MyApp

<back to all web services

ChatCompletion

AI

Chat Completions API (OpenAI-Compatible)

The following routes are available for this service:
POST/v1/chat/completions
ChatCompletion Parameters:
NameParameterData TypeRequiredDescription
MessagesbodyList<AiMessage>YesThe messages to generate chat completions for.
ModelbodystringYesID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API

Allowable Values

  • gemini-flash-latest
  • gemini-flash-lite-latest
  • glm-4.6
  • gpt-oss:120b
  • gpt-oss:20b
  • kimi-k2
  • kimi-k2-thinking
  • llama4:400b
  • minimax-m2
  • mistral-small3.2:24b
AudiobodyAiChatAudioNoParameters for audio output. Required when audio output is requested with modalities: [audio]
LogitBiasbodyDictionary<int, int>NoModify the likelihood of specified tokens appearing in the completion.
MetadatabodyDictionary<string, string>NoSet of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format.
ReasoningEffortbodystringNoConstrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high (none, default). Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Allowable Values

  • low
  • medium
  • high
  • none
  • default
ResponseFormatbodyAiResponseFormatNoAn object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. Setting Type to ResponseFormat.JsonObject enables JSON mode, which guarantees the message the model generates is valid JSON.
ServiceTierbodystringNoSpecifies the processing type used for serving the request.

Allowable Values

  • auto
  • default
SafetyIdentifierbodystringNoA stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user.
StopbodyList<string>NoUp to 4 sequences where the API will stop generating further tokens.
ModalitiesbodyList<string>NoOutput types that you would like the model to generate. Most models are capable of generating text, which is the default:
PromptCacheKeybodystringNoUsed by OpenAI to cache responses for similar requests to optimize your cache hit rates.
ToolsbodyList<Tool>NoA list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
VerbositybodystringNoConstrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

Allowable Values

  • low
  • medium
  • high
Temperaturebodydouble?NoWhat 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.

Valid Range: 0 - 2

MaxCompletionTokensbodyint?NoAn upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Valid Range: 1 -

TopLogprobsbodyint?NoAn integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Valid Range: 0 - 20

TopPbodydouble?NoAn 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.

Valid Range: 0 - 1

FrequencyPenaltybodydouble?NoNumber 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.

Valid Range: 0 - 2

PresencePenaltybodydouble?NoNumber 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.

Valid Range: 0 - 2

Seedbodyint?NoThis 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.
Nbodyint?NoHow 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.
Storebodybool?NoWhether or not to store the output of this chat completion request for use in our model distillation or evals products.
Logprobsbodybool?NoWhether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.
ParallelToolCallsbodybool?NoWhether to enable parallel function calling during tool use.
EnableThinkingbodybool?NoWhether to enable thinking mode for some Qwen models and providers.
Streambodybool?NoIf set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message.
AiMessage Parameters:
NameParameterData TypeRequiredDescription
ContentformList<AiContent>NoThe contents of the message.
RoleformstringYesThe role of the author of this message. Valid values are `system`, `user`, `assistant` and `tool`.
NameformstringNoAn optional name for the participant. Provides the model information to differentiate between participants of the same role.
ToolCallsformList<ToolCall>NoThe tool calls generated by the model, such as function calls.
ToolCallIdformstringNoTool call that this message is responding to.
AiContent Parameters:
NameParameterData TypeRequiredDescription
TypeformstringYesThe type of the content part.
ToolCall Parameters:
NameParameterData TypeRequiredDescription
IdformstringYesThe ID of the tool call.
TypeformstringYesThe type of the tool. Currently, only `function` is supported.
FunctionformstringYesThe function that the model called.
AiChatAudio Parameters:
NameParameterData TypeRequiredDescription
FormatformstringYesSpecifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16.
VoiceformstringYesThe voice the model uses to respond. Supported voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer.
AiResponseFormat Parameters:
NameParameterData TypeRequiredDescription
TypeformResponseFormatNoAn object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.
ResponseFormat Enum:
NameValue
Texttext
JsonObjectjson_object
Tool Parameters:
NameParameterData TypeRequiredDescription
TypeformToolTypeNoThe type of the tool. Currently, only function is supported.
ToolType Enum:
NameValue
Functionfunction
ChatResponse Parameters:
NameParameterData TypeRequiredDescription
IdformstringYesA unique identifier for the chat completion.
ChoicesformList<Choice>YesA list of chat completion choices. Can be more than one if n is greater than 1.
CreatedformlongNoThe Unix timestamp (in seconds) of when the chat completion was created.
ModelformstringYesThe model used for the chat completion.
SystemFingerprintformstringNoThis fingerprint represents the backend configuration that the model runs with.
ObjectformstringYesThe object type, which is always chat.completion.
ServiceTierformstringNoSpecifies the processing type used for serving the request.
UsageformAiUsageYesUsage statistics for the completion request.
ProviderformstringNoThe provider used for the chat completion.
MetadataformDictionary<string, string>NoSet of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format.
ResponseStatusformResponseStatusNo
Choice Parameters:
NameParameterData TypeRequiredDescription
FinishReasonformstringYesThe 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
IndexformintNoThe index of the choice in the list of choices.
MessageformChoiceMessageYesA chat completion message generated by the model.
ChoiceMessage Parameters:
NameParameterData TypeRequiredDescription
ContentformstringYesThe contents of the message.
RefusalformstringNoThe refusal message generated by the model.
ReasoningformstringNoThe reasoning process used by the model.
RoleformstringYesThe role of the author of this message.
AnnotationsformList<ChoiceAnnotation>NoAnnotations for the message, when applicable, as when using the web search tool.
AudioformChoiceAudioNoIf the audio output modality is requested, this object contains data about the audio response from the model.
ToolCallsformList<ToolCall>NoThe tool calls generated by the model, such as function calls.
ChoiceAnnotation Parameters:
NameParameterData TypeRequiredDescription
TypeformstringYesThe type of the URL citation. Always url_citation.
UrlCitationformUrlCitationYesA URL citation when using web search.
UrlCitation Parameters:
NameParameterData TypeRequiredDescription
EndIndexformintNoThe index of the last character of the URL citation in the message.
StartIndexformintNoThe index of the first character of the URL citation in the message.
TitleformstringYesThe title of the web resource.
UrlformstringYesThe URL of the web resource.
ChoiceAudio Parameters:
NameParameterData TypeRequiredDescription
DataformstringYesBase64 encoded audio bytes generated by the model, in the format specified in the request.
ExpiresAtformintNoThe Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.
IdformstringYesUnique identifier for this audio response.
TranscriptformstringYesTranscript of the audio generated by the model.
AiUsage Parameters:
NameParameterData TypeRequiredDescription
CompletionTokensformintNoNumber of tokens in the generated completion.
PromptTokensformintNoNumber of tokens in the prompt.
TotalTokensformintNoTotal number of tokens used in the request (prompt + completion).
CompletionTokensDetailsformAiCompletionUsageNoBreakdown of tokens used in a completion.
PromptTokensDetailsformAiPromptUsageNoBreakdown of tokens used in the prompt.
AiCompletionUsage Parameters:
NameParameterData TypeRequiredDescription
AcceptedPredictionTokensformintNoWhen using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
AudioTokensformintNoAudio input tokens generated by the model.
ReasoningTokensformintNoTokens generated by the model for reasoning.
RejectedPredictionTokensformintNoWhen using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion.
AiPromptUsage Parameters:
NameParameterData TypeRequiredDescription
AcceptedPredictionTokensformintNoWhen using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
AudioTokensformintNoAudio input tokens present in the prompt.
CachedTokensformintNoCached tokens present in the prompt.

To override the Content-type in your clients, use the HTTP Accept Header, append the .json suffix or ?format=json

To embed the response in a jsonp callback, append ?callback=myCallback

HTTP + JSON

The following are sample HTTP requests and responses. The placeholders shown need to be replaced with actual values.

POST /v1/chat/completions HTTP/1.1 
Host: blazor-vue.web-templates.io 
Accept: application/json
Content-Type: application/json
Content-Length: length

{"messages":[{"content":[{}],"role":"String","name":"String","tool_calls":[{"id":"String","type":"String","function":"String"}],"tool_call_id":"String"}],"model":"String","audio":{"format":"String","voice":"String"},"logit_bias":{"0":0},"metadata":{"String":"String"},"reasoning_effort":"String","response_format":{"response_format":"text"},"service_tier":"String","safety_identifier":"String","stop":["String"],"modalities":["String"],"prompt_cache_key":"String","tools":[{"type":"function"}],"verbosity":"String","temperature":0,"max_completion_tokens":0,"top_logprobs":0,"top_p":0,"frequency_penalty":0,"presence_penalty":0,"seed":0,"n":0,"store":false,"logprobs":false,"parallel_tool_calls":false,"enable_thinking":false,"stream":false}
HTTP/1.1 200 OK
Content-Type: application/json
Content-Length: length

{"id":"String","choices":[{"finish_reason":"String","index":0,"message":{"content":"String","refusal":"String","reasoning":"String","role":"String","annotations":[{"type":"String","url_citation":{"end_index":0,"start_index":0,"title":"String","url":"String"}}],"audio":{"data":"String","expires_at":0,"id":"String","transcript":"String"},"tool_calls":[{"id":"String","type":"String","function":"String"}]}}],"created":0,"model":"String","system_fingerprint":"String","object":"String","service_tier":"String","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":{"accepted_prediction_tokens":0,"audio_tokens":0,"cached_tokens":0}},"provider":"String","metadata":{"String":"String"},"responseStatus":{"errorCode":"String","message":"String","stackTrace":"String","errors":[{"errorCode":"String","fieldName":"String","message":"String","meta":{"String":"String"}}],"meta":{"String":"String"}}}