Generate OpenAI chat completion from messages

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 plus a fixed set of vendor generation parameters such as top_k, guided_choice, and thinking; other extra fields are dropped, and fields that set the provider endpoint, credentials, or headers (for example api_base, api_key, extra_headers) are rejected with a 422. 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.

POST /v5/chat/completions

Generate OpenAI chat completion from messages

cURL

curl --request POST \
  --url https://api.egp.scale.com/v5/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "top_k": 123,
  "frequency_penalty": 0,
  "function_call": {},
  "functions": [
    {}
  ],
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 123,
  "max_tokens": 123,
  "metadata": {},
  "modalities": [
    "<string>"
  ],
  "n": 123,
  "parallel_tool_calls": true,
  "prediction": {},
  "presence_penalty": 0,
  "reasoning_effort": "<string>",
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "store": true,
  "stream": true,
  "stream_options": {},
  "temperature": 1,
  "tool_choice": "<string>",
  "tools": [
    {}
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "audio": {}
}
'

200

{
  "id": "<string>",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "refusal": "<string>",
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "end_index": 123,
              "start_index": 123,
              "title": "<string>",
              "url": "<string>"
            }
          }
        ],
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "function_call": {
          "arguments": "<string>",
          "name": "<string>"
        },
        "tool_calls": [
          {
            "id": "<string>",
            "function": {
              "arguments": "<string>",
              "name": "<string>"
            },
            "type": "function"
          }
        ]
      },
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ],
        "refusal": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ]
      }
    }
  ],
  "created": 123,
  "model": "<string>",
  "object": "chat.completion",
  "service_tier": "auto",
  "system_fingerprint": "<string>",
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "prompt_tokens_details": {
      "audio_tokens": 123,
      "cached_tokens": 123
    }
  }
}

Authorizations

x-api-key · string · header · required

Headers

x-api-key · string | null

x-openai-api-key · string | null

x-selected-account-id · string | null

Body

application/json

model · string · required

model specified as model_vendor/model, for example openai/gpt-4o

messages · Messages · object[] · required

openai standard message format

top_k · integer | null

Only sample from the top K options for each subsequent token

frequency_penalty · number | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.

Required range: -2 <= x <= 2

function_call · Function Call · object | null

Deprecated in favor of tool_choice. Controls which function is called by the model.

functions · Functions · object[] | null

Deprecated in favor of tools. A list of functions the model may generate JSON inputs for.

logit_bias · Logit Bias · object | null

Modify the likelihood of specified tokens appearing in the completion. Maps tokens to bias values from -100 to 100.

Show child attributes

logprobs · boolean | null

Whether to return log probabilities of the output tokens or not.

max_completion_tokens · integer | null

An upper bound for the number of tokens that can be generated, including visible output tokens and reasoning tokens.

max_tokens · integer | null

Deprecated in favor of max_completion_tokens. The maximum number of tokens to generate.

metadata · Metadata · object | null

Developer-defined tags and values used for filtering completions in the dashboard.

Show child attributes

modalities · string[] | null

Output types that you would like the model to generate for this request.

n · integer | null

How many chat completion choices to generate for each input message.

parallel_tool_calls · boolean | null

Whether to enable parallel function calling during tool use.

prediction · Prediction · object | null

Static predicted output content, such as the content of a text file being regenerated.

presence_penalty · number | null

Number between -2.0 and 2.0. Positive values penalize tokens based on whether they appear in the text so far.

Required range: -2 <= x <= 2

reasoning_effort · string | null

For o1 models only. Constrains effort on reasoning. Values: low, medium, high.

response_format · Response Format · object | null

An object specifying the format that the model must output.

seed · integer | null

If specified, system will attempt to sample deterministically for repeated requests with same seed.

stop · string string[]

Up to 4 sequences where the API will stop generating further tokens.

store · boolean | null

Whether to store the output for use in model distillation or evals products.

stream · boolean | null

If true, partial message deltas will be sent as server-sent events.

stream_options · Stream Options · object | null

Options for streaming response. Only set this when stream is true.

temperature · number | null

What sampling temperature to use. Higher values make output more random, lower more focused.

Required range: 0 <= x <= 2

tool_choice · string Tool Choice · object

Controls which tool is called by the model. Values: none, auto, required, or specific tool.

tools · Tools · object[] | null

A list of tools the model may call. Currently, only functions are supported. Max 128 functions.

top_logprobs · integer | null

Number of most likely tokens to return at each position, with associated log probability.

Required range: 0 <= x <= 20

top_p · number | null

Alternative to temperature. Only tokens comprising top_p probability mass are considered.

Required range: 0 <= x <= 1

audio · Audio · object | null

Parameters for audio output. Required when audio output is requested with modalities: ['audio'].

Response

200

application/json

Successful Response

Response Post-V5-/V5/Chat/Completions

Response Post-V5-/V5/Chat/Completions

id · string · required

choices · Choice · object[] · required

Show child attributes

created · integer · required

model · string · required

object · string · default: chat.completion

Allowed value: "chat.completion"

service_tier · enum<string> | null

Available options: auto, default, flex, scale, priority

system_fingerprint · string | null

usage · CompletionUsage · object | null

Usage statistics for the completion request.

Show child attributes