Responses (ZeroClick)

Create a response (ZeroClick-authenticated)

curl --request POST \
  --url https://api.zerogpu.ai/zeroclick/v1/responses \
  --header 'Content-Type: application/json' \
  --header 'zc-signature: <api-key>' \
  --data '
{
  "model": "LFM2.5-1.2B-Instruct",
  "input": "Summarize the following article: ..."
}
'

import requests

url = "https://api.zerogpu.ai/zeroclick/v1/responses"

payload = {
    "model": "LFM2.5-1.2B-Instruct",
    "input": "Summarize the following article: ..."
}
headers = {
    "zc-signature": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'zc-signature': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: 'LFM2.5-1.2B-Instruct', input: 'Summarize the following article: ...'})
};

fetch('https://api.zerogpu.ai/zeroclick/v1/responses', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.zerogpu.ai/zeroclick/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"LFM2.5-1.2B-Instruct\",\n  \"input\": \"Summarize the following article: ...\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("zc-signature", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.zerogpu.ai/zeroclick/v1/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["zc-signature"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"LFM2.5-1.2B-Instruct\",\n  \"input\": \"Summarize the following article: ...\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "error": "invalid_zeroclick_signature"
}

{}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "error": {
    "message": "Internal error",
    "type": "internal_error"
  }
}

POST

zeroclick

responses

Create a response (ZeroClick-authenticated)

curl --request POST \
  --url https://api.zerogpu.ai/zeroclick/v1/responses \
  --header 'Content-Type: application/json' \
  --header 'zc-signature: <api-key>' \
  --data '
{
  "model": "LFM2.5-1.2B-Instruct",
  "input": "Summarize the following article: ..."
}
'

import requests

url = "https://api.zerogpu.ai/zeroclick/v1/responses"

payload = {
    "model": "LFM2.5-1.2B-Instruct",
    "input": "Summarize the following article: ..."
}
headers = {
    "zc-signature": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'zc-signature': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: 'LFM2.5-1.2B-Instruct', input: 'Summarize the following article: ...'})
};

fetch('https://api.zerogpu.ai/zeroclick/v1/responses', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.zerogpu.ai/zeroclick/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"LFM2.5-1.2B-Instruct\",\n  \"input\": \"Summarize the following article: ...\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("zc-signature", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.zerogpu.ai/zeroclick/v1/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["zc-signature"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"LFM2.5-1.2B-Instruct\",\n  \"input\": \"Summarize the following article: ...\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "error": "invalid_zeroclick_signature"
}

{}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "status": "completed",
  "completed_at": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  },
  "incomplete_details": null,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "type": "message",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            "<unknown>"
          ]
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>",
  "metadata": {}
}

{
  "error": {
    "message": "Internal error",
    "type": "internal_error"
  }
}

This is the Responses endpoint behind ZeroClick, ZeroGPU’s agent-payment layer. Same request/response bodies and same model routing as /v1/responses, except for retired model ids (below) — authentication, authorization, and metering differ.

Authentication — no x-api-key. A buying agent calls ZeroClick’s hosted pay URL; ZeroClick proxies the request and signs the raw request bytes with an HMAC in the zc-signature header. A request is authenticated only by a valid signature.
Authorization — a ZeroClick allowance check runs before any billable work. It fails open on a transient ZeroClick outage (the signature has already verified), but never for a missing or invalid signature.
Retired model ids — deepseek-v4-flash, glm-5.2 and gliner2-base-v1 are served and metered as their successors (deepseek-v4.1-flash, glm-5.3-flash, gliner2.5-base-v1); the response’s model is the successor. Send the current id.
Metering — actual token usage is settled with ZeroClick and reported via the zc-usage response header. Stripe metering is bypassed; ZeroClick is the sole biller.

The input and output shapes vary by model; open a model page for a prefilled playground. Handle errors the same way as API error codes.

Authorizations

zc-signature

string

header

required

HMAC signature minted by ZeroClick over the raw request bytes, of the form t=<unix-seconds>,kid=<key-id>,v1=<hex-hmac>. Verified by the @zeroclickai/sellers SDK against the seller's signing secret keyed by kid. A missing or invalid signature is rejected with 401 invalid_zeroclick_signature; this is never failed open.

Headers

zc-request-id

string

ZeroClick request id, echoed in logs for correlation. Set by ZeroClick when it proxies the request.

Example:

"zcreq_1"

zc-agent-id

string

Identifier of the buying agent. Used to partition logs/analytics by agent; becomes the synthesized caller identity.

Example:

"agt_1"

Body

application/json

model

enum<string>

required

Model id; routes the request via model metadata. Kebab-cased into a ZeroClick service slug for metering. The same models are served on /zeroclick/v1/chat/completions and /zeroclick/v1/responses; embedding, moderation and audio models are routable only on their own endpoints. A retired id (deepseek-v4-flash, glm-5.2, gliner2-base-v1) is still accepted, and is served and metered as its successor.

Available options:

LFM2.5-1.2B-Instruct,

LFM2.5-1.2B-Thinking,

qwen3.6-35b-a3b,

qwen3-30b-a3b-fp8,

deepseek-v4.1-flash,

glm-5.3-flash,

gpt-4.1-mini,

gpt-5.4-nano,

gpt-5.6-luna,

gpt-oss-120b,

llama-3.1-8b-instruct-fast,

llama-3.2-3b-instruct-fast,

zlm-v1-iab-classify-edge,

zlm-v2-iab-classify-edge-enriched,

zlm-v1-iab-domain-classifier,

zlm-v1-signal-extract,

deberta-v3-small,

gliner2.5-base-v1,

gliner2.5-multi-v1,

gliner2.5-decide-v1,

gliner-multi-pii-v1

Example:

"LFM2.5-1.2B-Instruct"

input

string

required

Prompt text. Combined with instructions (as a system message) to form the model input.

instructions

string

System-style instructions prepended to the input. Classification models may pass comma-separated or bracketed candidate labels here.

max_output_tokens

integer | null

parallel_tool_calls

boolean

default:true

previous_response_id

string | null

store

boolean

default:true

temperature

number | null

top_p

number | null

truncation

enum<string>

default:auto

Available options:

auto,

disabled

Response

OpenAI Responses response object. Includes the zc-usage header settling actual usage with ZeroClick.

OpenAI Responses response object. On error, status is failed and error is populated.

string

object

string

Allowed value: "response"

created_at

integer

status

enum<string>

Available options:

completed,

failed

completed_at

integer | null

error

null | object

Error attached to a Responses envelope. OpenAI's ResponseError carries code and message; type and param are also emitted by some error sites on this endpoint.

Hide child attributes

error.message

string

required

error.type

string

error.param

string

error.code

string

incomplete_details

unknown

instructions

string | null

max_output_tokens

integer | null

model

string

output

object[]

Hide child attributes

output.type

string

Allowed value: "message"

output.id

string

output.status

string

output.role

string

Allowed value: "assistant"

output.content

object[]

Hide child attributes

output.content.type

string

Allowed value: "output_text"

output.content.text

string

output.content.annotations

any[]

parallel_tool_calls

boolean

previous_response_id

string | null

reasoning

object

Hide child attributes

reasoning.effort

unknown

reasoning.summary

unknown

store

boolean

temperature

number | null

text

object

Hide child attributes

text.format

object

Hide child attributes

text.format.type

string

tool_choice

string

tools

any[]

top_p

number | null

truncation

enum<string>

Available options:

auto,

disabled

usage

object | null

Hide child attributes

usage.input_tokens

integer

usage.input_tokens_details

object

Hide child attributes

usage.input_tokens_details.cached_tokens

integer

usage.output_tokens

integer

usage.output_tokens_details

object

Hide child attributes

usage.output_tokens_details.reasoning_tokens

integer

usage.total_tokens

integer

user

string | null

metadata

object

Hide child attributes

metadata.{key}

string

Endpoints

Audio Models

ZeroClick

Batch API

Responses (ZeroClick)

Authorizations

Headers

Body

Response