> For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. > For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Chat Completion POST https://api.sarvam.ai/v2/chat/completions Content-Type: application/json Creates a model response for the given chat conversation. OpenAI-compatible request and response shape; differences from OpenAI are called out in the Open-Source Models documentation. Requires `api-subscription-key`. Keys without beta access to this endpoint receive `400 invalid_request_error` before the model is called. Set `"stream": true` to receive the reply incrementally as server-sent events. Reasoning models return their chain-of-thought in a separate `reasoning_content` field on the message (`delta.reasoning_content` when streaming); reasoning tokens count against `max_tokens`. Reference: https://docs.sarvam.ai/api-reference/open-source/chat-completions ## OpenAPI Specification ```yaml openapi: 3.1.0 info: title: sarvam version: 1.0.0 paths: /v2/chat/completions: post: operationId: chat_completions_v2 summary: Chat Completion description: >- Creates a model response for the given chat conversation. OpenAI-compatible request and response shape; differences from OpenAI are called out in the Open-Source Models documentation. Requires `api-subscription-key`. Keys without beta access to this endpoint receive `400 invalid_request_error` before the model is called. Set `"stream": true` to receive the reply incrementally as server-sent events. Reasoning models return their chain-of-thought in a separate `reasoning_content` field on the message (`delta.reasoning_content` when streaming); reasoning tokens count against `max_tokens`. tags: - openSourceModels parameters: - name: api-subscription-key in: header required: true schema: type: string responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionV2Response' '400': description: >- Invalid request — a malformed field, a capability the model lacks (e.g. an image sent to a text-only model), or a remote image URL. content: application/json: schema: description: Any type '401': description: >- Missing or invalid API key — returned as 403 invalid_api_key_error in practice. content: application/json: schema: description: Any type '403': description: Missing or invalid API key (`invalid_api_key_error`). content: application/json: schema: description: Any type '413': description: Request larger than 10 MB (text and inline images combined). content: application/json: schema: description: Any type '422': description: >- Request that cannot be served — e.g. estimated prompt tokens + max_tokens exceed the model's context window. content: application/json: schema: description: Any type '429': description: Rate limit exceeded. content: application/json: schema: description: Any type requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionV2Request' servers: - url: https://api.sarvam.ai description: Production components: schemas: ChatCompletionRequestSystemMessage: type: object properties: content: type: string description: The contents of the system message. role: type: string enum: - system description: The role of the messages author, in this case `system`. required: - content - role title: ChatCompletionRequestSystemMessage ImageUrlDetail: type: string enum: - auto - low - high default: auto title: ImageUrlDetail ImageURL: type: object properties: url: type: string detail: oneOf: - $ref: '#/components/schemas/ImageUrlDetail' - type: 'null' default: auto required: - url title: ImageURL ChatCompletionRequestUserMessageContentOneOf1Items: oneOf: - type: object properties: type: type: string enum: - image_url image_url: $ref: '#/components/schemas/ImageURL' required: - type - image_url description: ImagePart variant - type: object properties: type: type: string enum: - text text: type: string required: - type - text description: TextPart variant discriminator: propertyName: type title: ChatCompletionRequestUserMessageContentOneOf1Items ChatCompletionRequestUserMessageContent1: type: array items: $ref: >- #/components/schemas/ChatCompletionRequestUserMessageContentOneOf1Items title: ChatCompletionRequestUserMessageContent1 ChatCompletionRequestUserMessageContent: oneOf: - type: string - $ref: '#/components/schemas/ChatCompletionRequestUserMessageContent1' description: | The contents of the user message. title: ChatCompletionRequestUserMessageContent ChatCompletionRequestUserMessage: type: object properties: role: type: string enum: - user description: The role of the messages author, in this case `user`. content: $ref: '#/components/schemas/ChatCompletionRequestUserMessageContent' description: | The contents of the user message. required: - role - content title: ChatCompletionRequestUserMessage FunctionCall: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as a JSON string. required: - name - arguments title: FunctionCall ChatCompletionMessageToolCall: type: object properties: id: type: string description: The ID of the tool call. type: type: string enum: - function description: The type of the tool call, currently only `function`. function: $ref: '#/components/schemas/FunctionCall' required: - id - type - function title: ChatCompletionMessageToolCall ChatCompletionRequestAssistantMessage: type: object properties: content: type: - string - 'null' description: | The contents of the assistant message role: type: string enum: - assistant description: The role of the messages author, in this case `assistant`. tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' description: The tool calls generated by the model. required: - role title: ChatCompletionRequestAssistantMessage ChatCompletionRequestToolMessage: type: object properties: role: type: string enum: - tool description: The role of the messages author, in this case `tool`. content: type: string description: The contents of the tool message. tool_call_id: type: string description: Tool call that this message is responding to. required: - role - content - tool_call_id title: ChatCompletionRequestToolMessage ChatCompletionRequestGenericMessageContentOneOf1Items: oneOf: - type: object properties: type: type: string enum: - image_url image_url: $ref: '#/components/schemas/ImageURL' required: - type - image_url description: ImagePart variant - type: object properties: type: type: string enum: - text text: type: string required: - type - text description: TextPart variant discriminator: propertyName: type title: ChatCompletionRequestGenericMessageContentOneOf1Items ChatCompletionRequestGenericMessageContent1: type: array items: $ref: >- #/components/schemas/ChatCompletionRequestGenericMessageContentOneOf1Items title: ChatCompletionRequestGenericMessageContent1 ChatCompletionRequestGenericMessageContent: oneOf: - type: string - $ref: '#/components/schemas/ChatCompletionRequestGenericMessageContent1' description: The contents of the message. title: ChatCompletionRequestGenericMessageContent ChatCompletionRequestGenericMessage: type: object properties: role: type: string description: The role of the messages author. content: $ref: '#/components/schemas/ChatCompletionRequestGenericMessageContent' description: The contents of the message. name: type: - string - 'null' description: An optional name for the participant. required: - role - content title: ChatCompletionRequestGenericMessage ChatCompletionRequestMessage: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestSystemMessage' - $ref: '#/components/schemas/ChatCompletionRequestUserMessage' - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage' - $ref: '#/components/schemas/ChatCompletionRequestToolMessage' - $ref: '#/components/schemas/ChatCompletionRequestGenericMessage' title: ChatCompletionRequestMessage V2ModelIds: type: string enum: - sarvam-105b - glm5.2 - gemma4 description: >- Model IDs from `GET /v2/models`: - **`sarvam-105b`** — Sarvam flagship chat model. - **`glm5.2`** — open-source; 512K context, tool calling, visible reasoning. - **`gemma4`** — open-source; image input, tool calling. title: V2ModelIds ReasoningEffort: type: string enum: - low - medium - high title: ReasoningEffort StopConfiguration: oneOf: - type: string - type: array items: type: string description: | Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. title: StopConfiguration FunctionDefinition: type: object properties: name: type: string description: The name of the function to be called. description: type: - string - 'null' description: A description of what the function does. parameters: type: - object - 'null' additionalProperties: description: Any type description: >- The parameters the function accepts, described as a JSON Schema object. required: - name title: FunctionDefinition ChatCompletionTool: type: object properties: type: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. function: $ref: '#/components/schemas/FunctionDefinition' required: - type - function title: ChatCompletionTool ToolChoiceOption0: type: string enum: - none - auto - required title: ToolChoiceOption0 ChatCompletionNamedToolChoiceFunction: type: object properties: name: type: string description: The name of the function to call. required: - name title: ChatCompletionNamedToolChoiceFunction ChatCompletionNamedToolChoice: type: object properties: type: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. function: $ref: '#/components/schemas/ChatCompletionNamedToolChoiceFunction' required: - type - function title: ChatCompletionNamedToolChoice ToolChoiceOption: oneOf: - $ref: '#/components/schemas/ToolChoiceOption0' - $ref: '#/components/schemas/ChatCompletionNamedToolChoice' title: ToolChoiceOption JsonSchemaDefinition: type: object properties: name: type: string description: >- The name of the response format. Must contain only alphanumeric characters, underscores and dashes. description: type: - string - 'null' description: >- A description of what the response format is for, used by the model to determine how to respond in the format. schema: type: object additionalProperties: description: Any type description: >- The schema for the response format, described as a JSON Schema object. strict: type: - boolean - 'null' default: false description: >- Whether to enable strict schema adherence when generating the output. required: - name - schema description: The `json_schema` body of a `response_format` of type `json_schema`. title: JsonSchemaDefinition ResponseFormat: oneOf: - type: object properties: type: type: string enum: - json_object description: The type of response format being defined. Always `json_object`. required: - type description: ResponseFormatJsonObject variant - type: object properties: type: type: string enum: - json_schema description: The type of response format being defined. Always `json_schema`. json_schema: $ref: '#/components/schemas/JsonSchemaDefinition' description: >- Structured Outputs configuration options, including a JSON Schema. required: - type - json_schema description: ResponseFormatJsonSchema variant - type: object properties: type: type: string enum: - text description: The type of response format being defined. Always `text`. required: - type description: ResponseFormatText variant discriminator: propertyName: type title: ResponseFormat CreateChatCompletionV2Request: type: object properties: messages: type: array items: $ref: '#/components/schemas/ChatCompletionRequestMessage' description: A list of messages comprising the conversation so far. model: $ref: '#/components/schemas/V2ModelIds' temperature: type: - number - 'null' format: double description: > 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: type: - number - 'null' format: double default: 1 description: > 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: oneOf: - $ref: '#/components/schemas/ReasoningEffort' - type: 'null' description: The effort to use for reasoning max_tokens: type: - integer - 'null' default: 2048 description: >- The maximum number of tokens that can be generated in the chat completion. stream: type: - boolean - 'null' default: false description: >- 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: oneOf: - $ref: '#/components/schemas/StopConfiguration' - type: 'null' 'n': type: - integer - 'null' default: 1 description: >- 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: type: - integer - 'null' description: > 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: type: - number - 'null' format: double default: 0 description: > 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: type: - number - 'null' format: double default: 0 description: > 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. tools: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionTool' description: >- A list of tools the model may call. Currently, only functions are supported as a tool. tool_choice: oneOf: - $ref: '#/components/schemas/ToolChoiceOption' - type: 'null' description: Controls which (if any) tool is called by the model. response_format: oneOf: - $ref: '#/components/schemas/ResponseFormat' - type: 'null' description: >- An object specifying the format that the model must output. Setting `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model generates output matching the supplied JSON Schema. Setting `{ "type": "json_object" }` enables the older JSON mode, which guarantees valid JSON but not a specific schema. extra_body: type: object additionalProperties: description: Any type default: {} description: Extra body to be sent to the model. required: - messages - model title: CreateChatCompletionV2Request FinishReason: type: string enum: - stop - length - tool_calls - content_filter - function_call title: FinishReason Role: type: string enum: - assistant title: Role ChatCompletionResponseMessage: type: object properties: content: type: - string - 'null' description: The contents of the message. refusal: type: - string - 'null' reasoning_content: type: - string - 'null' description: The contents of the reasoning message. role: $ref: '#/components/schemas/Role' description: The role of the author of this message. tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' description: The tool calls generated by the model. required: - content - role title: ChatCompletionResponseMessage Choice: type: object properties: finish_reason: $ref: '#/components/schemas/FinishReason' description: > The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. index: type: integer description: The index of the choice in the list of choices. logprobs: type: - object - 'null' additionalProperties: description: Any type message: $ref: '#/components/schemas/ChatCompletionResponseMessage' required: - finish_reason - index - message title: Choice CompletionUsage: type: object properties: completion_tokens: type: integer description: Number of tokens in the generated completion. prompt_tokens: type: integer description: Number of tokens in the prompt. total_tokens: type: integer description: Total number of tokens used in the request (prompt + completion). completion_tokens_details: type: - object - 'null' additionalProperties: description: Any type prompt_tokens_details: type: - object - 'null' additionalProperties: description: Any type required: - completion_tokens - prompt_tokens - total_tokens title: CompletionUsage CreateChatCompletionV2Response: type: object properties: id: type: string description: A unique identifier for the chat completion. choices: type: array items: $ref: '#/components/schemas/Choice' description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. created: type: integer description: >- The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. object: type: string enum: - chat.completion description: The object type, which is always `chat.completion`. service_tier: type: - string - 'null' system_fingerprint: type: - string - 'null' usage: oneOf: - $ref: '#/components/schemas/CompletionUsage' - type: 'null' required: - id - choices - created - model - object title: CreateChatCompletionV2Response securitySchemes: ApiKeyAuth: type: apiKey in: header name: api-subscription-key HTTPBearer: type: http scheme: bearer ``` ## Examples **Request** ```json { "messages": [ { "content": "Summarise the causes of the 2008 financial crisis.", "role": "user" } ], "model": "glm5.2" } ``` **Response** ```json { "id": "20250101_0a1b2c3d-1234-5678-9abc-def012345678", "choices": [ { "finish_reason": "stop", "index": 0, "message": { "content": "The 2008 financial crisis was driven by a housing bubble, subprime lending, and the collapse of mortgage-backed securities.", "role": "assistant", "refusal": null, "reasoning_content": null, "tool_calls": null }, "logprobs": {} } ], "created": 1735689600, "model": "glm5.2", "object": "chat.completion", "usage": { "completion_tokens": 24, "prompt_tokens": 18, "total_tokens": 42 } } ``` **SDK Code** ```python Open-Source Models_chat_completions_v2_example from sarvamai import SarvamAI, ChatCompletionRequestSystemMessage client = SarvamAI( api_subscription_key="YOUR_API_KEY_HERE", ) client.open_source_models.chat_completions_v2( messages=[ ChatCompletionRequestSystemMessage( content="Summarise the causes of the 2008 financial crisis.", role="user", ) ], model="glm5.2", ) ``` ```javascript Open-Source Models_chat_completions_v2_example const url = 'https://api.sarvam.ai/v2/chat/completions'; const options = { method: 'POST', headers: { 'api-subscription-key': '', 'Content-Type': 'application/json' }, body: '{"messages":[{"content":"Summarise the causes of the 2008 financial crisis.","role":"user"}],"model":"glm5.2"}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Open-Source Models_chat_completions_v2_example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.sarvam.ai/v2/chat/completions" payload := strings.NewReader("{\n \"messages\": [\n {\n \"content\": \"Summarise the causes of the 2008 financial crisis.\",\n \"role\": \"user\"\n }\n ],\n \"model\": \"glm5.2\"\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("api-subscription-key", "") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Open-Source Models_chat_completions_v2_example require 'uri' require 'net/http' url = URI("https://api.sarvam.ai/v2/chat/completions") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["api-subscription-key"] = '' request["Content-Type"] = 'application/json' request.body = "{\n \"messages\": [\n {\n \"content\": \"Summarise the causes of the 2008 financial crisis.\",\n \"role\": \"user\"\n }\n ],\n \"model\": \"glm5.2\"\n}" response = http.request(request) puts response.read_body ``` ```java Open-Source Models_chat_completions_v2_example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.sarvam.ai/v2/chat/completions") .header("api-subscription-key", "") .header("Content-Type", "application/json") .body("{\n \"messages\": [\n {\n \"content\": \"Summarise the causes of the 2008 financial crisis.\",\n \"role\": \"user\"\n }\n ],\n \"model\": \"glm5.2\"\n}") .asString(); ``` ```php Open-Source Models_chat_completions_v2_example request('POST', 'https://api.sarvam.ai/v2/chat/completions', [ 'body' => '{ "messages": [ { "content": "Summarise the causes of the 2008 financial crisis.", "role": "user" } ], "model": "glm5.2" }', 'headers' => [ 'Content-Type' => 'application/json', 'api-subscription-key' => '', ], ]); echo $response->getBody(); ``` ```csharp Open-Source Models_chat_completions_v2_example using RestSharp; var client = new RestClient("https://api.sarvam.ai/v2/chat/completions"); var request = new RestRequest(Method.POST); request.AddHeader("api-subscription-key", ""); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"messages\": [\n {\n \"content\": \"Summarise the causes of the 2008 financial crisis.\",\n \"role\": \"user\"\n }\n ],\n \"model\": \"glm5.2\"\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Open-Source Models_chat_completions_v2_example import Foundation let headers = [ "api-subscription-key": "", "Content-Type": "application/json" ] let parameters = [ "messages": [ [ "content": "Summarise the causes of the 2008 financial crisis.", "role": "user" ] ], "model": "glm5.2" ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.sarvam.ai/v2/chat/completions")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ```