Create a chat completion

Creates a completion for the provided messages. Supports streaming via SSE.

POST /v1/chat/completions

Create a chat completion

cURL

curl --request POST \
  --url http://localhost:8080/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4",
  "messages": [
    {
      "role": "assistant",
      "name": "<string>",
      "content": "<string>",
      "tool_call_id": "<string>",
      "refusal": "<string>",
      "audio": {
        "id": "<string>",
        "data": "<string>",
        "expires_at": 123,
        "transcript": "<string>"
      },
      "reasoning": "<string>",
      "reasoning_details": [
        {
          "id": "<string>",
          "index": 123,
          "type": "reasoning.summary",
          "summary": "<string>",
          "text": "<string>",
          "signature": "<string>",
          "data": "<string>"
        }
      ],
      "annotations": [
        {
          "type": "<string>",
          "url_citation": {
            "start_index": 123,
            "end_index": 123,
            "title": "<string>",
            "url": "<string>",
            "sources": {},
            "type": "<string>"
          }
        }
      ],
      "tool_calls": [
        {
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          },
          "index": 123,
          "type": "<string>",
          "id": "<string>"
        }
      ]
    }
  ],
  "fallbacks": [
    "<string>"
  ],
  "stream": true,
  "frequency_penalty": 0,
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 123,
  "metadata": {},
  "modalities": [
    "<string>"
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "prompt_cache_key": "<string>",
  "reasoning": {
    "effort": "none",
    "max_tokens": 123
  },
  "response_format": {},
  "safety_identifier": "<string>",
  "service_tier": "<string>",
  "stream_options": {
    "include_obfuscation": true,
    "include_usage": true
  },
  "store": true,
  "temperature": 1,
  "tool_choice": "none",
  "tools": [
    {
      "type": "function",
      "custom": {},
      "cache_control": {
        "type": "ephemeral",
        "ttl": "<string>"
      }
    }
  ],
  "seed": 123,
  "top_p": 0.5,
  "top_logprobs": 10,
  "stop": "<string>",
  "prediction": {
    "type": "<string>",
    "content": "<string>"
  },
  "prompt_cache_retention": "in-memory",
  "web_search_options": {
    "search_context_size": "low",
    "user_location": {
      "type": "<string>",
      "approximate": {
        "city": "<string>",
        "country": "<string>",
        "region": "<string>",
        "timezone": "<string>"
      }
    }
  },
  "truncation": "<string>",
  "user": "<string>",
  "verbosity": "low"
}
'

200

{
  "id": "<string>",
  "choices": [
    {
      "index": 123,
      "finish_reason": "<string>",
      "log_probs": {
        "content": [
          {
            "bytes": [
              123
            ],
            "logprob": 123,
            "token": "<string>",
            "top_logprobs": [
              {
                "bytes": [
                  123
                ],
                "logprob": 123,
                "token": "<string>"
              }
            ]
          }
        ],
        "refusal": [
          {
            "bytes": [
              123
            ],
            "logprob": 123,
            "token": "<string>"
          }
        ],
        "text_offset": [
          123
        ],
        "token_logprobs": [
          123
        ],
        "tokens": [
          "<string>"
        ],
        "top_logprobs": [
          {}
        ]
      },
      "text": "<string>",
      "delta": {
        "role": "<string>",
        "content": "<string>",
        "refusal": "<string>",
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "reasoning": "<string>",
        "reasoning_details": [
          {
            "id": "<string>",
            "index": 123,
            "type": "reasoning.summary",
            "summary": "<string>",
            "text": "<string>",
            "signature": "<string>",
            "data": "<string>"
          }
        ],
        "tool_calls": [
          {
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            },
            "index": 123,
            "type": "<string>",
            "id": "<string>"
          }
        ]
      }
    }
  ],
  "created": 123,
  "model": "<string>",
  "object": "<string>",
  "service_tier": "<string>",
  "system_fingerprint": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "prompt_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "image_tokens": 123,
      "cached_read_tokens": 123,
      "cached_write_tokens": 123
    },
    "completion_tokens": 123,
    "completion_tokens_details": {
      "text_tokens": 123,
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "citation_tokens": 123,
      "num_search_queries": 123,
      "reasoning_tokens": 123,
      "image_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "total_tokens": 123,
    "cost": {
      "input_tokens_cost": 123,
      "output_tokens_cost": 123,
      "reasoning_tokens_cost": 123,
      "citation_tokens_cost": 123,
      "search_queries_cost": 123,
      "request_cost": 123,
      "total_cost": 123
    }
  },
  "extra_fields": {
    "request_type": "<string>",
    "provider": "openai",
    "model_requested": "<string>",
    "model_deployment": "<string>",
    "latency": 123,
    "chunk_index": 123,
    "raw_request": {},
    "raw_response": {},
    "cache_debug": {
      "cache_hit": true,
      "cache_id": "<string>",
      "hit_type": "<string>",
      "requested_provider": "<string>",
      "requested_model": "<string>",
      "provider_used": "<string>",
      "model_used": "<string>",
      "input_tokens": 123,
      "threshold": 123,
      "similarity": 123
    }
  },
  "search_results": [
    {
      "title": "<string>",
      "url": "<string>",
      "date": "<string>",
      "last_updated": "<string>",
      "snippet": "<string>",
      "source": "<string>"
    }
  ],
  "videos": [
    {
      "url": "<string>",
      "thumbnail_url": "<string>",
      "thumbnail_width": 123,
      "thumbnail_height": 123,
      "duration": 123
    }
  ],
  "citations": [
    "<string>"
  ]
}

Body

application/json

model · string · required

Model in provider/model format (e.g., openai/gpt-4)

Example:

"openai/gpt-4"

messages · object[] · required

List of messages in the conversation

Show child attributes

fallbacks · string[]

Fallback models in provider/model format

stream · boolean

Whether to stream the response

frequency_penalty · number

Required range: -2 <= x <= 2

logit_bias · object

Show child attributes

logprobs · boolean

max_completion_tokens · integer

metadata · object

modalities · string[]

parallel_tool_calls · boolean

presence_penalty · number

Required range: -2 <= x <= 2

prompt_cache_key · string

reasoning · object

Show child attributes

response_format · object

Format for the response

safety_identifier · string

service_tier · string

stream_options · object

Show child attributes

store · boolean

temperature · number

Required range: 0 <= x <= 2

tool_choice · enum<string> object

Available options: none, auto, required

tools · object[]

Show child attributes

seed · integer

Deterministic sampling seed

top_p · number

Nucleus sampling parameter

Required range: 0 <= x <= 1

top_logprobs · integer

Number of most likely tokens to return at each position

Required range: 0 <= x <= 20

stop · string string[]

Up to 4 sequences where the API will stop generating tokens

prediction · object

Predicted output content for the model to reference (OpenAI only). Can reduce latency.

Show child attributes

prompt_cache_retention · enum<string>

Prompt cache retention policy

Available options: in-memory, 24h

web_search_options · object

Web search options for chat completions (OpenAI only)

Show child attributes

truncation · string

user · string

verbosity · enum<string>

Available options: low, medium, high

Response

200

application/json

Successful response

id · string

choices · object[]

Show child attributes

created · integer

model · string

object · string

service_tier · string

system_fingerprint · string

usage · object

Token usage information

Show child attributes

extra_fields · object

Additional fields included in responses

Show child attributes

search_results · object[]

Show child attributes

videos · object[]

Show child attributes

citations · string[]