Responses API

Get Your API Key

Go to the API Keys page to create your API key.

API Base URL

https://tokenoff.com/api

OpenAI models support the /v1/responses endpoint, fully compatible with the OpenAI Responses API.

curl

Blocking Call

curl https://tokenoff.com/api/v1/responses \
-H "Authorization: Bearer your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
  	"model": "gpt-5.4",
  	"input": [
    		{
      		"type": "message",
      		"role": "user",
      		"content": [
        			{"type": "input_text", "text": "Hello"}
      		]
    		}
  	]
}'

Output:

{
  "id": "resp_0ede5d514f3134ce0069e0c56cd4908197b2609163d3b20dcd",
  "object": "response",
  "created_at": 1776338284,
  "status": "completed",
  "background": false,
  "completed_at": 1776338285,
  "content_filters": null,
  "error": null,
  "frequency_penalty": 0.0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "model": "gpt-5.4",
  "output": [
    {
      "id": "msg_0ede5d514f3134ce0069e0c56d61e08197b8c88db05e2b03af",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "Hello! How can I help?"
        }
      ],
      "phase": "final_answer",
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0.0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": "none",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 7,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 11,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 18
  },
  "user": null,
  "metadata": {}
}

Streaming Response

curl https://tokenoff.com/api/v1/responses \
-H "Authorization: Bearer your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
  	"model": "gpt-5.4",
  	"input": [
    		{
      		"type": "message",
      		"role": "user",
      		"content": [
        			{"type": "input_text", "text": "Hello"}
      		]
    		}
  	],
      "stream": true
}'

Output:

event: response.created
data: {"type":"response.created","response":{"id":"resp_0ebb288bdd28cf950069e0c5b6c7088194a3390bd883d78953","object":"response","created_at":1776338358,"status":"in_progress","background":false,"completed_at":null,"content_filters":null,"error":null,"frequency_penalty":0.0,"incomplete_details":null,"instructions":null,"max_output_tokens":null,"max_tool_calls":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"presence_penalty":0.0,"previous_response_id":null,"prompt_cache_key":null,"prompt_cache_retention":null,"reasoning":{"effort":"none","summary":null},"safety_identifier":null,"service_tier":"auto","store":true,"temperature":1.0,"text":{"format":{"type":"text"},"verbosity":"medium"},"tool_choice":"auto","tools":[],"top_logprobs":0,"top_p":0.98,"truncation":"disabled","usage":null,"user":null,"metadata":{}},"sequence_number":0}

event: response.in_progress
data: {"type":"response.in_progress","response":{"id":"resp_0ebb288bdd28cf950069e0c5b6c7088194a3390bd883d78953","object":"response","created_at":1776338358,"status":"in_progress","background":false,"completed_at":null,"content_filters":null,"error":null,"frequency_penalty":0.0,"incomplete_details":null,"instructions":null,"max_output_tokens":null,"max_tool_calls":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"presence_penalty":0.0,"previous_response_id":null,"prompt_cache_key":null,"prompt_cache_retention":null,"reasoning":{"effort":"none","summary":null},"safety_identifier":null,"service_tier":"auto","store":true,"temperature":1.0,"text":{"format":{"type":"text"},"verbosity":"medium"},"tool_choice":"auto","tools":[],"top_logprobs":0,"top_p":0.98,"truncation":"disabled","usage":null,"user":null,"metadata":{}},"sequence_number":1}

event: response.output_item.added
data: {"type":"response.output_item.added","item":{"id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","type":"message","status":"in_progress","content":[],"phase":"final_answer","role":"assistant"},"output_index":0,"sequence_number":2}

event: response.content_part.added
data: {"type":"response.content_part.added","content_index":0,"item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","output_index":0,"part":{"type":"output_text","annotations":[],"logprobs":[],"text":""},"sequence_number":3}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":"Hello","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"PQG6rAgXwIS","output_index":0,"sequence_number":4}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":"!","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"05oCdMjfVQIl2nI","output_index":0,"sequence_number":5}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":" How","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"mrsMyP9aG5d6","output_index":0,"sequence_number":6}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":" can","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"vxot3eZ0O24n","output_index":0,"sequence_number":7}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":" I","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"VtWDc1nve4DmHu","output_index":0,"sequence_number":8}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":" help","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"iRjU41lFZhR","output_index":0,"sequence_number":9}

event: response.output_text.delta
data: {"type":"response.output_text.delta","content_index":0,"delta":"?","item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"obfuscation":"Gf768wfM626vI1E","output_index":0,"sequence_number":10}

event: response.output_text.done
data: {"type":"response.output_text.done","content_index":0,"item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","logprobs":[],"output_index":0,"sequence_number":11,"text":"Hello! How can I help?"}

event: response.content_part.done
data: {"type":"response.content_part.done","content_index":0,"item_id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","output_index":0,"part":{"type":"output_text","annotations":[],"logprobs":[],"text":"Hello! How can I help?"},"sequence_number":12}

event: response.output_item.done
data: {"type":"response.output_item.done","item":{"id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":"Hello! How can I help?"}],"phase":"final_answer","role":"assistant"},"output_index":0,"sequence_number":13}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_0ebb288bdd28cf950069e0c5b6c7088194a3390bd883d78953","object":"response","created_at":1776338358,"status":"completed","background":false,"completed_at":1776338359,"content_filters":null,"error":null,"frequency_penalty":0.0,"incomplete_details":null,"instructions":null,"max_output_tokens":null,"max_tool_calls":null,"model":"gpt-5.4","output":[{"id":"msg_0ebb288bdd28cf950069e0c5b72d24819499b67d5e9f42ac9d","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":"Hello! How can I help?"}],"phase":"final_answer","role":"assistant"}],"parallel_tool_calls":true,"presence_penalty":0.0,"previous_response_id":null,"prompt_cache_key":null,"prompt_cache_retention":null,"reasoning":{"effort":"none","summary":null},"safety_identifier":null,"service_tier":"default","store":true,"temperature":1.0,"text":{"format":{"type":"text"},"verbosity":"medium"},"tool_choice":"auto","tools":[],"top_logprobs":0,"top_p":0.98,"truncation":"disabled","usage":{"input_tokens":7,"input_tokens_details":{"cached_tokens":0},"output_tokens":11,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":18},"user":null,"metadata":{}},"sequence_number":14}

Python

pip install openai

Blocking Call

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.responses.create(
  model="gpt-5.4",
  input=[
      {
          "type": "message",
          "role": "user",
          "content": [
              {"type": "input_text", "text": "Hello"}
          ],
      }
  ],
)

print(response.output_text)

Output:

Hello! How can I help you today?

Streaming Response

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.responses.create(
  model="gpt-5.4",
  input=[
      {
          "type": "message",
          "role": "user",
          "content": [
              {"type": "input_text", "text": "Hello"}
          ],
      }
  ],
  stream=True,
)

for event in response:
  print(event)

Output:

ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content='', function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content='Hello', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content='!', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' How', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' can', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' I', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' help', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' you', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=' today', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content='?', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_00a6d0440377313b0069e0c71e487c819482704ea3a47b1038', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role=None, tool_calls=None), finish_reason='stop', index=0, logprobs=None)], created=1776338718, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=13, prompt_tokens=7, total_tokens=20, completion_tokens_details=None, prompt_tokens_details=None))

TypeScript

npm install openai

Blocking Call

import OpenAI from "openai";

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

const response = await client.responses.create({
model: "gpt-5.4",
input: [
	{
  		type: "message",
  		role: "user",
  		content: [
  			{ type: "input_text", text: "Hello" },
  		],
  	},
],
});

console.log(response.output_text);

Output:

Hello! How can I help?

Streaming Response

import OpenAI from "openai";

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

const response = await client.responses.create({
model: "gpt-5.4",
input: [
	{
  		type: "message",
  		role: "user",
  		content: [
  			{ type: "input_text", text: "Hello" },
  		],
  	},
],
stream: true,
});

for await (const event of response) {
console.log(event);
}

Output:

{
  type: 'response.created',
  response: {
    id: 'resp_05c96bf3f567ee650069e0c6a804fc819395b958d72ccefca8',
    object: 'response',
    created_at: 1776338600,
    status: 'in_progress',
    background: false,
    completed_at: null,
    content_filters: null,
    error: null,
    frequency_penalty: 0,
    incomplete_details: null,
    instructions: null,
    max_output_tokens: null,
    max_tool_calls: null,
    model: 'gpt-5.4',
    output: [],
    parallel_tool_calls: true,
    presence_penalty: 0,
    previous_response_id: null,
    prompt_cache_key: null,
    prompt_cache_retention: null,
    reasoning: { effort: 'none', summary: null },
    safety_identifier: null,
    service_tier: 'auto',
    store: true,
    temperature: 1,
    text: { format: [Object], verbosity: 'medium' },
    tool_choice: 'auto',
    tools: [],
    top_logprobs: 0,
    top_p: 0.98,
    truncation: 'disabled',
    usage: null,
    user: null,
    metadata: {}
  },
  sequence_number: 0
}
{
  type: 'response.in_progress',
  response: {
    id: 'resp_05c96bf3f567ee650069e0c6a804fc819395b958d72ccefca8',
    object: 'response',
    created_at: 1776338600,
    status: 'in_progress',
    background: false,
    completed_at: null,
    content_filters: null,
    error: null,
    frequency_penalty: 0,
    incomplete_details: null,
    instructions: null,
    max_output_tokens: null,
    max_tool_calls: null,
    model: 'gpt-5.4',
    output: [],
    parallel_tool_calls: true,
    presence_penalty: 0,
    previous_response_id: null,
    prompt_cache_key: null,
    prompt_cache_retention: null,
    reasoning: { effort: 'none', summary: null },
    safety_identifier: null,
    service_tier: 'auto',
    store: true,
    temperature: 1,
    text: { format: [Object], verbosity: 'medium' },
    tool_choice: 'auto',
    tools: [],
    top_logprobs: 0,
    top_p: 0.98,
    truncation: 'disabled',
    usage: null,
    user: null,
    metadata: {}
  },
  sequence_number: 1
}
{
  type: 'response.output_item.added',
  item: {
    id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
    type: 'message',
    status: 'in_progress',
    content: [],
    phase: 'final_answer',
    role: 'assistant'
  },
  output_index: 0,
  sequence_number: 2
}
{
  type: 'response.content_part.added',
  content_index: 0,
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  output_index: 0,
  part: { type: 'output_text', annotations: [], logprobs: [], text: '' },
  sequence_number: 3
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: 'Hello',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: '17zdmCnqVoo',
  output_index: 0,
  sequence_number: 4
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: '!',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: 'uxLgHYMdTFPMM1j',
  output_index: 0,
  sequence_number: 5
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: ' How',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: 'DkMSeFRAFhKk',
  output_index: 0,
  sequence_number: 6
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: ' can',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: 'A3jZg7VBtZrc',
  output_index: 0,
  sequence_number: 7
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: ' I',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: '3wk1NWsADEYKcF',
  output_index: 0,
  sequence_number: 8
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: ' help',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: 'vHVLSahOZsA',
  output_index: 0,
  sequence_number: 9
}
{
  type: 'response.output_text.delta',
  content_index: 0,
  delta: '?',
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  obfuscation: 'Hjq0GpUmeSiTAlv',
  output_index: 0,
  sequence_number: 10
}
{
  type: 'response.output_text.done',
  content_index: 0,
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  logprobs: [],
  output_index: 0,
  sequence_number: 11,
  text: 'Hello! How can I help?'
}
{
  type: 'response.content_part.done',
  content_index: 0,
  item_id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
  output_index: 0,
  part: {
    type: 'output_text',
    annotations: [],
    logprobs: [],
    text: 'Hello! How can I help?'
  },
  sequence_number: 12
}
{
  type: 'response.output_item.done',
  item: {
    id: 'msg_05c96bf3f567ee650069e0c6a88f288193b0672b72501fb6eb',
    type: 'message',
    status: 'completed',
    content: [ [Object] ],
    phase: 'final_answer',
    role: 'assistant'
  },
  output_index: 0,
  sequence_number: 13
}
{
  type: 'response.completed',
  response: {
    id: 'resp_05c96bf3f567ee650069e0c6a804fc819395b958d72ccefca8',
    object: 'response',
    created_at: 1776338600,
    status: 'completed',
    background: false,
    completed_at: 1776338600,
    content_filters: null,
    error: null,
    frequency_penalty: 0,
    incomplete_details: null,
    instructions: null,
    max_output_tokens: null,
    max_tool_calls: null,
    model: 'gpt-5.4',
    output: [ [Object] ],
    parallel_tool_calls: true,
    presence_penalty: 0,
    previous_response_id: null,
    prompt_cache_key: null,
    prompt_cache_retention: null,
    reasoning: { effort: 'none', summary: null },
    safety_identifier: null,
    service_tier: 'default',
    store: true,
    temperature: 1,
    text: { format: [Object], verbosity: 'medium' },
    tool_choice: 'auto',
    tools: [],
    top_logprobs: 0,
    top_p: 0.98,
    truncation: 'disabled',
    usage: {
      input_tokens: 7,
      input_tokens_details: [Object],
      output_tokens: 11,
      output_tokens_details: [Object],
      total_tokens: 18
    },
    user: null,
    metadata: {}
  },
  sequence_number: 14
}

Supported Models

Contact Us

If you encounter any issues while using TokenOff:

Contact us atsupport@tokenoff.comand other official channels for technical support
Submit an issue on ourGithubrepository

TokenOff

Responses API

Get Your API Key

API Base URL

curl

Blocking Call

Streaming Response

Python

Blocking Call

Streaming Response

TypeScript

Blocking Call

Streaming Response

Supported Models

gpt-5.4

gpt-5.4-mini

gpt-5.4-nano

gpt-5.2

gpt-5.1

gpt-5

gpt-5-mini

gpt-5-nano

gpt-4.1

gpt-4.1-mini

gpt-4.1-nano

gpt-4o

gpt-4o-mini

o4-mini

o3

o3-mini

o3-pro

gpt-5.3-codex

gpt-5.3-codex-spark

gpt-5.2-codex

gpt-5.1-codex-max

gpt-5.1-codex

gpt-5-codex

gpt-5.1-codex-mini

Contact Us

On this page