curl --request POST \
  --url https://api.omniall.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}
'

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 4,
    "total_tokens": 14
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "无效的令牌 (request id: ...)",
    "type": "new_api_error",
    "code": ""
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

ChatGPT

Chat Completions

OpenAI Chat Completions API relayed by Omniall AI.

Base path: POST https://api.omniall.ai/v1/chat/completions

Compatible with the official OpenAI Chat Completions schema. Use model IDs from the Model Square.

Common scenarios

Vision: multimodal messages[].content with image_url
File analysis: type: file content parts (when the upstream model supports it)
Web search: web_search_options / provider search fields when the model supports search
Agent: tools + tool_choice function calling loop
Streaming: stream: true (SSE)

Official reference: https://platform.openai.com/docs/api-reference/chat

POST

chat

completions

curl --request POST \
  --url https://api.omniall.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}
'

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 4,
    "total_tokens": 14
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "无效的令牌 (request id: ...)",
    "type": "new_api_error",
    "code": ""
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "new_api_error",
    "code": "<string>"
  }
}

Authorizations

Authorization

string

header

required

Use Authorization: Bearer sk-... from https://omniall.ai/dashboard

Body

application/json

OpenAI Chat Completions request (POST /v1/chat/completions). Maps to Omniall gateway GeneralOpenAIRequest.

model

string

required

Model id from Model Square / GET /v1/models. Must be a model your key can access.

Example:

"gpt-4o"

messages

object[]

required

Full conversation so far, oldest first. Include system/user/assistant/tool turns as needed.

Show child attributes

stream

boolean

default:false

If true, return Server-Sent Events (chat.completion.chunk) instead of a single JSON object.

stream_options

object

Streaming extras.

Show child attributes

temperature

number

Sampling temperature (about 0–2). Higher = more random; 0 = more deterministic.

Required range: 0 <= x <= 2

top_p

number

Nucleus sampling probability mass (0–1). Prefer tuning either temperature or top_p, not both aggressively.

Required range: 0 <= x <= 1

top_k

integer

Top-K sampling when the upstream model supports it (ignored by some OpenAI models).

integer

How many completions to generate for this prompt (cost scales with n).

Required range: x >= 1

max_tokens

integer

Legacy max tokens for the completion. Prefer max_completion_tokens on newer OpenAI models.

max_completion_tokens

integer

Maximum tokens the model may generate (preferred for newer OpenAI chat models).

stop

Stop sequence(s). Generation ends when any sequence is produced.

presence_penalty

number

Penalize new tokens based on whether they appear in the text so far (−2 to 2). Positive values encourage new topics.

Required range: -2 <= x <= 2

frequency_penalty

number

Penalize tokens by frequency (−2 to 2). Positive values reduce repetition.

Required range: -2 <= x <= 2

seed

number

Best-effort deterministic seed when the provider supports it.

user

string

Stable end-user id for abuse monitoring (opaque string). Do not put secrets here.

logit_bias

object

Map of token-id → bias to ban/boost specific tokens (provider-specific).

Show child attributes

logprobs

boolean

Whether to return log probabilities for output tokens.

top_logprobs

integer

Number of most likely tokens to return at each position when logprobs is enabled.

response_format

object

Force output shape. json_object asks for valid JSON; json_schema asks for JSON matching your schema (when supported).

Show child attributes

tools

object[]

Function tools available to the model for agent workflows.

Show child attributes

tool_choice

Controls tool use: none / auto / required, or force a specific function.

Available options:

none,

auto,

required

parallel_tool_calls

boolean

Whether the model may call multiple tools in one turn.

reasoning_effort

enum<string>

Reasoning intensity for o-series / compatible models (low / medium / high).

Available options:

low,

medium,

high

modalities

enum<string>[]

Requested output modalities, e.g. text, audio.

Available options:

text,

audio

audio

object

Audio output settings when using audio modalities.

web_search_options

object

OpenAI-style web search options when the model supports search.

Show child attributes

enable_search

Qwen-style web search toggle (channel/model dependent).

web_search

object

Provider-specific web search object (e.g. Baidu).

search_parameters

object

xAI search parameters object.

thinking

object

Doubao / Zhipu thinking controls.

enable_thinking

Qwen thinking toggle.

extra_body

object

Extra provider fields (sometimes used for Gemini-related options on the OpenAI-compatible path).

metadata

object

Arbitrary metadata passthrough when supported.

prediction

object

Predicted-output hint to reduce latency when you can anticipate part of the answer.

Response

Chat completion JSON, or SSE stream when stream=true.

Non-streaming Chat Completions response.

string

Unique completion id.

object

string

Always chat.completion for non-streaming.

Example:

"chat.completion"

created

integer

Unix timestamp (seconds) when the completion was created.

model

string

Model that produced the answer (may reflect routing).

choices

object[]

Generated choices (usually one).

Show child attributes

usage

object

Token usage when provided by upstream.

Show child attributes

system_fingerprint

string

Upstream system fingerprint when available (reproducibility signal).

Overview

Models

Chat

Images

Video

Audio

Platform

Rerank

Chat Completions

Common scenarios

Authorizations

Body

Response