OpenAI

OpenAI-series models use the OpenAI-compatible Chat Completions endpoint. This page describes common parameters and model differences for GPT, Codex, and o reasoning models.

Endpoint Paths

Method	Path	Purpose
POST	`/v1/chat/completions`	Create a chat completion, reasoning, or code-generation request
GET	`/v1/models`	List models available to the current token
GET	`/v1/models/{model}`	Retrieve one model's details

Request Structure

{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "Introduce Routescope API in one sentence."
    }
  ],
  "temperature": 0.7
}

curl -X POST "https://api.routescope.ai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Hello, please introduce yourself in one sentence."
      }
    ]
  }'

curl -X POST "https://api.routescope.ai/v1/chat/completions" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4o-mini",    "messages": [      {        "role": "user",        "content": "Hello, please introduce yourself in one sentence."      }    ]  }'

{
  "id": "task_01JZ8M9Q4R7V2K8N9P0Q",
  "object": "string",
  "created": 1,
  "model": "gpt-4o-mini",
  "choices": [],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1,
    "input_tokens": 1,
    "output_tokens": 1
  }
}

{
  "error": null,
  "message": "success"
}

Authorization

BearerAuth

AuthorizationBearer <token>

Model relay interface recognition. Request heading: Autoration: Bearer .

In: header

Request Body

application/json

model*string

The model name to call.

messages*

Can not open message Can not open message Scope: At least 1 message.

temperature?number

Sampling temperatures spread more and more. Sample temperature. Range: 0 to 2; the larger the value, the more random.

Range0 <= value <= 2

top_p?number

Nuclear sampling parameters. Nuclear sampling parameters. Range: 0 to 1; usually no large adjustments with temperature.

Range0 <= value <= 1

max_tokens?integer

Maximum output number of Tokens. Maximum output number of Tokens. Scope: 1 to the maximum of the context of the model.

Range1 <= value

stream?boolean

Whether to enable SSE flow output. Whether or not to enable flow output. Scope: True or false.

stream_options?

Stream extension options. Upstream support varied.

enable_thinking?boolean

Whether or not to start deep thinking mode. Qwen/Ariyuncrery OpenAI compatible extension parameters: _FD_PROTECT_0 _ Start thinking, _FD_PROTECT_1 _ Close thinking; part of the thinking model is always open and does not support closure. Python OpenAI SDK can be imported through FD_PROTECT_2.

tools?

Tool definitions for which models can be called. . Scope: The length of arrays and the complexity of schema are based on upstream limits.

tool_choice?string|

Tools call policies, such as _FD_PROTEC_0, FD_PROTEC_1 or visible specifying functions. Tool call policy. Scope: auto, none, required or visible tool objects.

response_format?object

Structured output constraints, such as JSON Schema.

user?string

End-user identification for audit and control.

Response Body

application/json

Model Selection

Model ID	Capability	Typical Use
`gpt-5`, `gpt-5-2025-08-07`	Chat completions	General text generation and multi-turn conversation
`gpt-5.1`, `gpt-5.1-2025-11-13`, `gpt-5.1-chat-latest`	Chat completions	General conversation, pinned versions, or latest entry
`gpt-5.2-2025-12-11`, `gpt-5.2-chat-latest`	Chat completions	General conversation, pinned versions, or latest entry
`gpt-5.3-chat-latest`	Chat completions	Latest entry
`gpt-5.4`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano`, `gpt-5.4-pro`, `gpt-5.4-pro-2026-03-05`	Chat completions	General, mini, nano, and pro tiers
`gpt-5-pro`, `gpt-5-pro-2025-10-06`	Chat completions	Advanced text tasks
`gpt-5.1-codex-mini`, `gpt-5.1-codex`, `gpt-5.1-codex-max`, `gpt-5.2-codex`, `gpt-5.3-codex`	Code generation	Codex and code-focused tasks
`o3`, `o3-2025-04-16`	Reasoning	Reasoning-heavy tasks

Common Parameters

Field	Type	Required	Description
`model`	string	Yes	Model ID to call.
`messages`	array	Yes	Conversation messages. Roles include `system`, `user`, `assistant`, and `tool`.
`temperature`	number	No	Sampling temperature. OpenAPI schema marks the range as `0` to `2`.
`top_p`	number	No	Nucleus sampling parameter. OpenAPI schema marks the range as `0` to `1`.
`max_tokens`	integer	No	Maximum output tokens, limited by the selected model context.
`stream`	boolean	No	Whether to use SSE streaming.
`tools`	array	No	Tool definitions.
`tool_choice`	string/object	No	Tool-calling strategy.
`response_format`	object	No	Structured output constraint, such as JSON Schema.
`user`	string	No	End-user identifier for auditing and risk control.

Model-Specific Notes

Field	Applicable Models	Description
`model`	`All`	Copy a model ID available to the current token from the model selection table or /v1/models.
`stream_options`	`OpenAI-compatible models that support streaming`	Marked in the OpenAPI schema as streaming extensions. Upstream support may vary.
`enable_thinking`	`Qwen / Alibaba Cloud OpenAI-compatible extension`	This field exists in the OpenAPI schema but is not a generic OpenAI GPT-series field, so it is not included in GPT examples.
`Reasoning / code model capability`	`o3 and Codex series`	There is no unified extra field listed here. Follow API responses or the actual console display.

Response Structure

OpenAI-style responses include id, object, created, model, choices, and usage. When stream=true, the response is pushed as SSE chunks.

Endpoint Paths

Request Structure

Authorization

Request Body

Response Body

200application/json

400application/json

Model Selection

Common Parameters

Model-Specific Notes

Response Structure

application/json

application/json