OpenAI format - HaiToken Doc

POST

chat

completions

Create chat completion

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "tool_calls": [
        {
          "id": "<string>",
          "index": 123,
          "type": "<string>",
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          }
        }
      ],
      "tool_call_id": "<string>",
      "reasoning_content": "<string>",
      "content": {},
      "name": "<string>",
      "refusal": "<string>",
      "annotations": [
        {}
      ]
    }
  ],
  "stream_options": {
    "include_usage": true
  },
  "top_p": 123,
  "max_tokens": 123,
  "max_completion_tokens": 123,
  "frequency_penalty": 123,
  "presence_penalty": 123,
  "logit_bias": {
    "key": 123
  },
  "top_logprobs": 123,
  "response_format": {
    "json_schema": {
      "name": "<string>",
      "description": "<string>",
      "schema": {},
      "strict": true
    },
    "type": "<string>"
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_retention": "<string>",
  "safety_identifier": "<string>",
  "tool_choice": {},
  "parallel_tool_calls": true,
  "service_tier": "<string>",
  "reasoning_effort": "<string>",
  "web_search_options": {},
  "function_call": {},
  "stream": true,
  "temperature": 123,
  "stop": {},
  "n": 123,
  "logprobs": true,
  "seed": 123,
  "user": "<string>",
  "tools": [
    {
      "type": "<string>",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": true
      }
    }
  ],
  "modalities": [
    "<string>"
  ],
  "audio": {},
  "metadata": {
    "key": "<string>"
  },
  "prediction": {},
  "verbosity": "<string>",
  "functions": [
    {}
  ]
}
'

{
  "system_fingerprint": "<string>",
  "service_tier": "<string>",
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "finish_reason": "<string>",
      "index": 123,
      "message": {
        "tool_calls": [
          {
            "id": "<string>",
            "index": 123,
            "type": "<string>",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ],
        "tool_call_id": "<string>",
        "reasoning_content": "<string>",
        "content": {},
        "name": "<string>",
        "refusal": "<string>",
        "annotations": [
          {}
        ]
      },
      "logprobs": {
        "content": [
          {
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ]
          }
        ],
        "refusal": [
          {
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ]
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "audio_tokens": 123
    },
    "completion_tokens_details": {
      "reasoning_tokens": 123,
      "audio_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "ephemeral_5m_input_tokens": 123,
    "ephemeral_1h_input_tokens": 123,
    "web_search_requests": 123
  }
}

This endpoint is compatible with the OpenAI Chat Completions protocol for creating chat completion requests.

Features

Supports both streaming (SSE) and non-streaming response modes
Supports multimodal input (text, images, etc.)
Supports function calling and tool calling
Supports structured output (JSON Schema)
Supports reasoning effort configuration
Supports web search options

Use cases

Suitable for scenarios requiring interaction with OpenAI-compatible models, including:

Single-turn or multi-turn conversations
Function calling and tool orchestration
Structured JSON output
Real-time streaming responses

Authentication

Include the Authorization header in the format Bearer YOUR_API_KEY.

Never expose API keys in client-side code. Use a server-side proxy to forward requests.

Quick example

import requests

url = "https://api.haitoken.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "gpt-4o",
    "messages": [
        {"role": "user", "content": "Hello, please introduce yourself"}
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

Headers

Authorization

string

required

Example:

"Bearer YOUR_API_KEY"

Content-Type

string

Example:

"application/json"

Body

application/json

model

string

required

Model ID, e.g. gpt-4o, deepseek-chat, etc.

messages

object[]

required

List of messages

Show child attributes

stream_options

object

Streaming response options (only used when stream=true)

Show child attributes

top_p

number

Nucleus sampling, between 0 and 1

max_tokens

integer

Maximum number of tokens to generate (deprecated, use max_completion_tokens instead)

max_completion_tokens

integer

Maximum number of tokens to generate (including visible output tokens and reasoning tokens)

frequency_penalty

number

Frequency penalty, -2.0 to 2.0

presence_penalty

number

Presence penalty, -2.0 to 2.0

logit_bias

object

Map to modify the likelihood of specified tokens appearing

Show child attributes

top_logprobs

integer

Maximum number of most likely tokens to return at each token position (0-20)

response_format

object

Response format, supports "text", "json_object", "json_schema"

Show child attributes

prompt_cache_key

string

Stable identifier for cache optimization

prompt_cache_retention

string

Cache retention policy: "in_memory" or "24h"

safety_identifier

string

Safety identifier for detecting violating users

tool_choice

object

Controls which tool the model calls, can be a string ("none"/"auto"/"required") or an object

parallel_tool_calls

boolean

Whether to enable parallel tool calls

service_tier

string

Service tier: "auto", "default", "flex", "scale", "priority"

reasoning_effort

string

Reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh"

web_search_options

object

Web search options

function_call

object

Deprecated: function call control

stream

boolean

Whether to enable streaming output

temperature

number

Sampling temperature, between 0 and 2, higher values produce more random output

stop

object

Stop sequences

integer

Number of chat completion choices to generate for each input message

logprobs

boolean

Whether to return log probabilities of output tokens

seed

integer<int64>

Seed value for deterministic sampling

user

string

User identifier (deprecated, use prompt_cache_key instead)

tools

object[]

List of tools the model can call

Show child attributes

modalities

string[]

Output type list: ["text"] or ["text", "audio"]

audio

object

Audio output parameters

metadata

object

Metadata, up to 16 key-value pairs

Show child attributes

prediction

object

Predicted output content

verbosity

string

Response verbosity: "low", "medium", "high"

functions

object[]

Deprecated: list of function definitions

Response

200 - application/json

OpenAI Chat Completions API response object

system_fingerprint

string

System fingerprint, representing backend configuration

service_tier

string

Actual service tier used

string

Unique identifier for the chat completion

object

string

Object type, always "chat.completion"

created

integer<int64>

Creation time (Unix timestamp)

model

string

Model ID used

choices

object[]

List of chat completion choices

Show child attributes

usage

object

Usage statistics

Show child attributes

Claude formatCreate Claude messages compatible with the Anthropic Messages protocol, supporting streaming and non-streaming responses

Create chat completion

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "tool_calls": [
        {
          "id": "<string>",
          "index": 123,
          "type": "<string>",
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          }
        }
      ],
      "tool_call_id": "<string>",
      "reasoning_content": "<string>",
      "content": {},
      "name": "<string>",
      "refusal": "<string>",
      "annotations": [
        {}
      ]
    }
  ],
  "stream_options": {
    "include_usage": true
  },
  "top_p": 123,
  "max_tokens": 123,
  "max_completion_tokens": 123,
  "frequency_penalty": 123,
  "presence_penalty": 123,
  "logit_bias": {
    "key": 123
  },
  "top_logprobs": 123,
  "response_format": {
    "json_schema": {
      "name": "<string>",
      "description": "<string>",
      "schema": {},
      "strict": true
    },
    "type": "<string>"
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_retention": "<string>",
  "safety_identifier": "<string>",
  "tool_choice": {},
  "parallel_tool_calls": true,
  "service_tier": "<string>",
  "reasoning_effort": "<string>",
  "web_search_options": {},
  "function_call": {},
  "stream": true,
  "temperature": 123,
  "stop": {},
  "n": 123,
  "logprobs": true,
  "seed": 123,
  "user": "<string>",
  "tools": [
    {
      "type": "<string>",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": true
      }
    }
  ],
  "modalities": [
    "<string>"
  ],
  "audio": {},
  "metadata": {
    "key": "<string>"
  },
  "prediction": {},
  "verbosity": "<string>",
  "functions": [
    {}
  ]
}
'

{
  "system_fingerprint": "<string>",
  "service_tier": "<string>",
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "finish_reason": "<string>",
      "index": 123,
      "message": {
        "tool_calls": [
          {
            "id": "<string>",
            "index": 123,
            "type": "<string>",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ],
        "tool_call_id": "<string>",
        "reasoning_content": "<string>",
        "content": {},
        "name": "<string>",
        "refusal": "<string>",
        "annotations": [
          {}
        ]
      },
      "logprobs": {
        "content": [
          {
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ]
          }
        ],
        "refusal": [
          {
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ]
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "audio_tokens": 123
    },
    "completion_tokens_details": {
      "reasoning_tokens": 123,
      "audio_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "ephemeral_5m_input_tokens": 123,
    "ephemeral_1h_input_tokens": 123,
    "web_search_requests": 123
  }
}

​Features

​Use cases

​Authentication

​Quick example

Headers

Body

Response

Features

Use cases

Authentication

Quick example