Skip to main content
POST
/
v1
/
chat
/
completions
Create Chat Completion
curl --request POST \
  --url http://localhost:8080/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "openai/gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?",
      "tool_call_id": "<string>",
      "tool_calls": [
        {
          "id": "tool_123",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\": \"San Francisco, CA\"}"
          }
        }
      ],
      "refusal": "<string>",
      "annotations": [
        {
          "type": "<string>",
          "url_citation": {
            "start_index": 123,
            "end_index": 123,
            "title": "<string>",
            "url": "<string>",
            "sources": "<any>",
            "type": "<string>"
          }
        }
      ],
      "thought": "<string>"
    }
  ],
  "max_tokens": 1000,
  "temperature": 1,
  "top_p": 0.5,
  "n": 1,
  "stream": false,
  "stream_options": {
    "include_usage": true
  },
  "stop": "<string>",
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "logit_bias": {},
  "logprobs": false,
  "top_logprobs": 10,
  "max_completion_tokens": 123,
  "metadata": {},
  "modalities": [
    "<string>"
  ],
  "parallel_tool_calls": true,
  "prompt_cache_key": "<string>",
  "reasoning_effort": "<string>",
  "response_format": {
    "type": "text"
  },
  "safety_identifier": "<string>",
  "seed": 123,
  "service_tier": "auto",
  "store": true,
  "tool_choice": "none",
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "<string>",
        "name": "<string>",
        "parameters": {}
      }
    }
  ],
  "user": "<string>",
  "verbosity": "<string>",
  "fallbacks": [
    "anthropic/claude-3-sonnet-20240229",
    "openai/gpt-4o"
  ]
}'
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "user",
        "content": "Hello, how are you?",
        "tool_call_id": "<string>",
        "tool_calls": [
          {
            "id": "tool_123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\": \"San Francisco, CA\"}"
            }
          }
        ],
        "refusal": "<string>",
        "annotations": [
          {
            "type": "<string>",
            "url_citation": {
              "start_index": 123,
              "end_index": 123,
              "title": "<string>",
              "url": "<string>",
              "sources": "<any>",
              "type": "<string>"
            }
          }
        ],
        "thought": "<string>"
      },
      "finish_reason": "stop",
      "stop": "<string>",
      "log_probs": {
        "content": [
          {
            "bytes": [
              123
            ],
            "logprob": -0.123,
            "token": "hello",
            "top_logprobs": [
              {
                "bytes": [
                  123
                ],
                "logprob": -0.456,
                "token": "world"
              }
            ]
          }
        ],
        "refusal": [
          {
            "bytes": [
              123
            ],
            "logprob": -0.456,
            "token": "world"
          }
        ]
      }
    }
  ],
  "data": [
    {
      "index": 123,
      "object": "<string>",
      "embedding": [
        123
      ]
    }
  ],
  "speech": {
    "usage": {
      "characters": 123
    },
    "audio": "aSDinaTvuI8gbWludGxpZnk="
  },
  "transcribe": {
    "text": "<string>",
    "logprobs": [
      {
        "token": "<string>",
        "log_prob": 123
      }
    ],
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 123,
      "total_tokens": 123
    }
  },
  "messages": [
    {
      "role": "user",
      "content": "<string>"
    }
  ],
  "conversation_id": "<string>",
  "finish_reason": "<string>",
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "prompt_cache": {
    "status": "<string>"
  },
  "model": "gpt-4o",
  "created": 1677652288,
  "service_tier": "<string>",
  "system_fingerprint": "<string>",
  "usage": {
    "prompt_tokens": 56,
    "completion_tokens": 31,
    "total_tokens": 87,
    "completion_tokens_details": {
      "reasoning_tokens": 123,
      "audio_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123
    }
  },
  "extra_fields": {
    "provider": "openai",
    "request_type": "list_models",
    "model_requested": "<string>",
    "model_params": {
      "temperature": 0.7,
      "top_p": 0.9,
      "top_k": 40,
      "max_tokens": 1000,
      "stop_sequences": [
        "\n\n",
        "END"
      ],
      "presence_penalty": 0,
      "frequency_penalty": 0,
      "tools": [
        {
          "id": "<string>",
          "type": "function",
          "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
              "type": "object",
              "description": "<string>",
              "properties": {},
              "required": [
                "<string>"
              ],
              "enum": [
                "<string>"
              ]
            }
          }
        }
      ],
      "tool_choice": {
        "type": "auto",
        "function": {
          "name": "get_weather"
        }
      },
      "parallel_tool_calls": true
    },
    "latency": 1234,
    "billed_usage": {
      "prompt_tokens": 123,
      "completion_tokens": 123,
      "search_units": 123,
      "classifications": 123
    },
    "raw_response": {}
  }
}

Body

application/json
​
model
string
required
Example:
​
messages
object[]
required
Minimum length: 1
​
max_tokens
integer
Required range: x >= 1
Example:
​
temperature
number
Required range: 0 <= x <= 2
​
top_p
number
Required range: 0 <= x <= 1
​
n
integer
default:1
​
stream
boolean
default:false
​
stream_options
object
​
stop
​
presence_penalty
number
Required range: -2 <= x <= 2
​
frequency_penalty
number
Required range: -2 <= x <= 2
​
logit_bias
object
​
logprobs
boolean
default:false
​
top_logprobs
integer
Required range: 0 <= x <= 20
​
max_completion_tokens
integer
​
metadata
object
​
modalities
string[]
​
parallel_tool_calls
boolean
​
prompt_cache_key
string
​
reasoning_effort
string
​
response_format
object
​
safety_identifier
string
​
seed
integer
​
service_tier
enum<string>
Available options:
auto,
default
​
store
boolean
​
tool_choice
Available options:
none,
auto,
required
​
tools
object[]
​
user
string
​
verbosity
string
​
fallbacks
string[]
Example:

Response

​
id
string
Example:
​
object
enum<string>
Available options:
text.completion,
chat.completion,
embedding,
speech,
transcribe,
responses.completion
Example:
​
choices
object[]
​
data
object[]
​
speech
object
​
transcribe
object
​
messages
object[]
​
conversation_id
string
​
finish_reason
string
​
stop_reason
string
​
stop_sequence
string
​
prompt_cache
object
​
model
string
Example:
​
created
integer
Example:
​
service_tier
string
​
system_fingerprint
string
​
usage
object
​
extra_fields
object