Chat completions

cURL

curl https://compute.prentis.ai/v1/chat/completions \
  -H "Authorization: Bearer $PRENTIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Summarise the CAP theorem in two sentences."}
    ],
    "max_tokens": 200,
    "temperature": 0.7
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://compute.prentis.ai/v1", api_key=os.environ["PRENTIS_API_KEY"])

resp = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Summarise the CAP theorem in two sentences."},
    ],
    max_tokens=200,
    temperature=0.7,
)
print(resp.choices[0].message.content)
print(resp.usage.total_tokens, "tokens billed")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://compute.prentis.ai/v1",
  apiKey: process.env.PRENTIS_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
    { role: "system", content: "You are a concise assistant." },
    { role: "user", content: "Summarise the CAP theorem in two sentences." },
  ],
  max_tokens: 200,
  temperature: 0.7,
});
console.log(resp.choices[0]?.message.content);

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_calls: [
          {
            id: '<string>',
            type: 'function',
            function: {name: '<string>', arguments: '<string>'}
          }
        ],
        tool_call_id: '<string>'
      }
    ],
    stream: false,
    stream_options: {include_usage: false},
    max_tokens: 2,
    max_completion_tokens: 2,
    temperature: 1,
    top_p: 1,
    stop: '<string>',
    seed: 123,
    frequency_penalty: 0,
    presence_penalty: 0,
    user: '<string>',
    tools: [{type: 'function', function: {name: '<string>', parameters: {}, strict: true}}],
    response_format: {json_schema: {}},
    service_tier: 'standard',
    n: 1,
    logprobs: false
  })
};

fetch('https://compute.prentis.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://compute.prentis.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([
    'model' => '<string>',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_calls' => [
                                [
                                                                'id' => '<string>',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => '<string>',
                                                                                                                                'arguments' => '<string>'
                                                                ]
                                ]
                ],
                'tool_call_id' => '<string>'
        ]
    ],
    'stream' => false,
    'stream_options' => [
        'include_usage' => false
    ],
    'max_tokens' => 2,
    'max_completion_tokens' => 2,
    'temperature' => 1,
    'top_p' => 1,
    'stop' => '<string>',
    'seed' => 123,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'user' => '<string>',
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => true
                ]
        ]
    ],
    'response_format' => [
        'json_schema' => [
                
        ]
    ],
    'service_tier' => 'standard',
    'n' => 1,
    'logprobs' => false
  ]),
  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://compute.prentis.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\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://compute.prentis.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://compute.prentis.ai/v1/chat/completions")

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\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\n}"

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

{
  "id": "chatcmpl-01K5S8N4Q2VZ",
  "object": "chat.completion",
  "created": 1789286400,
  "model": "deepseek-v4.1-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A distributed store can hold at most two of consistency, availability and partition tolerance at once. Because partitions do happen in practice, the real choice is between answering with stale data and not answering at all."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 47,
    "total_tokens": 75
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

POST

chat

completions

cURL

curl https://compute.prentis.ai/v1/chat/completions \
  -H "Authorization: Bearer $PRENTIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Summarise the CAP theorem in two sentences."}
    ],
    "max_tokens": 200,
    "temperature": 0.7
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://compute.prentis.ai/v1", api_key=os.environ["PRENTIS_API_KEY"])

resp = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Summarise the CAP theorem in two sentences."},
    ],
    max_tokens=200,
    temperature=0.7,
)
print(resp.choices[0].message.content)
print(resp.usage.total_tokens, "tokens billed")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://compute.prentis.ai/v1",
  apiKey: process.env.PRENTIS_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
    { role: "system", content: "You are a concise assistant." },
    { role: "user", content: "Summarise the CAP theorem in two sentences." },
  ],
  max_tokens: 200,
  temperature: 0.7,
});
console.log(resp.choices[0]?.message.content);

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_calls: [
          {
            id: '<string>',
            type: 'function',
            function: {name: '<string>', arguments: '<string>'}
          }
        ],
        tool_call_id: '<string>'
      }
    ],
    stream: false,
    stream_options: {include_usage: false},
    max_tokens: 2,
    max_completion_tokens: 2,
    temperature: 1,
    top_p: 1,
    stop: '<string>',
    seed: 123,
    frequency_penalty: 0,
    presence_penalty: 0,
    user: '<string>',
    tools: [{type: 'function', function: {name: '<string>', parameters: {}, strict: true}}],
    response_format: {json_schema: {}},
    service_tier: 'standard',
    n: 1,
    logprobs: false
  })
};

fetch('https://compute.prentis.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://compute.prentis.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([
    'model' => '<string>',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_calls' => [
                                [
                                                                'id' => '<string>',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => '<string>',
                                                                                                                                'arguments' => '<string>'
                                                                ]
                                ]
                ],
                'tool_call_id' => '<string>'
        ]
    ],
    'stream' => false,
    'stream_options' => [
        'include_usage' => false
    ],
    'max_tokens' => 2,
    'max_completion_tokens' => 2,
    'temperature' => 1,
    'top_p' => 1,
    'stop' => '<string>',
    'seed' => 123,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'user' => '<string>',
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'parameters' => [
                                                                
                                ],
                                'strict' => true
                ]
        ]
    ],
    'response_format' => [
        'json_schema' => [
                
        ]
    ],
    'service_tier' => 'standard',
    'n' => 1,
    'logprobs' => false
  ]),
  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://compute.prentis.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\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://compute.prentis.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://compute.prentis.ai/v1/chat/completions")

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\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": false\n  },\n  \"max_tokens\": 2,\n  \"max_completion_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"stop\": \"<string>\",\n  \"seed\": 123,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"user\": \"<string>\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"parameters\": {},\n        \"strict\": true\n      }\n    }\n  ],\n  \"response_format\": {\n    \"json_schema\": {}\n  },\n  \"service_tier\": \"standard\",\n  \"n\": 1,\n  \"logprobs\": false\n}"

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

{
  "id": "chatcmpl-01K5S8N4Q2VZ",
  "object": "chat.completion",
  "created": 1789286400,
  "model": "deepseek-v4.1-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A distributed store can hold at most two of consistency, availability and partition tolerance at once. Because partitions do happen in practice, the real choice is between answering with stale data and not answering at all."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 47,
    "total_tokens": 75
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "code": "INVALID_API_KEY",
    "param": "<string>"
  }
}

Streaming

With stream: true the response is text/event-stream: one data: event per chunk, terminated by data: [DONE]. The last data event carries usage whether or not you sent stream_options.include_usage — you never have to choose between streaming and knowing what you were billed. If a stream fails partway, chunks already sent are not withdrawn. You get one more event carrying an error object, then [DONE]. Treat a stream that ended without [DONE] as incomplete.

Token accounting

The usage object is the number you are billed on, not an estimate of it. When a stream is cancelled after the model has begun producing output, those tokens are still billed — see Errors for the two codes where that happens.

Authorizations

Authorization

string

header

required

Authorization: Bearer <your API key>. On /v1/messages, the Anthropic-style x-api-key: <your API key> header is accepted instead.

Headers

Idempotency-Key

string

Your own key for making a retry safe (up to 255 characters). It is accepted and echoed back today; de-duplication of replays arrives in a later release, so a retry is currently a second billable call.

Maximum string length: 255

Body

application/json

model

string

required

Which model answers the call. A bare slug for platform models (deepseek-v4.1-flash), or a full resource name for something your account owns (accounts/{account}/models/{model}, or a deployment). Never an upstream vendor's own name.

Maximum string length: 256

messages

object[]

required

The conversation so far, oldest first. Each turn carries a role (system, user, assistant or tool) and its content.

Minimum array length: 1

Show child attributes

stream

boolean

default:false

Return the answer as server-sent events as it is generated, instead of one response at the end. The last data event carries the usage numbers either way.

stream_options

object

Streaming options. include_usage is accepted for compatibility; usage arrives on the final event whether or not you ask for it.

Show child attributes

max_tokens

integer

Ceiling on how many tokens may be generated. Omit it to use the model's own default.

Required range: x >= 1

max_completion_tokens

integer

Ceiling on generated tokens. Wins over max_tokens when both are sent.

Required range: x >= 1

temperature

number

default:1

How much randomness to allow when picking each token. Lower is more repeatable, higher is more varied.

Required range: 0 <= x <= 2

top_p

number

default:1

Nucleus sampling: only consider the most likely tokens up to this share of the probability mass. Tune this or temperature, not both.

Required range: 0 <= x <= 1

stop

Up to 4 strings that end generation as soon as the model produces one. The matched string is not included in the output.

seed

integer

Best effort repeatability: the same seed with the same parameters returns the same answer on models that support it.

frequency_penalty

number

default:0

Pushes the model away from tokens it has already used often in this answer. Negative values do the opposite.

Required range: -2 <= x <= 2

presence_penalty

number

default:0

Pushes the model away from tokens that have appeared at all in this answer, which tends to move it on to new ground.

Required range: -2 <= x <= 2

user

string

Your own identifier for the end user behind the call. It is echoed back in this request's log line so you can correlate the two; it is not kept on the usage record.

Maximum string length: 256

tools

object[]

Function definitions the model may call. If none of the providers that can serve this model support tools, the call is rejected rather than answered as though you had not asked.

Show child attributes

tool_choice

Whether the model may, must, or must not call a tool: none, auto, required, or one named function.

Available options:

none,

auto,

required

response_format

object

Ask for free text, a JSON object, or JSON matching a schema. Rejected if no provider behind this model can honour it.

Show child attributes

service_tier

enum<string>

default:standard

Which service tier serves the call. Only standard is accepted today.

Available options:

standard,

priority,

fast

integer

How many completions to return.

Only 1 is accepted. Any other value returns INVALID_REQUEST.

logprobs

boolean

Per-token log probabilities.

Only false is accepted. true returns INVALID_REQUEST.

Response

OK. With stream: true the same call answers text/event-stream instead, one chunk per event, terminated by data: [DONE]; the last data event carries usage whether or not you asked for it.

string

required

object

string

required

Allowed value: "chat.completion"

created

integer

required

model

string

required

choices

object[]

required

Show child attributes

usage

object

required

Show child attributes

system_fingerprint

string

Overview

Inference

Models

Chat completions

Streaming

Token accounting

Authorizations

Headers

Body

Response

​Streaming

​Token accounting

Authorizations

Headers

Body

Response

Streaming

Token accounting