OpenAI - chat completion

POST

/v1/chat/completions

curl --request POST \
  --url https://coder.api.visioncoder.cn/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "model": "gpt-5.4", "messages": [ { "role": "system", "content": "Hello", "name": "example", "tool_call_id": "example" } ], "temperature": 1, "top_p": 1, "n": 1, "max_tokens": 4096, "max_completion_tokens": 1, "stream": false, "stop": "example", "presence_penalty": 1, "frequency_penalty": 1, "seed": 1, "response_format": { "type": "text" }, "tools": [ {} ], "tool_choice": "example", "user": "example" }'

• Production

Authorizations

• BearerAuth

Request Body^required

Media typeapplication/json

OpenAIChatCompletionReq

OpenAI Chat Completions request body. The platform forwards it upstream as-is; fields follow the official OpenAI protocol.

object

model

required

Model ID. Accepts any chat-capable model returned by GET /v1/models — e.g. OpenAI gpt-5.4 / gpt-5.5, Anthropic claude-sonnet-5 / claude-opus-5, or open-source deepseek-v4-pro / qwen3.6-35b-a3b / kimi-k2.6 / glm-5.1 / glm-5.2 / minimax-m2.7.

string

Example

gpt-5.4

messages

required

Conversation message list

Array<object>

object

role

required

string

Allowed values: system user assistant tool

Example

user

content

required

string

Example

Hello

name

string

tool_call_id

string

temperature

number format: float

default: 1 <= 2

Example

0.7

top_p

number format: float

default: 1 <= 1

n

Number of candidate completions to generate

integer

default: 1

max_tokens

Maximum output tokens

integer

Example

4096

max_completion_tokens

Newer field, equivalent to max_tokens

integer

stream

Whether to stream the response via SSE

boolean

stop

Stop sequence(s); string or array of strings

presence_penalty

number format: float

>= -2 <= 2

frequency_penalty

number format: float

>= -2 <= 2

seed

integer

response_format

object

type

string

Allowed values: text json_object json_schema

tools

Function-calling tool definitions

Array<object>

object

tool_choice

Tool choice strategy; string or object

user

End-user identifier

string

Responses

200

A successful response.

Media typeapplication/json

OpenAIChatCompletionResp

OpenAI Chat Completions response body. Fields follow the official OpenAI protocol.

object

id

string

object

string

created

integer

model

string

system_fingerprint

string

choices

Array<object>

object

index

integer

message

object

role

string

content

string

tool_calls

Array<object>

object

logprobs

object

finish_reason

string

Allowed values: stop length tool_calls content_filter

usage

object

prompt_tokens

integer

completion_tokens

integer

total_tokens

integer

Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1730000000,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 28,
    "total_tokens": 40
  }
}