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. - `frequency_penalty` number, double, nullable — Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, double, nullable — Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `wiki_grounding` boolean, nullable — If set to true, the model response will be wiki grounded. - `tools` ChatCompletionTool[], nullable — A list of tools the model may call. Currently, only functions are supported as a tool. - `type` 'function', required — The type of the tool. Currently, only `function` is supported. - `function` FunctionDefinition, required - `name` string, required — The name of the function to be called. - `description` string, nullable — A description of what the function does. - `parameters` object, nullable — The parameters the function accepts, described as a JSON Schema object. - `tool_choice` union - 'none' | 'auto' | 'required' - ChatCompletionNamedToolChoice - `type` 'function', required — The type of the tool. Currently, only `function` is supported. - `function` ChatCompletionNamedToolChoiceFunction, required - `name` string, required — The name of the function to call. - `response_format` union - object — ResponseFormatText variant - `type` 'text', required — The type of response format being defined. Always `text`. - object — ResponseFormatJsonObject variant - `type` 'json_object', required — The type of response format being defined. Always `json_object`. - object — ResponseFormatJsonSchema variant - `type` 'json_schema', required — The type of response format being defined. Always `json_schema`. - `json_schema` JsonSchemaDefinition, required - `name` string, required — The name of the response format. Must contain only alphanumeric characters, underscores and dashes. - `description` string, nullable — A description of what the response format is for, used by the model to determine how to respond in the format. - `schema` JsonSchemaDefinitionSchema — The schema for the response format, described as a JSON Schema object. - `strict` boolean, nullable — Whether to enable strict schema adherence when generating the output. ## Response `200` Successful Response - CreateChatCompletionResponse - `id` string, required — A unique identifier for the chat completion. - `choices` Choice[], required — A list of chat completion choices. Can be more than one if `n` is greater than 1. - `finish_reason` 'stop' | 'length' | 'tool_calls' | 'content_filter' | 'function_call', required - `index` integer, required — The index of the choice in the list of choices. - `logprobs` object, nullable - `message` ChatCompletionResponseMessage, required - `content` string, nullable, required — The contents of the message. - `refusal` string, nullable - `reasoning_content` string, nullable — The contents of the reasoning message. - `role` 'assistant', required - `tool_calls` ChatCompletionMessageToolCall[], nullable — The tool calls generated by the model. - `id` string, required — The ID of the tool call. - `type` 'function', required — The type of the tool call, currently only `function`. - `function` FunctionCall, required - `name` string, required — The name of the function to call. - `arguments` string, required — The arguments to call the function with, as a JSON string. - `created` integer, required — The Unix timestamp (in seconds) of when the chat completion was created. - `model` string, required — The model used for the chat completion. - `object` 'chat.completion', required — The object type, which is always `chat.completion`. - `service_tier` string, nullable - `system_fingerprint` string, nullable - `usage` CompletionUsage - `completion_tokens` integer, required — Number of tokens in the generated completion. - `prompt_tokens` integer, required — Number of tokens in the prompt. - `total_tokens` integer, required — Total number of tokens used in the request (prompt + completion). - `completion_tokens_details` object, nullable - `prompt_tokens_details` object, nullable ## Other responses - `400` — Bad Request - `403` — Forbidden - `422` — Unprocessable Entity - `429` — Quota Exceeded - `500` — Internal Server Error --- [API](https://skmtc.dev/sarvam/apis/endpoints.md) · [All operations](https://skmtc.dev/sarvam/apis/endpoints/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/sarvam/endpoints/revisions/2b7f7955b147/schema)