Use the Responses API to generate text responses from AI models. The input array contains message objects with a role (user or assistant) and content field. The model processes the input and returns a response with the generated text.
The Responses API is best supported on the Enterprise plan. Use https://enterprise.blackbox.ai as the base URL for full model availability and production reliability. The API is also available on standard plans at https://api.blackbox.ai, where it is currently experimental.
Basic Request
const response = await fetch('https://enterprise.blackbox.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${process.env.BLACKBOX_API_KEY}`,
},
body: JSON.stringify({
model: 'openai/gpt-5.3-codex',
input: [
{
type: 'message',
role: 'user',
content: 'Why do developers prefer dark mode?',
},
],
}),
});
const result = await response.json();
console.log(result);
output array, along with token usage information.
{
"id": "resp_abc123",
"object": "response",
"model": "openai/gpt-5.3-codex",
"output": [
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Habit and aesthetics reinforce the preference, but ergonomics and contrast are the primary drivers."
}
]
}
],
"usage": {
"input_tokens": 14,
"output_tokens": 18
}
}
Multi-turn Conversations
For conversations with multiple messages, include both user and assistant messages in the input array:
const response = await fetch('https://enterprise.blackbox.ai/v1/responses', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${process.env.BLACKBOX_API_KEY}`,
},
body: JSON.stringify({
model: 'openai/gpt-5.3-codex',
input: [
{
type: 'message',
role: 'user',
content: 'What is React?',
},
{
type: 'message',
role: 'assistant',
content: 'React is a JavaScript library for building user interfaces.',
},
{
type: 'message',
role: 'user',
content: 'What are the main benefits?',
},
],
}),
});
const result = await response.json();
Request Parameters
The model identifier to use for generation. Example: openai/gpt-5.3-codexSee the full list of available models in the Models section. Array of input messages. Each message object must contain:
type: Always "message"role: Either "user", "assistant", or "system"content: The message text content
Maximum number of tokens to generate. Controls the length of the output.
Controls randomness in generation. Range: 0.0 to 2.0. Lower values produce more focused output; higher values produce more varied output. Default: 1.0
Controls diversity via nucleus sampling. Range: 0.0 to 1.0. Not recommended to use alongside temperature. Default: 1.0
Response Fields
Unique identifier for this response.
Always "response" for this endpoint.
The model used to generate the response.
Array containing the generated response. Each item has:
type: "message"role: "assistant"content: Array with type: "output_text" and text fields
Token usage statistics with input_tokens and output_tokens.
Next Steps
