Create a chat completion

curl --request POST \
  --url http://localhost:8080/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-5-nano",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "openai/gpt-5-nano",
  "choices": [
    {
      "index": 123,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "<string>",
        "refusal": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            },
            "custom": {
              "name": "<string>",
              "input": "<string>"
            }
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "cache_write_tokens": 123,
      "audio_tokens": 123
    },
    "completion_tokens_details": {
      "reasoning_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123,
      "audio_tokens": 123
    }
  },
  "system_fingerprint": "<string>",
  "service_tier": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

POST

chat

completions

curl --request POST \
  --url http://localhost:8080/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-5-nano",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "openai/gpt-5-nano",
  "choices": [
    {
      "index": 123,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "<string>",
        "refusal": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            },
            "custom": {
              "name": "<string>",
              "input": "<string>"
            }
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "cache_write_tokens": 123,
      "audio_tokens": 123
    },
    "completion_tokens_details": {
      "reasoning_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123,
      "audio_tokens": 123
    }
  },
  "system_fingerprint": "<string>",
  "service_tier": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "insufficient_quota",
    "param": "<string>",
    "origin": "gateway",
    "warpllm_code": "quota_exceeded",
    "provider": "deepseek",
    "provider_status": 402,
    "provider_code": "<string>"
  }
}

Body

application/json

Fields not listed here are forwarded to the provider untouched.

model

string

required

A provider/model routing string. The prefix is required; an unlisted name is an error, never a guess.

Examples:

"openai/gpt-5-nano"

"deepseek/deepseek-v4-flash"

"openrouter/anthropic/claude-sonnet-4"

messages

object[]

required

Show child attributes

temperature

number | null

max_tokens

integer | null

top_p

number | null

stop

stream

boolean | null

true returns server-sent events instead of one JSON body.

stream_options

object | null

Show child attributes

tools

object[] | null

Show child attributes

tool_choice

"auto", "none", "required", or a named function.

response_format

object

Option 1
Option 2

Show child attributes

reasoning_effort

string | null

Reasoning budget hint for models that accept one.

Response

The completion, whole or streamed.

string

required

object

string

required

Example:

"chat.completion"

created

integer

required

model

string

required

Your provider/model routing string, not the upstream name.

Example:

"openai/gpt-5-nano"

choices

object[]

required

Show child attributes

usage

object

Show child attributes

system_fingerprint

string

service_tier

string | null

Self-hosted gateway

HTTP API

Create a chat completion

Body

Response