Chat Completions

cURL

curl --request POST \
  --url https://api.concentrate.ai/v1/chat/completions/ \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "content": "<string>",
      "name": "<string>"
    }
  ],
  "model": "<string>",
  "frequency_penalty": 0,
  "functions": [
    {
      "name": "<string>",
      "parameters": {},
      "description": "<string>"
    }
  ],
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 1,
  "max_tokens": 1,
  "metadata": {},
  "modalities": [],
  "n": 64,
  "parallel_tool_calls": true,
  "prediction": {
    "type": "content",
    "content": "<string>"
  },
  "presence_penalty": 0,
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "response_format": {
    "type": "text"
  },
  "safety_identifier": "<string>",
  "seed": "<string>",
  "stop": "<string>",
  "store": true,
  "stream": true,
  "stream_options": {
    "include_obfuscation": true,
    "include_usage": true
  },
  "temperature": 1,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": false
      }
    }
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "user": "<string>",
  "web_search_options": {
    "user_location": {
      "type": "approximate",
      "approximate": {
        "timezone": "<string>",
        "country": "<string>",
        "city": "<string>",
        "region": "<string>"
      }
    }
  },
  "routing": {
    "model": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance"
    },
    "provider": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance",
      "interval": "<string>"
    }
  }
}
'

import requests

url = "https://api.concentrate.ai/v1/chat/completions/"

payload = {
    "messages": [
        {
            "content": "<string>",
            "name": "<string>"
        }
    ],
    "model": "<string>",
    "frequency_penalty": 0,
    "functions": [
        {
            "name": "<string>",
            "parameters": {},
            "description": "<string>"
        }
    ],
    "logit_bias": {},
    "logprobs": True,
    "max_completion_tokens": 1,
    "max_tokens": 1,
    "metadata": {},
    "modalities": [],
    "n": 64,
    "parallel_tool_calls": True,
    "prediction": {
        "type": "content",
        "content": "<string>"
    },
    "presence_penalty": 0,
    "prompt_cache_key": "<string>",
    "prompt_cache_options": {},
    "response_format": { "type": "text" },
    "safety_identifier": "<string>",
    "seed": "<string>",
    "stop": "<string>",
    "store": True,
    "stream": True,
    "stream_options": {
        "include_obfuscation": True,
        "include_usage": True
    },
    "temperature": 1,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {},
                "strict": False
            }
        }
    ],
    "top_logprobs": 10,
    "top_p": 0.5,
    "user": "<string>",
    "web_search_options": { "user_location": {
            "type": "approximate",
            "approximate": {
                "timezone": "<string>",
                "country": "<string>",
                "city": "<string>",
                "region": "<string>"
            }
        } },
    "routing": {
        "model": {
            "fallbacks": ["<string>"],
            "sort": "performance"
        },
        "provider": {
            "fallbacks": ["<string>"],
            "sort": "performance",
            "interval": "<string>"
        }
    }
}
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({
    messages: [{content: '<string>', name: '<string>'}],
    model: '<string>',
    frequency_penalty: 0,
    functions: [{name: '<string>', parameters: {}, description: '<string>'}],
    logit_bias: {},
    logprobs: true,
    max_completion_tokens: 1,
    max_tokens: 1,
    metadata: {},
    modalities: [],
    n: 64,
    parallel_tool_calls: true,
    prediction: {type: 'content', content: '<string>'},
    presence_penalty: 0,
    prompt_cache_key: '<string>',
    prompt_cache_options: {},
    response_format: {type: 'text'},
    safety_identifier: '<string>',
    seed: '<string>',
    stop: '<string>',
    store: true,
    stream: true,
    stream_options: {include_obfuscation: true, include_usage: true},
    temperature: 1,
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}, strict: false}
      }
    ],
    top_logprobs: 10,
    top_p: 0.5,
    user: '<string>',
    web_search_options: {
      user_location: {
        type: 'approximate',
        approximate: {
          timezone: '<string>',
          country: '<string>',
          city: '<string>',
          region: '<string>'
        }
      }
    },
    routing: {
      model: {fallbacks: ['<string>'], sort: 'performance'},
      provider: {fallbacks: ['<string>'], sort: 'performance', interval: '<string>'}
    }
  })
};

fetch('https://api.concentrate.ai/v1/chat/completions/', 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/chat/completions/",
  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([
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>'
        ]
    ],
    'model' => '<string>',
    'frequency_penalty' => 0,
    'functions' => [
        [
                'name' => '<string>',
                'parameters' => [
                                
                ],
                'description' => '<string>'
        ]
    ],
    'logit_bias' => [
        
    ],
    'logprobs' => true,
    'max_completion_tokens' => 1,
    'max_tokens' => 1,
    'metadata' => [
        
    ],
    'modalities' => [
        
    ],
    'n' => 64,
    'parallel_tool_calls' => true,
    'prediction' => [
        'type' => 'content',
        'content' => '<string>'
    ],
    'presence_penalty' => 0,
    'prompt_cache_key' => '<string>',
    'prompt_cache_options' => [
        
    ],
    'response_format' => [
        'type' => 'text'
    ],
    'safety_identifier' => '<string>',
    'seed' => '<string>',
    'stop' => '<string>',
    'store' => true,
    'stream' => true,
    'stream_options' => [
        'include_obfuscation' => true,
        'include_usage' => true
    ],
    'temperature' => 1,
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => false
                ]
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'user' => '<string>',
    'web_search_options' => [
        'user_location' => [
                'type' => 'approximate',
                'approximate' => [
                                'timezone' => '<string>',
                                'country' => '<string>',
                                'city' => '<string>',
                                'region' => '<string>'
                ]
        ]
    ],
    'routing' => [
        'model' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance'
        ],
        'provider' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance',
                'interval' => '<string>'
        ]
    ]
  ]),
  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/chat/completions/"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}")

	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/chat/completions/")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}"

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

{
  "id": "<string>",
  "model": "<string>",
  "created": 1,
  "object": "<string>",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "reasoning": "<string>",
        "reasoning_content": "<string>",
        "tool_calls": [
          {
            "type": "function",
            "id": "<string>",
            "function": {
              "name": "<unknown>",
              "arguments": "<string>"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "url": "<string>",
              "title": "<string>",
              "start_index": 1,
              "end_index": 1
            }
          }
        ]
      },
      "logprobs": {
        "content": [],
        "refusal": []
      }
    }
  ],
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1,
    "prompt_tokens_details": {
      "cached_tokens": 1,
      "audio_tokens": 1,
      "cache_write_tokens": 1
    },
    "completion_tokens_details": {
      "reasoning_tokens": 1,
      "accepted_prediction_tokens": 1,
      "audio_tokens": 1,
      "rejected_prediction_tokens": 1
    }
  },
  "cost": {
    "total": 123,
    "byok": true,
    "breakdown": {}
  },
  "metadata": {},
  "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

chat

completions

cURL

curl --request POST \
  --url https://api.concentrate.ai/v1/chat/completions/ \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "content": "<string>",
      "name": "<string>"
    }
  ],
  "model": "<string>",
  "frequency_penalty": 0,
  "functions": [
    {
      "name": "<string>",
      "parameters": {},
      "description": "<string>"
    }
  ],
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 1,
  "max_tokens": 1,
  "metadata": {},
  "modalities": [],
  "n": 64,
  "parallel_tool_calls": true,
  "prediction": {
    "type": "content",
    "content": "<string>"
  },
  "presence_penalty": 0,
  "prompt_cache_key": "<string>",
  "prompt_cache_options": {},
  "response_format": {
    "type": "text"
  },
  "safety_identifier": "<string>",
  "seed": "<string>",
  "stop": "<string>",
  "store": true,
  "stream": true,
  "stream_options": {
    "include_obfuscation": true,
    "include_usage": true
  },
  "temperature": 1,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {},
        "strict": false
      }
    }
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "user": "<string>",
  "web_search_options": {
    "user_location": {
      "type": "approximate",
      "approximate": {
        "timezone": "<string>",
        "country": "<string>",
        "city": "<string>",
        "region": "<string>"
      }
    }
  },
  "routing": {
    "model": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance"
    },
    "provider": {
      "fallbacks": [
        "<string>"
      ],
      "sort": "performance",
      "interval": "<string>"
    }
  }
}
'

import requests

url = "https://api.concentrate.ai/v1/chat/completions/"

payload = {
    "messages": [
        {
            "content": "<string>",
            "name": "<string>"
        }
    ],
    "model": "<string>",
    "frequency_penalty": 0,
    "functions": [
        {
            "name": "<string>",
            "parameters": {},
            "description": "<string>"
        }
    ],
    "logit_bias": {},
    "logprobs": True,
    "max_completion_tokens": 1,
    "max_tokens": 1,
    "metadata": {},
    "modalities": [],
    "n": 64,
    "parallel_tool_calls": True,
    "prediction": {
        "type": "content",
        "content": "<string>"
    },
    "presence_penalty": 0,
    "prompt_cache_key": "<string>",
    "prompt_cache_options": {},
    "response_format": { "type": "text" },
    "safety_identifier": "<string>",
    "seed": "<string>",
    "stop": "<string>",
    "store": True,
    "stream": True,
    "stream_options": {
        "include_obfuscation": True,
        "include_usage": True
    },
    "temperature": 1,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {},
                "strict": False
            }
        }
    ],
    "top_logprobs": 10,
    "top_p": 0.5,
    "user": "<string>",
    "web_search_options": { "user_location": {
            "type": "approximate",
            "approximate": {
                "timezone": "<string>",
                "country": "<string>",
                "city": "<string>",
                "region": "<string>"
            }
        } },
    "routing": {
        "model": {
            "fallbacks": ["<string>"],
            "sort": "performance"
        },
        "provider": {
            "fallbacks": ["<string>"],
            "sort": "performance",
            "interval": "<string>"
        }
    }
}
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({
    messages: [{content: '<string>', name: '<string>'}],
    model: '<string>',
    frequency_penalty: 0,
    functions: [{name: '<string>', parameters: {}, description: '<string>'}],
    logit_bias: {},
    logprobs: true,
    max_completion_tokens: 1,
    max_tokens: 1,
    metadata: {},
    modalities: [],
    n: 64,
    parallel_tool_calls: true,
    prediction: {type: 'content', content: '<string>'},
    presence_penalty: 0,
    prompt_cache_key: '<string>',
    prompt_cache_options: {},
    response_format: {type: 'text'},
    safety_identifier: '<string>',
    seed: '<string>',
    stop: '<string>',
    store: true,
    stream: true,
    stream_options: {include_obfuscation: true, include_usage: true},
    temperature: 1,
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}, strict: false}
      }
    ],
    top_logprobs: 10,
    top_p: 0.5,
    user: '<string>',
    web_search_options: {
      user_location: {
        type: 'approximate',
        approximate: {
          timezone: '<string>',
          country: '<string>',
          city: '<string>',
          region: '<string>'
        }
      }
    },
    routing: {
      model: {fallbacks: ['<string>'], sort: 'performance'},
      provider: {fallbacks: ['<string>'], sort: 'performance', interval: '<string>'}
    }
  })
};

fetch('https://api.concentrate.ai/v1/chat/completions/', 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/chat/completions/",
  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([
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>'
        ]
    ],
    'model' => '<string>',
    'frequency_penalty' => 0,
    'functions' => [
        [
                'name' => '<string>',
                'parameters' => [
                                
                ],
                'description' => '<string>'
        ]
    ],
    'logit_bias' => [
        
    ],
    'logprobs' => true,
    'max_completion_tokens' => 1,
    'max_tokens' => 1,
    'metadata' => [
        
    ],
    'modalities' => [
        
    ],
    'n' => 64,
    'parallel_tool_calls' => true,
    'prediction' => [
        'type' => 'content',
        'content' => '<string>'
    ],
    'presence_penalty' => 0,
    'prompt_cache_key' => '<string>',
    'prompt_cache_options' => [
        
    ],
    'response_format' => [
        'type' => 'text'
    ],
    'safety_identifier' => '<string>',
    'seed' => '<string>',
    'stop' => '<string>',
    'store' => true,
    'stream' => true,
    'stream_options' => [
        'include_obfuscation' => true,
        'include_usage' => true
    ],
    'temperature' => 1,
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => false
                ]
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'user' => '<string>',
    'web_search_options' => [
        'user_location' => [
                'type' => 'approximate',
                'approximate' => [
                                'timezone' => '<string>',
                                'country' => '<string>',
                                'city' => '<string>',
                                'region' => '<string>'
                ]
        ]
    ],
    'routing' => [
        'model' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance'
        ],
        'provider' => [
                'fallbacks' => [
                                '<string>'
                ],
                'sort' => 'performance',
                'interval' => '<string>'
        ]
    ]
  ]),
  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/chat/completions/"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}")

	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/chat/completions/")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"model\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"functions\": [\n    {\n      \"name\": \"<string>\",\n      \"parameters\": {},\n      \"description\": \"<string>\"\n    }\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 1,\n  \"max_tokens\": 1,\n  \"metadata\": {},\n  \"modalities\": [],\n  \"n\": 64,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {\n    \"type\": \"content\",\n    \"content\": \"<string>\"\n  },\n  \"presence_penalty\": 0,\n  \"prompt_cache_key\": \"<string>\",\n  \"prompt_cache_options\": {},\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"safety_identifier\": \"<string>\",\n  \"seed\": \"<string>\",\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {\n    \"include_obfuscation\": true,\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": false\n      }\n    }\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"user\": \"<string>\",\n  \"web_search_options\": {\n    \"user_location\": {\n      \"type\": \"approximate\",\n      \"approximate\": {\n        \"timezone\": \"<string>\",\n        \"country\": \"<string>\",\n        \"city\": \"<string>\",\n        \"region\": \"<string>\"\n      }\n    }\n  },\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}"

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

{
  "id": "<string>",
  "model": "<string>",
  "created": 1,
  "object": "<string>",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "reasoning": "<string>",
        "reasoning_content": "<string>",
        "tool_calls": [
          {
            "type": "function",
            "id": "<string>",
            "function": {
              "name": "<unknown>",
              "arguments": "<string>"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "url": "<string>",
              "title": "<string>",
              "start_index": 1,
              "end_index": 1
            }
          }
        ]
      },
      "logprobs": {
        "content": [],
        "refusal": []
      }
    }
  ],
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1,
    "prompt_tokens_details": {
      "cached_tokens": 1,
      "audio_tokens": 1,
      "cache_write_tokens": 1
    },
    "completion_tokens_details": {
      "reasoning_tokens": 1,
      "accepted_prediction_tokens": 1,
      "audio_tokens": 1,
      "rejected_prediction_tokens": 1
    }
  },
  "cost": {
    "total": 123,
    "byok": true,
    "breakdown": {}
  },
  "metadata": {},
  "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>"
  }
}

Beta FeatureThe Chat Completions API is currently in beta. It provides OpenAI Chat Completions API compatibility for clients like Cursor, Opencode, and other tools that use the OpenAI format. For production use, we recommend using the Responses API instead.

Overview

OpenAI Chat Completions API compatibility endpoint. Use Concentrate as a drop-in replacement for OpenAI in any tool or SDK that supports configurable base URLs.

Body

application/json

messages

(System Message · object | User Message · object | Assistant Message · object | Tool Message · object)[]

required

A list of messages comprising the conversation so far.

Minimum array length: 1

System Message
User Message
Assistant Message
Tool Message

Show child attributes

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.

frequency_penalty

number | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Required range: -2 <= x <= 2

function_call

Deprecated in favor of the tool_calls parameter. Will be converted to tool_choice. Using tool_choice will overwrite this.

Available options:

none,

auto

functions

object[] | null

Deprecated in favor of the tools parameter. Will be converted to tools when used.

Show child attributes

logit_bias

object | null

Unsupported. Modify the likelihood of specified tokens appearing in the completion.

Show child attributes

logprobs

boolean | null

Whether to return log probabilities of the output tokens. If true, logprobs will be included in the response.

max_completion_tokens

number | null

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.

Required range: x > 0

max_tokens

number | null

Deprecated, use max_completion_tokens instead.

Required range: x > 0

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.

Show child attributes

modalities

enum<string>[] | null

Unsupported. A list of modalities that the model supports. The model will use these modalities when processing the request.

Required array length: 1 - 2 elements

Available options:

text,

audio

integer | null

Unsupported. How many chat completion choices to generate for each input message.

Required range: 1 <= x <= 128

parallel_tool_calls

boolean | null

Whether to enable parallel function calling during tool use.

prediction

object | null

Unsupported. Specifies the model should predict a specified content, then continue generating naturally.

Show child attributes

presence_penalty

number | null

Unsupported. Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Required range: -2 <= x <= 2

prompt_cache_key

string | null

Optional custom identifier for managing prompt cache entries.

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_effort

enum<string> | null

Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all models support all reasoning levels. If your requested reasoning level isn't supported by the model, Concentrate bumps it up, then down, to the closest reasoning level.

Available options:

none,

minimal,

low,

medium,

high,

xhigh,

max

response_format

Text Format · object

An object specifying the format that the model must output.

Text Format
JSON Schema Format
JSON Object Format

Show child attributes

safety_identifier

string | null

Unique identifier to help detect when content may violate usage policies.

seed

string | null

Unsupported. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

service_tier

enum<string> | null

Specifies which tier to use for processing the request.

Available options:

auto,

default,

flex,

scale,

priority

stop

Unsupported. Up to 4 sequences where the API will stop generating further tokens.

store

boolean | null

If true, the model's response will be stored for reuse by other requests.

stream

boolean | null

If true, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available.

stream_options

object | null

Show child attributes

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.

Required range: 0 <= x <= 2

tool_choice

Controls which (if any) function is called by the model.

Available options:

none,

auto,

required

tools

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

A list of tools the model may call.

Function Tool
Custom Tool

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

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.

Required range: 0 <= x <= 1

user

string | null

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

verbosity

enum<string> | null

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

Available options:

low,

medium,

high

web_search_options

object | null

Options for web search integration.

Show child attributes

routing

object | null

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

Show child attributes

Response

Default Response

string

required

model

string

required

The model used for the chat completion.

created

number

required

The Unix timestamp (in seconds) of when the chat completion was created.

Required range: x >= 0

object

string

required

The object type, which is always 'chat.completion' or 'chat.completion.chunk'.

choices

object[]

required

A list of chat completion choices. Can contain more than one if n is greater than 1.

Show child attributes

usage

object

required

Usage statistics for the completion request.

Show child attributes

cost

object

required

The cost of the completion request.

Show child attributes

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.

Show child attributes

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

redact

object | null

Show child attributes

⌘I

API Documentation

Responses