Create Response

cURL

curl --request POST \
  --url https://api.concentrate.ai/v1/responses/ \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "model": "<string>",
  "include": [],
  "instructions": "<string>",
  "max_output_tokens": 4503599627370495,
  "metadata": {},
  "reasoning": {},
  "stream": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "parameters": {},
      "description": "<string>",
      "strict": true,
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "tool_choice": {
    "name": "<string>",
    "type": "function"
  },
  "top_p": 0.5,
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "top_logprobs": 10,
  "background": true,
  "context_management": [
    {
      "type": "compaction",
      "compact_threshold": 4503599627370996
    }
  ],
  "conversation": "<string>",
  "max_tool_calls": 4503599627370495,
  "prompt": {
    "id": "<string>",
    "version": "<string>",
    "variables": {}
  },
  "safety_identifier": "<string>",
  "store": true,
  "stream_options": {
    "include_obfuscation": true
  },
  "user": "<string>",
  "routing": {
    "model": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance"
    },
    "provider": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance",
      "interval": "<string>"
    }
  },
  "cache_control": {
    "type": "ephemeral",
    "ttl": "5m"
  }
}
'

import requests

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

payload = {
    "input": "<string>",
    "model": "<string>",
    "include": [],
    "instructions": "<string>",
    "max_output_tokens": 4503599627370495,
    "metadata": {},
    "reasoning": {},
    "stream": True,
    "temperature": 1,
    "text": {
        "format": { "type": "text" },
        "verbosity": "medium"
    },
    "tools": [
        {
            "type": "function",
            "name": "<string>",
            "parameters": {},
            "description": "<string>",
            "strict": True,
            "cache_control": {
                "type": "ephemeral",
                "ttl": "5m"
            }
        }
    ],
    "tool_choice": {
        "name": "<string>",
        "type": "function"
    },
    "top_p": 0.5,
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "prompt_cache_key": "<string>",
    "prompt_cache_options": {},
    "top_logprobs": 10,
    "background": True,
    "context_management": [
        {
            "type": "compaction",
            "compact_threshold": 4503599627370996
        }
    ],
    "conversation": "<string>",
    "max_tool_calls": 4503599627370495,
    "prompt": {
        "id": "<string>",
        "version": "<string>",
        "variables": {}
    },
    "safety_identifier": "<string>",
    "store": True,
    "stream_options": { "include_obfuscation": True },
    "user": "<string>",
    "routing": {
        "model": {
            "fallbacks": ["<string>"],
            "sort": "performance"
        },
        "provider": {
            "fallbacks": ["<string>"],
            "sort": "performance",
            "interval": "<string>"
        }
    },
    "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
    }
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: '<string>',
    model: '<string>',
    include: [],
    instructions: '<string>',
    max_output_tokens: 4503599627370495,
    metadata: {},
    reasoning: {},
    stream: true,
    temperature: 1,
    text: {format: {type: 'text'}, verbosity: 'medium'},
    tools: [
      {
        type: 'function',
        name: '<string>',
        parameters: {},
        description: '<string>',
        strict: true,
        cache_control: {type: 'ephemeral', ttl: '5m'}
      }
    ],
    tool_choice: {name: '<string>', type: 'function'},
    top_p: 0.5,
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    prompt_cache_key: '<string>',
    prompt_cache_options: {},
    top_logprobs: 10,
    background: true,
    context_management: [{type: 'compaction', compact_threshold: 4503599627370996}],
    conversation: '<string>',
    max_tool_calls: 4503599627370495,
    prompt: {id: '<string>', version: '<string>', variables: {}},
    safety_identifier: '<string>',
    store: true,
    stream_options: {include_obfuscation: true},
    user: '<string>',
    routing: {
      model: {fallbacks: ['<string>'], sort: 'performance'},
      provider: {fallbacks: ['<string>'], sort: 'performance', interval: '<string>'}
    },
    cache_control: {type: 'ephemeral', ttl: '5m'}
  })
};

fetch('https://api.concentrate.ai/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.concentrate.ai/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([
    'input' => '<string>',
    'model' => '<string>',
    'include' => [
        
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 4503599627370495,
    'metadata' => [
        
    ],
    'reasoning' => [
        
    ],
    'stream' => true,
    'temperature' => 1,
    'text' => [
        'format' => [
                'type' => 'text'
        ],
        'verbosity' => 'medium'
    ],
    'tools' => [
        [
                'type' => 'function',
                'name' => '<string>',
                'parameters' => [
                                
                ],
                'description' => '<string>',
                'strict' => true,
                'cache_control' => [
                                'type' => 'ephemeral',
                                'ttl' => '5m'
                ]
        ]
    ],
    'tool_choice' => [
        'name' => '<string>',
        'type' => 'function'
    ],
    'top_p' => 0.5,
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'prompt_cache_key' => '<string>',
    'prompt_cache_options' => [
        
    ],
    'top_logprobs' => 10,
    'background' => true,
    'context_management' => [
        [
                'type' => 'compaction',
                'compact_threshold' => 4503599627370996
        ]
    ],
    'conversation' => '<string>',
    'max_tool_calls' => 4503599627370495,
    'prompt' => [
        'id' => '<string>',
        'version' => '<string>',
        'variables' => [
                
        ]
    ],
    'safety_identifier' => '<string>',
    'store' => true,
    'stream_options' => [
        'include_obfuscation' => true
    ],
    'user' => '<string>',
    'routing' => [
        'model' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance'
        ],
        'provider' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance',
                'interval' => '<string>'
        ]
    ],
    'cache_control' => [
        'type' => 'ephemeral',
        'ttl' => '5m'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "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.concentrate.ai/v1/responses/"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}")

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

	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.concentrate.ai/v1/responses/")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}"

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

{
  "id": "<string>",
  "model": "<string>",
  "object": "response",
  "output": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            {
              "type": "url_citation",
              "start_index": 4503599627370495,
              "end_index": 4503599627370495,
              "title": "<string>",
              "url": "<string>"
            }
          ],
          "logprobs": [
            {
              "token": "<string>",
              "bytes": [
                123
              ],
              "logprob": 123,
              "top_logprobs": [
                {
                  "token": "<string>",
                  "bytes": [
                    123
                  ],
                  "logprob": 123
                }
              ]
            }
          ],
          "cache_control": {
            "type": "ephemeral",
            "ttl": "5m"
          },
          "prompt_cache_breakpoint": {
            "mode": "explicit"
          }
        }
      ],
      "type": "message",
      "id": "<string>",
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "usage": {
    "input_tokens": 1,
    "input_tokens_details": {
      "cached_tokens": 1,
      "cached_tokens_created": 1,
      "cache_write_tokens": 1
    },
    "output_tokens": 1,
    "output_tokens_details": {
      "reasoning_tokens": 1
    },
    "total_tokens": 1,
    "tool_calls": {
      "web_search": 1,
      "exa_web_search": 1
    }
  },
  "error": {
    "code": "<string>",
    "message": "<string>",
    "upstream_error": "<string>"
  },
  "frequency_penalty": 123,
  "incomplete_details": {},
  "instructions": "<string>",
  "metadata": {},
  "temperature": 1,
  "tool_choice": {
    "name": "<unknown>",
    "type": "function"
  },
  "tools": [
    {
      "type": "function",
      "name": "<unknown>",
      "parameters": {},
      "description": "<string>",
      "strict": true,
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "top_p": 0.5,
  "background": true,
  "completed_at": 0,
  "created_at": 0,
  "conversation": {
    "id": "<string>"
  },
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "parallel_tool_calls": true,
  "presence_penalty": 123,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "version": "<string>",
    "variables": {}
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "reasoning": {},
  "safety_identifier": "<string>",
  "store": true,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "top_logprobs": 10,
  "user": "<string>",
  "cost": {
    "total": 123,
    "byok": true,
    "breakdown": {}
  },
  "redact": {
    "entities_found": 123,
    "entity_types": [
      "<string>"
    ],
    "models_used": [
      "<string>"
    ],
    "execution_time_ms": 123,
    "redaction_coverage": 123,
    "redacted_input": [
      {
        "content": "<string>",
        "type": "message"
      }
    ],
    "redacted_tools": [
      {
        "type": "function",
        "name": "<unknown>",
        "parameters": {},
        "description": "<string>",
        "strict": true,
        "cache_control": {
          "type": "ephemeral",
          "ttl": "5m"
        }
      }
    ]
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "upstream_error": "<string>"
  }
}

POST

responses

cURL

curl --request POST \
  --url https://api.concentrate.ai/v1/responses/ \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "model": "<string>",
  "include": [],
  "instructions": "<string>",
  "max_output_tokens": 4503599627370495,
  "metadata": {},
  "reasoning": {},
  "stream": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "parameters": {},
      "description": "<string>",
      "strict": true,
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "tool_choice": {
    "name": "<string>",
    "type": "function"
  },
  "top_p": 0.5,
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "top_logprobs": 10,
  "background": true,
  "context_management": [
    {
      "type": "compaction",
      "compact_threshold": 4503599627370996
    }
  ],
  "conversation": "<string>",
  "max_tool_calls": 4503599627370495,
  "prompt": {
    "id": "<string>",
    "version": "<string>",
    "variables": {}
  },
  "safety_identifier": "<string>",
  "store": true,
  "stream_options": {
    "include_obfuscation": true
  },
  "user": "<string>",
  "routing": {
    "model": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance"
    },
    "provider": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance",
      "interval": "<string>"
    }
  },
  "cache_control": {
    "type": "ephemeral",
    "ttl": "5m"
  }
}
'

import requests

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

payload = {
    "input": "<string>",
    "model": "<string>",
    "include": [],
    "instructions": "<string>",
    "max_output_tokens": 4503599627370495,
    "metadata": {},
    "reasoning": {},
    "stream": True,
    "temperature": 1,
    "text": {
        "format": { "type": "text" },
        "verbosity": "medium"
    },
    "tools": [
        {
            "type": "function",
            "name": "<string>",
            "parameters": {},
            "description": "<string>",
            "strict": True,
            "cache_control": {
                "type": "ephemeral",
                "ttl": "5m"
            }
        }
    ],
    "tool_choice": {
        "name": "<string>",
        "type": "function"
    },
    "top_p": 0.5,
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "prompt_cache_key": "<string>",
    "prompt_cache_options": {},
    "top_logprobs": 10,
    "background": True,
    "context_management": [
        {
            "type": "compaction",
            "compact_threshold": 4503599627370996
        }
    ],
    "conversation": "<string>",
    "max_tool_calls": 4503599627370495,
    "prompt": {
        "id": "<string>",
        "version": "<string>",
        "variables": {}
    },
    "safety_identifier": "<string>",
    "store": True,
    "stream_options": { "include_obfuscation": True },
    "user": "<string>",
    "routing": {
        "model": {
            "fallbacks": ["<string>"],
            "sort": "performance"
        },
        "provider": {
            "fallbacks": ["<string>"],
            "sort": "performance",
            "interval": "<string>"
        }
    },
    "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
    }
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: '<string>',
    model: '<string>',
    include: [],
    instructions: '<string>',
    max_output_tokens: 4503599627370495,
    metadata: {},
    reasoning: {},
    stream: true,
    temperature: 1,
    text: {format: {type: 'text'}, verbosity: 'medium'},
    tools: [
      {
        type: 'function',
        name: '<string>',
        parameters: {},
        description: '<string>',
        strict: true,
        cache_control: {type: 'ephemeral', ttl: '5m'}
      }
    ],
    tool_choice: {name: '<string>', type: 'function'},
    top_p: 0.5,
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    prompt_cache_key: '<string>',
    prompt_cache_options: {},
    top_logprobs: 10,
    background: true,
    context_management: [{type: 'compaction', compact_threshold: 4503599627370996}],
    conversation: '<string>',
    max_tool_calls: 4503599627370495,
    prompt: {id: '<string>', version: '<string>', variables: {}},
    safety_identifier: '<string>',
    store: true,
    stream_options: {include_obfuscation: true},
    user: '<string>',
    routing: {
      model: {fallbacks: ['<string>'], sort: 'performance'},
      provider: {fallbacks: ['<string>'], sort: 'performance', interval: '<string>'}
    },
    cache_control: {type: 'ephemeral', ttl: '5m'}
  })
};

fetch('https://api.concentrate.ai/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.concentrate.ai/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([
    'input' => '<string>',
    'model' => '<string>',
    'include' => [
        
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 4503599627370495,
    'metadata' => [
        
    ],
    'reasoning' => [
        
    ],
    'stream' => true,
    'temperature' => 1,
    'text' => [
        'format' => [
                'type' => 'text'
        ],
        'verbosity' => 'medium'
    ],
    'tools' => [
        [
                'type' => 'function',
                'name' => '<string>',
                'parameters' => [
                                
                ],
                'description' => '<string>',
                'strict' => true,
                'cache_control' => [
                                'type' => 'ephemeral',
                                'ttl' => '5m'
                ]
        ]
    ],
    'tool_choice' => [
        'name' => '<string>',
        'type' => 'function'
    ],
    'top_p' => 0.5,
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'prompt_cache_key' => '<string>',
    'prompt_cache_options' => [
        
    ],
    'top_logprobs' => 10,
    'background' => true,
    'context_management' => [
        [
                'type' => 'compaction',
                'compact_threshold' => 4503599627370996
        ]
    ],
    'conversation' => '<string>',
    'max_tool_calls' => 4503599627370495,
    'prompt' => [
        'id' => '<string>',
        'version' => '<string>',
        'variables' => [
                
        ]
    ],
    'safety_identifier' => '<string>',
    'store' => true,
    'stream_options' => [
        'include_obfuscation' => true
    ],
    'user' => '<string>',
    'routing' => [
        'model' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance'
        ],
        'provider' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance',
                'interval' => '<string>'
        ]
    ],
    'cache_control' => [
        'type' => 'ephemeral',
        'ttl' => '5m'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "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.concentrate.ai/v1/responses/"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}")

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

	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.concentrate.ai/v1/responses/")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 4503599627370495,\n  \"metadata\": {},\n  \"reasoning\": {},\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\": \"medium\"\n  },\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\",\n      \"strict\": true,\n      \"cache_control\": {\n        \"type\": \"ephemeral\",\n        \"ttl\": \"5m\"\n      }\n    }\n  ],\n  \"tool_choice\": {\n    \"name\": \"<string>\",\n    \"type\": \"function\"\n  },\n  \"top_p\": 0.5,\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"top_logprobs\": 10,\n  \"background\": true,\n  \"context_management\": [\n    {\n      \"type\": \"compaction\",\n      \"compact_threshold\": 4503599627370996\n    }\n  ],\n  \"conversation\": \"<string>\",\n  \"max_tool_calls\": 4503599627370495,\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"version\": \"<string>\",\n    \"variables\": {}\n  },\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"model\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\"\n    },\n    \"provider\": {\n      \"fallbacks\": [\n        \"<string>\"\n      ],\n      \"sort\": \"performance\",\n      \"interval\": \"<string>\"\n    }\n  },\n  \"cache_control\": {\n    \"type\": \"ephemeral\",\n    \"ttl\": \"5m\"\n  }\n}"

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

{
  "id": "<string>",
  "model": "<string>",
  "object": "response",
  "output": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            {
              "type": "url_citation",
              "start_index": 4503599627370495,
              "end_index": 4503599627370495,
              "title": "<string>",
              "url": "<string>"
            }
          ],
          "logprobs": [
            {
              "token": "<string>",
              "bytes": [
                123
              ],
              "logprob": 123,
              "top_logprobs": [
                {
                  "token": "<string>",
                  "bytes": [
                    123
                  ],
                  "logprob": 123
                }
              ]
            }
          ],
          "cache_control": {
            "type": "ephemeral",
            "ttl": "5m"
          },
          "prompt_cache_breakpoint": {
            "mode": "explicit"
          }
        }
      ],
      "type": "message",
      "id": "<string>",
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "usage": {
    "input_tokens": 1,
    "input_tokens_details": {
      "cached_tokens": 1,
      "cached_tokens_created": 1,
      "cache_write_tokens": 1
    },
    "output_tokens": 1,
    "output_tokens_details": {
      "reasoning_tokens": 1
    },
    "total_tokens": 1,
    "tool_calls": {
      "web_search": 1,
      "exa_web_search": 1
    }
  },
  "error": {
    "code": "<string>",
    "message": "<string>",
    "upstream_error": "<string>"
  },
  "frequency_penalty": 123,
  "incomplete_details": {},
  "instructions": "<string>",
  "metadata": {},
  "temperature": 1,
  "tool_choice": {
    "name": "<unknown>",
    "type": "function"
  },
  "tools": [
    {
      "type": "function",
      "name": "<unknown>",
      "parameters": {},
      "description": "<string>",
      "strict": true,
      "cache_control": {
        "type": "ephemeral",
        "ttl": "5m"
      }
    }
  ],
  "top_p": 0.5,
  "background": true,
  "completed_at": 0,
  "created_at": 0,
  "conversation": {
    "id": "<string>"
  },
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "parallel_tool_calls": true,
  "presence_penalty": 123,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "version": "<string>",
    "variables": {}
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "reasoning": {},
  "safety_identifier": "<string>",
  "store": true,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "top_logprobs": 10,
  "user": "<string>",
  "cost": {
    "total": 123,
    "byok": true,
    "breakdown": {}
  },
  "redact": {
    "entities_found": 123,
    "entity_types": [
      "<string>"
    ],
    "models_used": [
      "<string>"
    ],
    "execution_time_ms": 123,
    "redaction_coverage": 123,
    "redacted_input": [
      {
        "content": "<string>",
        "type": "message"
      }
    ],
    "redacted_tools": [
      {
        "type": "function",
        "name": "<unknown>",
        "parameters": {},
        "description": "<string>",
        "strict": true,
        "cache_control": {
          "type": "ephemeral",
          "ttl": "5m"
        }
      }
    ]
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "upstream_error": "<string>"
  }
}

Overview

The main endpoint for generating AI responses. Supports both streaming and non-streaming modes, with automatic normalization across all providers.

Guardrails

Redaction guardrails are configured on your API key (not in this endpoint body). When enabled, they are applied automatically for requests made with that key. See Guardrails & Redaction.

Body

application/json

input

required

Text, image, or file inputs to the model, used to generate a response.

Minimum string length: 1

model

string

required

Model identifier. Use /v1/models to list all available models. Supports canonical names (e.g. gpt-5.2, claude-opus-4-6), aliases, and provider-prefixed formats (e.g. openai/gpt-5.2). Use "auto" for automatic model selection.

include

enum<string>[] | null

Specify additional output data to include in the model response.

Maximum array length: 8

Available options:

web_search_call.results,

web_search_call.action.sources,

message.output_text.logprobs,

message.input_image.image_url,

reasoning.encrypted_content,

file_search_call.results,

computer_call_output.output.image_url,

code_interpreter_call.outputs

instructions

string | null

A system (or developer) message inserted into the model's context. When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

max_output_tokens

integer | null

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

Required range: 0 < x <= 9007199254740991

metadata

object | null

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Show child attributes

reasoning

object | null

Configuration options for reasoning models.

Show child attributes

stream

boolean | null

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

temperature

number | null

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

Required range: 0 <= x <= 2

text

object | null

Configuration options for a text response from the model. Can be plain text or structured JSON data.

Show child attributes

tools

(Function Tool · object | Web Search Tool · object | Custom Tool · object)[] | null

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

A tool the model may call while generating a response.

Function Tool
Web Search Tool
Custom Tool

Show child attributes

tool_choice

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Show child attributes

top_p

number | null

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Required range: 0 <= x <= 1

parallel_tool_calls

boolean | null

Whether to allow the model to run tool calls in parallel.

previous_response_id

string | null

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Cannot be used in conjunction with conversation. Concentrate enables this for all models. In order to be used, request logging must be enabled. Learn more.

prompt_cache_key

string | null

Used to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. If prompt_cache_key or user is not set, Concentrate will automatically add a prompt cache key based on your API key.

prompt_cache_options

object | null

OpenAI prompt-cache behavior for this request.

Show child attributes

prompt_cache_retention

enum<string> | null

The legacy OpenAI prompt-cache retention policy. Earlier OpenAI models use this field for in-memory or 24-hour retention. GPT-5.6 and later use prompt_cache_options.ttl instead.

Available options:

in-memory,

in_memory,

24h

top_logprobs

integer | null

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.

Required range: 0 <= x <= 20

background

boolean | null

Whether to run the model response in the background. Unsupported, but included for compatibility.

context_management

object[] | null

Configuration for how the model's context window is managed during a response, such as automatic compaction of older turns. Supported on OpenAI models. Note: on OpenAI gpt-5-family reasoning models, OpenAI's backend currently errors when compaction triggers during a response that performs native web search.

Show child attributes

conversation

The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Cannot be used in conjunction with previous_response_id. Currently unsupported, but included for compatibility. Use previous_response_id instead.

max_tool_calls

integer | null

The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

Required range: 0 < x <= 9007199254740991

prompt

object | null

Reference to a prompt template and its variables. Currently unsupported, but included for compatibility.

Show child attributes

safety_identifier

string | null

A stable identifier used to help detect users of your application that may be violating usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Unsupported, as Concentrate reserves this field.

service_tier

enum<string> | null

Specifies the processing type used for serving the request. Determines the pricing and performance tier used to process the request. When not set, the default behavior is auto. Currently unsupported, but included for compatibility.

Available options:

auto,

default,

flex,

scale,

priority

store

boolean | null

Whether to store the generated model response for later retrieval via API.

stream_options

object | null

Options for streaming responses. Only set this when you set stream: true.

Show child attributes

truncation

enum<string> | null

The truncation strategy to use for the model response. auto: if the input exceeds the model's context window size, the model truncates the response by dropping items from the beginning of the conversation. disabled (default): if the input size exceeds the context window size for a model, the request fails with a 400 error. Currently unsupported, but included for compatibility.

Available options:

auto,

disabled

user

string | null

This field is being replaced by safety_identifier and prompt_cache_key. We recommend using prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help detect and prevent abuse. Using this as a safety identifier has no effect, but this value will be used for prompt_cache_key instead of a value based on your API key if provided.

routing

object | null

Concentrate routing configuration controlling how requests are routed across models and providers. Learn more about routing.

Show child attributes

cache_control

object | null

Cache control settings for explicit prompt caching of this content.

Show child attributes

Response

Default Response

string

required

model

string

required

object

enum<string>

default:response

required

Available options:

response

output

required

A message item produced by the model.

Show child attributes

usage

object | null

required

Show child attributes

error

object | null

Show child attributes

frequency_penalty

number | null

incomplete_details

object | null

Show child attributes

instructions

metadata

object | null

Show child attributes

temperature

number | null

Required range: 0 <= x <= 2

tool_choice

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Show child attributes

tools

(Function Tool · object | Web Search Tool · object | Custom Tool · object)[] | null

A tool the model may call while generating a response.

Function Tool
Web Search Tool
Custom Tool

Show child attributes

top_p

number | null

Required range: 0 <= x <= 1

background

boolean | null

completed_at

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

created_at

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

conversation

object | null

Show child attributes

max_output_tokens

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

max_tool_calls

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

parallel_tool_calls

boolean | null

presence_penalty

number | null

previous_response_id

string | null

prompt

object | null

Reference to a prompt template and its variables. Currently unsupported, but included for compatibility.

Show child attributes

prompt_cache_key

string | null

prompt_cache_options

object | null

OpenAI prompt-cache behavior for this request.

Show child attributes

prompt_cache_retention

enum<string> | null

The legacy OpenAI prompt-cache retention policy. Earlier OpenAI models use this field for in-memory or 24-hour retention. GPT-5.6 and later use prompt_cache_options.ttl instead.

Available options:

in-memory,

in_memory,

24h

reasoning

object | null

Configuration options for reasoning models.

Show child attributes

safety_identifier

string | null

service_tier

enum<string> | null

Available options:

auto,

default,

flex,

scale,

priority

status

enum<string> | null

The status of the response. One of completed, in_progress, incomplete, failed, cancelled, or queued.

Available options:

completed,

in_progress,

incomplete,

failed,

cancelled,

queued

store

boolean | null

text

object | null

Configuration options for a text response from the model. Can be plain text or structured JSON data.

Show child attributes

top_logprobs

integer | null

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.

Required range: 0 <= x <= 20

truncation

enum<string> | null

Available options:

auto,

disabled

user

string | null

cost

object | null

Show child attributes

redact

object | null

Show child attributes

⌘I

API Documentation

Responses

Chat Completions (Beta)

Messages (Beta)

Models

Utilities

Features

Reference

Overview

Guardrails

Body

Response

​Overview

​Guardrails

Body

Response

Overview

Guardrails