## Generate OpenAI chat completion from messages `client.Chat.Completions.New(ctx, params) (*ChatCompletionNewResponseUnion, error)` **post** `/v5/chat/completions` Generates a chat completion from an OpenAI-style `messages` array. Use this endpoint for standard messages-based chat inference; use /v5/completions instead when you have a raw text `prompt` rather than messages, /v5/responses for the OpenAI Responses API contract, and /v5/inference when the payload does not follow any OpenAI schema. The request accepts the OpenAI Chat Completions parameters (extra fields are allowed and forwarded), and the model is selected from `model` given as `vendor/name`; most vendors are served through the litellm proxy gateway, while OpenAI may use a native gateway. When `stream` is set the response is delivered as server-sent events of `chat.completion.chunk`; otherwise a single `chat.completion` object is returned. Token usage is recorded for the account, and for streaming responses it is read from the final chunk. ### Parameters - `params ChatCompletionNewParams` - `Messages param.Field[[]map[string, any]]` Body param: openai standard message format - `Model param.Field[string]` Body param: model specified as `model_vendor/model`, for example `openai/gpt-4o` - `Audio param.Field[map[string, any]]` Body param: Parameters for audio output. Required when audio output is requested with modalities: ['audio']. - `FrequencyPenalty param.Field[float64]` Body param: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. - `FunctionCall param.Field[map[string, any]]` Body param: Deprecated in favor of tool_choice. Controls which function is called by the model. - `Functions param.Field[[]map[string, any]]` Body param: Deprecated in favor of tools. A list of functions the model may generate JSON inputs for. - `LogitBias param.Field[map[string, int64]]` Body param: Modify the likelihood of specified tokens appearing in the completion. Maps tokens to bias values from -100 to 100. - `Logprobs param.Field[bool]` Body param: Whether to return log probabilities of the output tokens or not. - `MaxCompletionTokens param.Field[int64]` Body param: An upper bound for the number of tokens that can be generated, including visible output tokens and reasoning tokens. - `MaxTokens param.Field[int64]` Body param: Deprecated in favor of max_completion_tokens. The maximum number of tokens to generate. - `Metadata param.Field[map[string, string]]` Body param: Developer-defined tags and values used for filtering completions in the dashboard. - `Modalities param.Field[[]string]` Body param: Output types that you would like the model to generate for this request. - `N param.Field[int64]` Body param: How many chat completion choices to generate for each input message. - `ParallelToolCalls param.Field[bool]` Body param: Whether to enable parallel function calling during tool use. - `Prediction param.Field[map[string, any]]` Body param: Static predicted output content, such as the content of a text file being regenerated. - `PresencePenalty param.Field[float64]` Body param: Number between -2.0 and 2.0. Positive values penalize tokens based on whether they appear in the text so far. - `ReasoningEffort param.Field[string]` Body param: For o1 models only. Constrains effort on reasoning. Values: low, medium, high. - `ResponseFormat param.Field[map[string, any]]` Body param: An object specifying the format that the model must output. - `Seed param.Field[int64]` Body param: If specified, system will attempt to sample deterministically for repeated requests with same seed. - `Stop param.Field[ChatCompletionNewParamsStopUnion]` Body param: Up to 4 sequences where the API will stop generating further tokens. - `string` - `[]string` - `Store param.Field[bool]` Body param: Whether to store the output for use in model distillation or evals products. - `` - `StreamOptions param.Field[map[string, any]]` Body param: Options for streaming response. Only set this when stream is true. - `Temperature param.Field[float64]` Body param: What sampling temperature to use. Higher values make output more random, lower more focused. - `ToolChoice param.Field[ChatCompletionNewParamsToolChoiceUnion]` Body param: Controls which tool is called by the model. Values: none, auto, required, or specific tool. - `string` - `map[string, any]` - `Tools param.Field[[]map[string, any]]` Body param: A list of tools the model may call. Currently, only functions are supported. Max 128 functions. - `TopK param.Field[int64]` Body param: Only sample from the top K options for each subsequent token - `TopLogprobs param.Field[int64]` Body param: Number of most likely tokens to return at each position, with associated log probability. - `TopP param.Field[float64]` Body param: Alternative to temperature. Only tokens comprising top_p probability mass are considered. - `XOpenAIAPIKey param.Field[string]` Header param ### Returns - `type ChatCompletionNewResponseUnion interface{…}` - `type ChatCompletion struct{…}` - `ID string` - `Choices []ChatCompletionChoice` - `FinishReason string` - `const ChatCompletionChoiceFinishReasonStop ChatCompletionChoiceFinishReason = "stop"` - `const ChatCompletionChoiceFinishReasonLength ChatCompletionChoiceFinishReason = "length"` - `const ChatCompletionChoiceFinishReasonToolCalls ChatCompletionChoiceFinishReason = "tool_calls"` - `const ChatCompletionChoiceFinishReasonContentFilter ChatCompletionChoiceFinishReason = "content_filter"` - `const ChatCompletionChoiceFinishReasonFunctionCall ChatCompletionChoiceFinishReason = "function_call"` - `Index int64` - `Message ChatCompletionChoiceMessage` A chat completion message generated by the model. - `Role Assistant` - `const AssistantAssistant Assistant = "assistant"` - `Annotations []ChatCompletionChoiceMessageAnnotation` - `Type URLCitation` - `const URLCitationURLCitation URLCitation = "url_citation"` - `URLCitation ChatCompletionChoiceMessageAnnotationURLCitation` A URL citation when using web search. - `EndIndex int64` - `StartIndex int64` - `Title string` - `URL string` - `Audio ChatCompletionChoiceMessageAudio` If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](https://platform.openai.com/docs/guides/audio). - `ID string` - `Data string` - `ExpiresAt int64` - `Transcript string` - `Content string` - `FunctionCall ChatCompletionChoiceMessageFunctionCall` Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. - `Arguments string` - `Name string` - `Refusal string` - `ToolCalls []ChatCompletionChoiceMessageToolCallUnion` - `type ChatCompletionChoiceMessageToolCallChatCompletionMessageFunctionToolCall struct{…}` A call to a function tool created by the model. - `ID string` - `Function ChatCompletionChoiceMessageToolCallChatCompletionMessageFunctionToolCallFunction` The function that the model called. - `Arguments string` - `Name string` - `Type Function` - `const FunctionFunction Function = "function"` - `type ChatCompletionChoiceMessageToolCallChatCompletionMessageCustomToolCall struct{…}` A call to a custom tool created by the model. - `ID string` - `Custom ChatCompletionChoiceMessageToolCallChatCompletionMessageCustomToolCallCustom` The custom tool that the model called. - `Input string` - `Name string` - `Type Custom` - `const CustomCustom Custom = "custom"` - `Logprobs ChoiceLogprobs` Log probability information for the choice. - `Content []ChatCompletionTokenLogprob` - `Token string` - `Logprob float64` - `TopLogprobs []ChatCompletionTokenLogprobTopLogprob` - `Token string` - `Logprob float64` - `Bytes []int64` - `Bytes []int64` - `Refusal []ChatCompletionTokenLogprob` - `Token string` - `Logprob float64` - `TopLogprobs []ChatCompletionTokenLogprobTopLogprob` - `Bytes []int64` - `Created int64` - `Model string` - `Object ChatCompletionObject` - `const ChatCompletionObjectChatCompletion ChatCompletionObject = "chat.completion"` - `ServiceTier ChatCompletionServiceTier` - `const ChatCompletionServiceTierAuto ChatCompletionServiceTier = "auto"` - `const ChatCompletionServiceTierDefault ChatCompletionServiceTier = "default"` - `const ChatCompletionServiceTierFlex ChatCompletionServiceTier = "flex"` - `const ChatCompletionServiceTierScale ChatCompletionServiceTier = "scale"` - `const ChatCompletionServiceTierPriority ChatCompletionServiceTier = "priority"` - `SystemFingerprint string` - `Usage CompletionUsage` Usage statistics for the completion request. - `CompletionTokens int64` - `PromptTokens int64` - `TotalTokens int64` - `CompletionTokensDetails CompletionUsageCompletionTokensDetails` Breakdown of tokens used in a completion. - `AcceptedPredictionTokens int64` - `AudioTokens int64` - `ReasoningTokens int64` - `RejectedPredictionTokens int64` - `PromptTokensDetails CompletionUsagePromptTokensDetails` Breakdown of tokens used in the prompt. - `AudioTokens int64` - `CachedTokens int64` - `type ChatCompletionChunk struct{…}` - `ID string` - `Choices []ChatCompletionChunkChoice` - `Delta ChatCompletionChunkChoiceDelta` A chat completion delta generated by streamed model responses. - `Content string` - `FunctionCall ChatCompletionChunkChoiceDeltaFunctionCall` Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. - `Arguments string` - `Name string` - `Refusal string` - `Role string` - `const ChatCompletionChunkChoiceDeltaRoleDeveloper ChatCompletionChunkChoiceDeltaRole = "developer"` - `const ChatCompletionChunkChoiceDeltaRoleSystem ChatCompletionChunkChoiceDeltaRole = "system"` - `const ChatCompletionChunkChoiceDeltaRoleUser ChatCompletionChunkChoiceDeltaRole = "user"` - `const ChatCompletionChunkChoiceDeltaRoleAssistant ChatCompletionChunkChoiceDeltaRole = "assistant"` - `const ChatCompletionChunkChoiceDeltaRoleTool ChatCompletionChunkChoiceDeltaRole = "tool"` - `ToolCalls []ChatCompletionChunkChoiceDeltaToolCall` - `Index int64` - `ID string` - `Function ChatCompletionChunkChoiceDeltaToolCallFunction` - `Arguments string` - `Name string` - `Type string` - `const ChatCompletionChunkChoiceDeltaToolCallTypeFunction ChatCompletionChunkChoiceDeltaToolCallType = "function"` - `Index int64` - `FinishReason string` - `const ChatCompletionChunkChoiceFinishReasonStop ChatCompletionChunkChoiceFinishReason = "stop"` - `const ChatCompletionChunkChoiceFinishReasonLength ChatCompletionChunkChoiceFinishReason = "length"` - `const ChatCompletionChunkChoiceFinishReasonToolCalls ChatCompletionChunkChoiceFinishReason = "tool_calls"` - `const ChatCompletionChunkChoiceFinishReasonContentFilter ChatCompletionChunkChoiceFinishReason = "content_filter"` - `const ChatCompletionChunkChoiceFinishReasonFunctionCall ChatCompletionChunkChoiceFinishReason = "function_call"` - `Logprobs ChoiceLogprobs` Log probability information for the choice. - `Created int64` - `Model string` - `Object ChatCompletionChunkObject` - `const ChatCompletionChunkObjectChatCompletionChunk ChatCompletionChunkObject = "chat.completion.chunk"` - `ServiceTier ChatCompletionChunkServiceTier` - `const ChatCompletionChunkServiceTierAuto ChatCompletionChunkServiceTier = "auto"` - `const ChatCompletionChunkServiceTierDefault ChatCompletionChunkServiceTier = "default"` - `const ChatCompletionChunkServiceTierFlex ChatCompletionChunkServiceTier = "flex"` - `const ChatCompletionChunkServiceTierScale ChatCompletionChunkServiceTier = "scale"` - `const ChatCompletionChunkServiceTierPriority ChatCompletionChunkServiceTier = "priority"` - `SystemFingerprint string` - `Usage CompletionUsage` Usage statistics for the completion request. ### Example ```go package main import ( "context" "fmt" "github.com/scaleapi/sgp-dev-go" "github.com/scaleapi/sgp-dev-go/option" ) func main() { client := sgpdev.NewClient( option.WithAPIKey("My API Key"), option.WithAccountID("My Account ID"), ) completion, err := client.Chat.Completions.New(context.TODO(), sgpdev.ChatCompletionNewParams{ Messages: []map[string]any{map[string]any{ "foo": "bar", }}, Model: "model", }) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", completion) } ``` #### Response ```json { "id": "id", "choices": [ { "finish_reason": "stop", "index": 0, "message": { "role": "assistant", "annotations": [ { "type": "url_citation", "url_citation": { "end_index": 0, "start_index": 0, "title": "title", "url": "url" } } ], "audio": { "id": "id", "data": "data", "expires_at": 0, "transcript": "transcript" }, "content": "content", "function_call": { "arguments": "arguments", "name": "name" }, "refusal": "refusal", "tool_calls": [ { "id": "id", "function": { "arguments": "arguments", "name": "name" }, "type": "function" } ] }, "logprobs": { "content": [ { "token": "token", "logprob": 0, "top_logprobs": [ { "token": "token", "logprob": 0, "bytes": [ 0 ] } ], "bytes": [ 0 ] } ], "refusal": [ { "token": "token", "logprob": 0, "top_logprobs": [ { "token": "token", "logprob": 0, "bytes": [ 0 ] } ], "bytes": [ 0 ] } ] } } ], "created": 0, "model": "model", "object": "chat.completion", "service_tier": "auto", "system_fingerprint": "system_fingerprint", "usage": { "completion_tokens": 0, "prompt_tokens": 0, "total_tokens": 0, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens": 0 }, "prompt_tokens_details": { "audio_tokens": 0, "cached_tokens": 0 } } } ```