Chat

Responses

Alpha - This endpoint is currently available to Alpha testers only.

Creates a model response using the Responses API format. This is an OpenAI-compatible endpoint for Venice text models.

E2EE Model Limitation - E2EE-capable models are not supported on /api/v1/responses. Use /api/v1/chat/completions with the required E2EE headers instead.

Stateless Only - This API is stateless. Each request is independent and no conversation state is persisted between requests. You must include the full conversation history in each request.

The Responses API provides a structured output format with typed blocks for:

Reasoning: Thought process and reasoning chains from reasoning models
Messages: The main text response from the model
Function Calls: Tool/function call outputs
Web Search: Results from web search if enabled

This endpoint supports streaming via Server-Sent Events when stream: true is set.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST

responses

Create a response (Alpha)

curl --request POST \
  --url https://api.venice.ai/api/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "zai-org-glm-5-1",
  "input": "<string>",
  "include": [
    "<string>"
  ],
  "max_output_tokens": 1,
  "temperature": 1,
  "top_p": 0.5,
  "fallbacks": [
    {
      "model": "claude-opus-4-8"
    }
  ],
  "reasoning": {
    "enabled": true
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": true
      }
    }
  ],
  "tool_choice": "auto",
  "web_search": true,
  "stream": true,
  "anon_user_id": "end-user-123",
  "venice_parameters": {
    "character_slug": "<string>",
    "enable_e2ee": true,
    "enable_web_scraping": true,
    "enable_web_citations": true,
    "include_venice_system_prompt": true,
    "include_search_results_in_stream": true
  }
}
'

import requests

url = "https://api.venice.ai/api/v1/responses"

payload = {
    "model": "zai-org-glm-5-1",
    "input": "<string>",
    "include": ["<string>"],
    "max_output_tokens": 1,
    "temperature": 1,
    "top_p": 0.5,
    "fallbacks": [{ "model": "claude-opus-4-8" }],
    "reasoning": { "enabled": True },
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {},
                "strict": True
            }
        }
    ],
    "tool_choice": "auto",
    "web_search": True,
    "stream": True,
    "anon_user_id": "end-user-123",
    "venice_parameters": {
        "character_slug": "<string>",
        "enable_e2ee": True,
        "enable_web_scraping": True,
        "enable_web_citations": True,
        "include_venice_system_prompt": True,
        "include_search_results_in_stream": True
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'zai-org-glm-5-1',
    input: '<string>',
    include: ['<string>'],
    max_output_tokens: 1,
    temperature: 1,
    top_p: 0.5,
    fallbacks: [{model: 'claude-opus-4-8'}],
    reasoning: {enabled: true},
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}, strict: true}
      }
    ],
    tool_choice: 'auto',
    web_search: true,
    stream: true,
    anon_user_id: 'end-user-123',
    venice_parameters: {
      character_slug: '<string>',
      enable_e2ee: true,
      enable_web_scraping: true,
      enable_web_citations: true,
      include_venice_system_prompt: true,
      include_search_results_in_stream: true
    }
  })
};

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

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'zai-org-glm-5-1',
    'input' => '<string>',
    'include' => [
        '<string>'
    ],
    'max_output_tokens' => 1,
    'temperature' => 1,
    'top_p' => 0.5,
    'fallbacks' => [
        [
                'model' => 'claude-opus-4-8'
        ]
    ],
    'reasoning' => [
        'enabled' => true
    ],
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => true
                ]
        ]
    ],
    'tool_choice' => 'auto',
    'web_search' => true,
    'stream' => true,
    'anon_user_id' => 'end-user-123',
    'venice_parameters' => [
        'character_slug' => '<string>',
        'enable_e2ee' => true,
        'enable_web_scraping' => true,
        'enable_web_citations' => true,
        'include_venice_system_prompt' => true,
        'include_search_results_in_stream' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.venice.ai/api/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}"

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

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 123,
  "model": "<string>",
  "status": "completed",
  "output": [
    {
      "type": "reasoning",
      "id": "<string>",
      "summary": [
        "<string>"
      ],
      "encrypted_content": "<string>"
    }
  ],
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "total_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens_details": {
      "reasoning_tokens": 123
    }
  },
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

Beta endpoint, available to all API users. Venice translates Responses requests through Chat Completions, so some Responses features are ignored today: instructions, text.format, previous_response_id, reasoning replay, and provider-hosted tools. The Venice system prompt is also on by default here. See the Responses API guide for the full list and workarounds.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request body for the Responses API endpoint. E2EE-capable models are not supported on /api/v1/responses; use /api/v1/chat/completions with the required E2EE headers instead.

model

string

required

The ID of the model to use. E2EE-capable models are not supported on /api/v1/responses; use /api/v1/chat/completions with the required E2EE headers instead.

Example:

"zai-org-glm-5-1"

input

required

The input to generate a response for. Can be a simple string or an array of messages.

include

string[]

Additional response fields to include (OpenAI-compatible).

max_output_tokens

integer

Maximum number of tokens to generate.

Required range: x > 0

temperature

number

Sampling temperature between 0 and 2.

Required range: 0 <= x <= 2

top_p

number

Nucleus sampling parameter.

Required range: 0 <= x <= 1

fallbacks

object[]

Anthropic beta parameter for Claude Fable 5 server-side refusal fallback. Forwarded only for direct Anthropic routes; ignored for other providers.

Maximum array length: 10

Show child attributes

Example:

[{ "model": "claude-opus-4-8" }]

reasoning

Reasoning Configuration · object | null

Show child attributes

tools

A list of tools the model may call.

Show child attributes

tool_choice

Controls which tool is called by the model.

Available options:

auto

web_search

boolean

Enable web search for this request.

stream

boolean

Whether to stream back partial progress.

anon_user_id

string

Optional identifier for the API customer's end user. Combined with the Venice user id when attributing the request to upstream providers. Distinct from the discarded OpenAI user field. Must be printable ASCII and must not contain ||.

Required string length: 1 - 128

Pattern: ^[\x20-\x7E]+$

Example:

"end-user-123"

venice_parameters

Venice Parameters · object

Show child attributes

Response

Successful response

Response from the Responses API endpoint.

string

required

Unique identifier for the response.

Example:

"resp_abc123"

object

enum<string>

required

The object type.

Available options:

response

created_at

integer

required

Unix timestamp of when the response was created.

model

string

required

The model used for the response.

status

enum<string>

required

The status of the response.

Available options:

completed,

failed,

in_progress,

cancelled,

incomplete

output

(Reasoning Output · object | Message Output · object | Function Call Output · object | Web Search Call Output · object)[]

required

The output items generated by the model.

Reasoning Output
Message Output
Function Call Output
Web Search Call Output

Show child attributes

incomplete_details

object

Why generation ended before completion; partial output and usage are retained.

Show child attributes

usage

Usage · object

Token usage statistics.

Show child attributes

error

Error · object

Error information if the response failed.

Show child attributes

⌘I

Create a response (Alpha)

curl --request POST \
  --url https://api.venice.ai/api/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "zai-org-glm-5-1",
  "input": "<string>",
  "include": [
    "<string>"
  ],
  "max_output_tokens": 1,
  "temperature": 1,
  "top_p": 0.5,
  "fallbacks": [
    {
      "model": "claude-opus-4-8"
    }
  ],
  "reasoning": {
    "enabled": true
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": true
      }
    }
  ],
  "tool_choice": "auto",
  "web_search": true,
  "stream": true,
  "anon_user_id": "end-user-123",
  "venice_parameters": {
    "character_slug": "<string>",
    "enable_e2ee": true,
    "enable_web_scraping": true,
    "enable_web_citations": true,
    "include_venice_system_prompt": true,
    "include_search_results_in_stream": true
  }
}
'

import requests

url = "https://api.venice.ai/api/v1/responses"

payload = {
    "model": "zai-org-glm-5-1",
    "input": "<string>",
    "include": ["<string>"],
    "max_output_tokens": 1,
    "temperature": 1,
    "top_p": 0.5,
    "fallbacks": [{ "model": "claude-opus-4-8" }],
    "reasoning": { "enabled": True },
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {},
                "strict": True
            }
        }
    ],
    "tool_choice": "auto",
    "web_search": True,
    "stream": True,
    "anon_user_id": "end-user-123",
    "venice_parameters": {
        "character_slug": "<string>",
        "enable_e2ee": True,
        "enable_web_scraping": True,
        "enable_web_citations": True,
        "include_venice_system_prompt": True,
        "include_search_results_in_stream": True
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'zai-org-glm-5-1',
    input: '<string>',
    include: ['<string>'],
    max_output_tokens: 1,
    temperature: 1,
    top_p: 0.5,
    fallbacks: [{model: 'claude-opus-4-8'}],
    reasoning: {enabled: true},
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}, strict: true}
      }
    ],
    tool_choice: 'auto',
    web_search: true,
    stream: true,
    anon_user_id: 'end-user-123',
    venice_parameters: {
      character_slug: '<string>',
      enable_e2ee: true,
      enable_web_scraping: true,
      enable_web_citations: true,
      include_venice_system_prompt: true,
      include_search_results_in_stream: true
    }
  })
};

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

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'zai-org-glm-5-1',
    'input' => '<string>',
    'include' => [
        '<string>'
    ],
    'max_output_tokens' => 1,
    'temperature' => 1,
    'top_p' => 0.5,
    'fallbacks' => [
        [
                'model' => 'claude-opus-4-8'
        ]
    ],
    'reasoning' => [
        'enabled' => true
    ],
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => true
                ]
        ]
    ],
    'tool_choice' => 'auto',
    'web_search' => true,
    'stream' => true,
    'anon_user_id' => 'end-user-123',
    'venice_parameters' => [
        'character_slug' => '<string>',
        'enable_e2ee' => true,
        'enable_web_scraping' => true,
        'enable_web_citations' => true,
        'include_venice_system_prompt' => true,
        'include_search_results_in_stream' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.venice.ai/api/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"zai-org-glm-5-1\",\n  \"input\": \"<string>\",\n  \"include\": [\n    \"<string>\"\n  ],\n  \"max_output_tokens\": 1,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"fallbacks\": [\n    {\n      \"model\": \"claude-opus-4-8\"\n    }\n  ],\n  \"reasoning\": {\n    \"enabled\": true\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\",\n  \"web_search\": true,\n  \"stream\": true,\n  \"anon_user_id\": \"end-user-123\",\n  \"venice_parameters\": {\n    \"character_slug\": \"<string>\",\n    \"enable_e2ee\": true,\n    \"enable_web_scraping\": true,\n    \"enable_web_citations\": true,\n    \"include_venice_system_prompt\": true,\n    \"include_search_results_in_stream\": true\n  }\n}"

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

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 123,
  "model": "<string>",
  "status": "completed",
  "output": [
    {
      "type": "reasoning",
      "id": "<string>",
      "summary": [
        "<string>"
      ],
      "encrypted_content": "<string>"
    }
  ],
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "total_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens_details": {
      "reasoning_tokens": 123
    }
  },
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}