Create a chat completion

curl --request POST \
  --url https://tokens.flex.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "Meta-Llama-3.1-8B-Instruct-FP8",
  "messages": [
    {
      "content": "<string>",
      "name": "<string>",
      "tool_calls": [
        {}
      ],
      "tool_call_id": "<string>"
    }
  ],
  "stream": false,
  "stream_options": {
    "include_usage": true
  },
  "temperature": 1,
  "top_p": 0.5,
  "max_tokens": 2,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {}
      }
    }
  ],
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "user": "<string>"
}
'

import requests

url = "https://tokens.flex.ai/v1/chat/completions"

payload = {
    "model": "Meta-Llama-3.1-8B-Instruct-FP8",
    "messages": [
        {
            "content": "<string>",
            "name": "<string>",
            "tool_calls": [{}],
            "tool_call_id": "<string>"
        }
    ],
    "stream": False,
    "stream_options": { "include_usage": True },
    "temperature": 1,
    "top_p": 0.5,
    "max_tokens": 2,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {}
            }
        }
    ],
    "response_format": {},
    "seed": 123,
    "stop": "<string>",
    "user": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'Meta-Llama-3.1-8B-Instruct-FP8',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_calls: [{}],
        tool_call_id: '<string>'
      }
    ],
    stream: false,
    stream_options: {include_usage: true},
    temperature: 1,
    top_p: 0.5,
    max_tokens: 2,
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}}
      }
    ],
    response_format: {},
    seed: 123,
    stop: '<string>',
    user: '<string>'
  })
};

fetch('https://tokens.flex.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://tokens.flex.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' => 'Meta-Llama-3.1-8B-Instruct-FP8',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_calls' => [
                                [
                                                                
                                ]
                ],
                'tool_call_id' => '<string>'
        ]
    ],
    'stream' => false,
    'stream_options' => [
        'include_usage' => true
    ],
    'temperature' => 1,
    'top_p' => 0.5,
    'max_tokens' => 2,
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'response_format' => [
        
    ],
    'seed' => 123,
    'stop' => '<string>',
    'user' => '<string>'
  ]),
  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://tokens.flex.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\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://tokens.flex.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://tokens.flex.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\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\n}"

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

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {}
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation_input_tokens": 123
  }
}

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

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

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

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

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

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

POST

chat

completions

Create a chat completion

curl --request POST \
  --url https://tokens.flex.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "Meta-Llama-3.1-8B-Instruct-FP8",
  "messages": [
    {
      "content": "<string>",
      "name": "<string>",
      "tool_calls": [
        {}
      ],
      "tool_call_id": "<string>"
    }
  ],
  "stream": false,
  "stream_options": {
    "include_usage": true
  },
  "temperature": 1,
  "top_p": 0.5,
  "max_tokens": 2,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {}
      }
    }
  ],
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "user": "<string>"
}
'

import requests

url = "https://tokens.flex.ai/v1/chat/completions"

payload = {
    "model": "Meta-Llama-3.1-8B-Instruct-FP8",
    "messages": [
        {
            "content": "<string>",
            "name": "<string>",
            "tool_calls": [{}],
            "tool_call_id": "<string>"
        }
    ],
    "stream": False,
    "stream_options": { "include_usage": True },
    "temperature": 1,
    "top_p": 0.5,
    "max_tokens": 2,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {}
            }
        }
    ],
    "response_format": {},
    "seed": 123,
    "stop": "<string>",
    "user": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'Meta-Llama-3.1-8B-Instruct-FP8',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_calls: [{}],
        tool_call_id: '<string>'
      }
    ],
    stream: false,
    stream_options: {include_usage: true},
    temperature: 1,
    top_p: 0.5,
    max_tokens: 2,
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}}
      }
    ],
    response_format: {},
    seed: 123,
    stop: '<string>',
    user: '<string>'
  })
};

fetch('https://tokens.flex.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://tokens.flex.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' => 'Meta-Llama-3.1-8B-Instruct-FP8',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_calls' => [
                                [
                                                                
                                ]
                ],
                'tool_call_id' => '<string>'
        ]
    ],
    'stream' => false,
    'stream_options' => [
        'include_usage' => true
    ],
    'temperature' => 1,
    'top_p' => 0.5,
    'max_tokens' => 2,
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'response_format' => [
        
    ],
    'seed' => 123,
    'stop' => '<string>',
    'user' => '<string>'
  ]),
  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://tokens.flex.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\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://tokens.flex.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://tokens.flex.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\": \"Meta-Llama-3.1-8B-Instruct-FP8\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_calls\": [\n        {}\n      ],\n      \"tool_call_id\": \"<string>\"\n    }\n  ],\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_usage\": true\n  },\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"max_tokens\": 2,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"user\": \"<string>\"\n}"

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

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {}
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation_input_tokens": 123
  }
}

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

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

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

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

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

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

Authorizations

Authorization

string

header

required

Virtual API key. Create one from the FlexAI dashboard. Pass as Authorization: Bearer sk-xxxx.

Body

application/json

model

string

required

Model id. See GET /v1/models for available models.

Example:

"Meta-Llama-3.1-8B-Instruct-FP8"

messages

object[]

required

Show child attributes

stream

boolean

default:false

stream_options

object

Show child attributes

temperature

number

default:1

Required range: 0 <= x <= 2

top_p

number

Required range: 0 <= x <= 1

max_tokens

integer

Required range: x >= 1

tools

object[]

Show child attributes

tool_choice

Available options:

none,

auto,

required

response_format

object

Show child attributes

seed

integer

stop

user

string

Response

Successful response. When stream: true, body is an SSE stream of text/event-stream chunks.

string

required

object

enum<string>

required

Available options:

chat.completion

created

integer

required

model

string

required

choices

object[]

required

Show child attributes

usage

object

Show child attributes

Usage Policy Create a (legacy) text completion

⌘I

Get Started

Guides

Reference

Chat

Completions

Embeddings

Models

Usage

Status

Create a chat completion

Authorizations

Body

Response