ResponsesFormat

OpenAI Responses interface supports multiple rounds of context, built-in tools and inference models. Compatible with /v1/responses.

Compatible with OpenAI Responses API. It can be called using the platform token as api_key and base_url as https://api.covanexus.com/v1.

POST /v1/responses https://api.covanexus.com

Authorization

Body

Authorization

Authorization BearerAuth

Authorization Bearer <token>

Use Bearer Token authentication. Format: Authorization: Bearer $COVA_NEXUS_API_KEY

in: header

Request Body

application/json

model* string

Model ID

input? string | array[object]

Enter content. Can be a plain text string, or an array of message objects (including role and content)

instructions? string

System-level directive (equivalent to system prompt)

max_output_tokens? integer

Maximum number of output tokens

temperature? number

Sampling temperature

top_p? number

Kernel sampling parameters

stream? boolean

Whether to stream output (SSE event streaming)

Default false

tools? array[object]

List of available tools (Function Calling / built-in tools)

tool_choice? string | object

Tool selection strategy

reasoning? object

Inference configuration (for inference models, such as {"effort":"medium"})

previous_response_id? string

ID of the last response, used for multiple rounds of context concatenation

truncation? string

Context truncation strategy

Value in "auto" | "disabled"

Response Body

status code	Type
200	application/json
400	application/json
429	application/json

curl -X POST "https://api.covanexus.com/v1/responses" \
  -H "Authorization: Bearer $COVA_NEXUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-4o",
  "input": "用一句话介绍你自己"
}'

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "$COVA_NEXUS_API_KEY",
  baseURL: "https://api.covanexus.com/v1"
});

const response = await client.responses.create({
  model: "gpt-4o",
  input: "用一句话介绍你自己"
});
console.log(response.output_text);

from openai import OpenAI

client = OpenAI(
    api_key="$COVA_NEXUS_API_KEY",
    base_url="https://api.covanexus.com/v1"
)
response = client.responses.create(
    model="gpt-4o",
    input="用一句话介绍你自己"
)
print(response.output_text)

200

400

429

{
  "id": "resp_xxx",
  "object": "response",
  "created_at": 0,
  "model": "gpt-4o",
  "status": "completed",
  "output": [
    {
      "id": "msg_xxx",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "string"
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

BearerAuth