Responses

Asynchronous task result query interface, used to query results of asynchronous inference tasks, also supports direct synchronous call for content generation.

Endpoint

POST https://ai-tokenhub.com/api/v1/responses

Authorizations

BearerAuth

Name	Type	Required	Description
Authorization	string	Yes	Bearer token authentication. Use your API key or platform authentication token, virtual keys (prefixed with sk-bf-) can also be passed here. Format: Bearer YOUR_API_KEY
Content-Type	string	Yes	application/json

Request Body

application/json

Parameter	Type	Required	Default	Description
model	string	Yes	-	Model identifier, format: provider/model (e.g.: doubao-seed-2-0-pro) Example: "doubao-seed-2-0-pro"
input	string/object[]	Yes	-	Input content, can be text string or message array
stream	boolean	No	false	Whether to enable streaming response
temperature	number	No	0.7	Generation temperature, value range: -2 <= x <= 2
frequency_penalty	number	No	0	Frequency penalty, value range: -2 <= x <= 2
presence_penalty	number	No	0	Presence penalty, value range: -2 <= x <= 2
max_tokens	integer	No	-	Maximum number of generated tokens
metadata	object	No	-	User-defined metadata
parallel_tool_calls	boolean	No	true	Whether to enable parallel tool calls
tool_choice	string/object	No	"auto"	Tool call selection strategy
tools	object[]	No	-	List of available tools
top_p	number	No	0.9	Nucleus sampling parameter
user	string	No	-	User identifier

Request Examples

curl https://ai-tokenhub.com/api/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "doubao-seed-2-0-pro",
    "input": "Tell me a joke about computers",
    "temperature": 0.7
  }'

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://ai-tokenhub.com/api/v1"
)
response = client.responses.create(
    model="doubao-seed-2-0-pro",
    input="Tell me a joke about computers",
    temperature=0.7
)
print(response.output[0].content[0].text)

import OpenAI from 'openai';
const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://ai-tokenhub.com/api/v1'
});
const response = await client.responses.create({
  model: 'doubao-seed-2-0-pro',
  input: 'Tell me a joke about computers',
  temperature: 0.7
});
console.log(response.output[0].content[0].text);

import okhttp3.*;
import java.io.IOException;
public class Main {
    public static void main(String[] args) throws IOException {
        OkHttpClient client = new OkHttpClient();
        String json = "{\"model\":\"doubao-seed-2-0-pro\"," +
                      "\"input\":\"Tell me a joke about computers\"," +
                      "\"temperature\":0.7}";
        MediaType mediaType = MediaType.parse("application/json");
        RequestBody body = RequestBody.create(json, mediaType);
        Request request = new Request.Builder()
            .url("https://ai-tokenhub.com/api/v1/responses")
            .post(body)
            .addHeader("Content-Type", "application/json")
            .addHeader("Authorization", "Bearer YOUR_API_KEY")
            .build();
        try (Response response = client.newCall(request).execute()) {
            System.out.println(response.body().string());
        }
    }
}

Response Example

{
  "completed_at": 1700000300,
  "created_at": 1700000000,
  "error": null,
  "frequency_penalty": 0.5,
  "id": "resp_abc123",
  "incomplete_details": null,
  "instructions": [
    {
      "content": "Tell me a joke about computers",
      "role": "user"
    }
  ],
  "metadata": {},
  "model": "doubao-seed-2-0-pro",
  "object": "response",
  "parallel_tool_calls": true,
  "presence_penalty": 0.3,
  "status": "completed",
  "temperature": 0.7,
  "tool_choice": "auto",
  "tools": [],
  "top_p": 0.9,
  "output": [
    {
      "type": "message",
      "content": [
        {
          "text": "Why do programmers prefer dark mode? Because light attracts bugs!",
          "type": "output_text"
        }
      ],
      "id": "msg-xyz789",
      "role": "assistant"
    }
  ],
  "usage": {
    "input_tokens": 15,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 20,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 35
  }
}