deepseek-v4-flash Chat Completions

deepseek-v4-flash

curl --request POST \
  --url https://api.powertokens.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "content": "You are a helpful assistant",
      "role": "system"
    },
    {
      "content": "Hi",
      "role": "user"
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "high",
  "max_tokens": 4096,
  "response_format": {
    "type": "text"
  },
  "stop": null,
  "stream": false,
  "stream_options": null,
  "temperature": 1,
  "top_p": 1,
  "tools": null,
  "tool_choice": "none",
  "logprobs": false,
  "top_logprobs": null
}
'

import requests

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

payload = {
    "model": "deepseek-v4-flash",
    "messages": [
        {
            "content": "You are a helpful assistant",
            "role": "system"
        },
        {
            "content": "Hi",
            "role": "user"
        }
    ],
    "thinking": { "type": "enabled" },
    "reasoning_effort": "high",
    "max_tokens": 4096,
    "response_format": { "type": "text" },
    "stop": None,
    "stream": False,
    "stream_options": None,
    "temperature": 1,
    "top_p": 1,
    "tools": None,
    "tool_choice": "none",
    "logprobs": False,
    "top_logprobs": None
}
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: 'deepseek-v4-flash',
    messages: [
      {content: 'You are a helpful assistant', role: 'system'},
      {content: 'Hi', role: 'user'}
    ],
    thinking: {type: 'enabled'},
    reasoning_effort: 'high',
    max_tokens: 4096,
    response_format: {type: 'text'},
    stop: null,
    stream: false,
    stream_options: null,
    temperature: 1,
    top_p: 1,
    tools: null,
    tool_choice: 'none',
    logprobs: false,
    top_logprobs: null
  })
};

fetch('https://api.powertokens.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.powertokens.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' => 'deepseek-v4-flash',
    'messages' => [
        [
                'content' => 'You are a helpful assistant',
                'role' => 'system'
        ],
        [
                'content' => 'Hi',
                'role' => 'user'
        ]
    ],
    'thinking' => [
        'type' => 'enabled'
    ],
    'reasoning_effort' => 'high',
    'max_tokens' => 4096,
    'response_format' => [
        'type' => 'text'
    ],
    'stop' => null,
    'stream' => false,
    'stream_options' => null,
    'temperature' => 1,
    'top_p' => 1,
    'tools' => null,
    'tool_choice' => 'none',
    'logprobs' => false,
    'top_logprobs' => null
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

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

	payload := strings.NewReader("{\n  \"model\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.powertokens.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.powertokens.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\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}"

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

{
  "id": "26231-33ea-4464-af18-c8c49d256",
  "object": "chat.completion",
  "created": 1782805310,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?",
        "reasoning_content": "We are given a conversation: \"You are a helpful assistant\" and \"Hi\". We need to respond appropriately. Since I'm the assistant, I should respond to the user's greeting. A simple friendly response is fine."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 55,
    "total_tokens": 65,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 45
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 10
  },
  "system_fingerprint": "fp_9954bca7_prod0820_fp8_kvcache_20260402"
}

{
  "error": {
    "message": "messages is required",
    "type": "invalid_request_error",
    "param": "messages",
    "code": "bad_request_body"
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please retry later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal processing failed, please retry later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

POST

chat

completions

deepseek-v4-flash

curl --request POST \
  --url https://api.powertokens.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "content": "You are a helpful assistant",
      "role": "system"
    },
    {
      "content": "Hi",
      "role": "user"
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "high",
  "max_tokens": 4096,
  "response_format": {
    "type": "text"
  },
  "stop": null,
  "stream": false,
  "stream_options": null,
  "temperature": 1,
  "top_p": 1,
  "tools": null,
  "tool_choice": "none",
  "logprobs": false,
  "top_logprobs": null
}
'

import requests

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

payload = {
    "model": "deepseek-v4-flash",
    "messages": [
        {
            "content": "You are a helpful assistant",
            "role": "system"
        },
        {
            "content": "Hi",
            "role": "user"
        }
    ],
    "thinking": { "type": "enabled" },
    "reasoning_effort": "high",
    "max_tokens": 4096,
    "response_format": { "type": "text" },
    "stop": None,
    "stream": False,
    "stream_options": None,
    "temperature": 1,
    "top_p": 1,
    "tools": None,
    "tool_choice": "none",
    "logprobs": False,
    "top_logprobs": None
}
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: 'deepseek-v4-flash',
    messages: [
      {content: 'You are a helpful assistant', role: 'system'},
      {content: 'Hi', role: 'user'}
    ],
    thinking: {type: 'enabled'},
    reasoning_effort: 'high',
    max_tokens: 4096,
    response_format: {type: 'text'},
    stop: null,
    stream: false,
    stream_options: null,
    temperature: 1,
    top_p: 1,
    tools: null,
    tool_choice: 'none',
    logprobs: false,
    top_logprobs: null
  })
};

fetch('https://api.powertokens.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.powertokens.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' => 'deepseek-v4-flash',
    'messages' => [
        [
                'content' => 'You are a helpful assistant',
                'role' => 'system'
        ],
        [
                'content' => 'Hi',
                'role' => 'user'
        ]
    ],
    'thinking' => [
        'type' => 'enabled'
    ],
    'reasoning_effort' => 'high',
    'max_tokens' => 4096,
    'response_format' => [
        'type' => 'text'
    ],
    'stop' => null,
    'stream' => false,
    'stream_options' => null,
    'temperature' => 1,
    'top_p' => 1,
    'tools' => null,
    'tool_choice' => 'none',
    'logprobs' => false,
    'top_logprobs' => null
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

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

	payload := strings.NewReader("{\n  \"model\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.powertokens.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.powertokens.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\": \"deepseek-v4-flash\",\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful assistant\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"Hi\",\n      \"role\": \"user\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"high\",\n  \"max_tokens\": 4096,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": null,\n  \"stream\": false,\n  \"stream_options\": null,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"tools\": null,\n  \"tool_choice\": \"none\",\n  \"logprobs\": false,\n  \"top_logprobs\": null\n}"

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

{
  "id": "26231-33ea-4464-af18-c8c49d256",
  "object": "chat.completion",
  "created": 1782805310,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?",
        "reasoning_content": "We are given a conversation: \"You are a helpful assistant\" and \"Hi\". We need to respond appropriately. Since I'm the assistant, I should respond to the user's greeting. A simple friendly response is fine."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 55,
    "total_tokens": 65,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 45
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 10
  },
  "system_fingerprint": "fp_9954bca7_prod0820_fp8_kvcache_20260402"
}

{
  "error": {
    "message": "messages is required",
    "type": "invalid_request_error",
    "param": "messages",
    "code": "bad_request_body"
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please retry later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal processing failed, please retry later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

Authorizations

Authorization

string

header

required

Pass Authorization: Bearer <token> in the request header.

Body

application/json

DeepSeek chat completions request body.

model

enum<string>

required

The ID of the model to use. Supports deepseek-v4-flash.

Available options:

deepseek-v4-flash

Example:

"deepseek-v4-flash"

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

A single message in the conversation. Depending on the role, it is divided into four message types: system, user, assistant, and tool.

System message
User message
Assistant message
Tool message

Show child attributes

thinking

object

Controls the switch between thinking mode and non-thinking mode.

Show child attributes

stream

boolean

default:false

If set to true, the model will send message deltas as SSE (server-sent events). The message stream ends with data: [DONE].

stream_options

object

Options for streaming output. This parameter can only be set when the stream parameter is true.

Show child attributes

max_tokens

integer

The maximum number of tokens the model can generate for the completion in a single request. The total length of input and output tokens is limited by the model's context length.

stop

A string or a list of up to 16 strings. The API will stop generating further tokens when it encounters any of these strings.

reasoning_effort

enum<string>

Controls the reasoning effort of the model. For normal requests, the default is high. For some complex agent-style requests (e.g. Claude Code, OpenCode), it is automatically set to max. For compatibility, low and medium are mapped to high, and xhigh is mapped to max.

Available options:

high,

max

response_format

object

An object specifying the format that the model must output. Setting to { "type": "json_object" } enables JSON Output, which guarantees the message the model generates is valid JSON.

Important: When using JSON Output, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

Show child attributes

temperature

number

default:1

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

Required range: 0 <= x <= 2

top_p

number

default:1

An alternative to sampling with temperature, the model considers the results of the tokens with top_p probability. 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

logprobs

boolean

Whether to return the log probabilities of the output tokens. If true, the log probabilities of each output token are returned in the content of the message.

top_logprobs

integer

An integer N between 0 and 20 that specifies the top N tokens by probability to return at each output position, along with their log probabilities. When this parameter is specified, logprobs must be true.

Required range: 0 <= x <= 20

tools

object[]

A list of tools the model may call. Currently, only function is supported as a tool. Use this parameter to provide a list of functions that take JSON as input. Up to 128 functions are supported.

Show child attributes

tool_choice

Controls the model's tool calling behavior. none means the model will not call any tool and instead generates a message. auto means the model can choose to generate a message or call one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

Available options:

none,

auto,

required

user_id

string

Your custom user_id, with the character set [a-zA-Z0-9-_] and a maximum length of 512. Do not include private user information in user_id. user_id can be used to distinguish user identities on your side to help us with content safety review. user_id can be used for KVCache isolation for privacy management. user_id can be used for scheduling isolation of users on your business side.

Response

Success. Returns JSON in non-streaming mode; returns an SSE event stream in streaming mode.

DeepSeek chat completions success response.

string

A unique identifier for the chat.

object

string

The type of the object, which is chat.completion.

created

integer

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

model

string

The name of the model that generated the completion.

system_fingerprint

string

This fingerprint represents the backend configuration that the model runs with.

choices

object[]

A list of completions generated by the model.

Show child attributes

usage

object

Usage information for this chat completion request.

Show child attributes

seed-2-0-pro-260328 Chat Completions

deepseek-v4-pro Chat Completions

Chat Models

Image Models

Video Models

Audio Models

asset library

deepseek-v4-flash Chat Completions

Authorizations

Body

Response