DeepSeek V4 Flash

curl -X POST https://api.vibetool.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

import openai

client = openai.OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.vibetool.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

const response = await fetch('https://api.vibetool.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'deepseek/deepseek-v4-flash',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});
const data = await response.json();
console.log(data.choices[0].message.content);

package main

import (
	"bytes"
	"fmt"
	"net/http"
)

func main() {
	url := "https://api.vibetool.ai/v1/chat/completions"
	payload := []byte(`{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello!"}]}`)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	fmt.Println("Status:", resp.Status)
}

{
  "id": "chat_202601201327_c17f839a",
  "object": "chat.completion",
  "model": "deepseek/deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 10,
    "total_tokens": 18
  }
}

{
    "error": {
        "message": "Invalid request",
        "type": "invalid_request_error",
        "param": null,
        "code": 400
    }
}

{
    "error": {
        "message": "Invalid API Key provided",
        "type": "authentication_error",
        "param": null,
        "code": 401
    }
}

{
    "error": {
        "message": "Your credit balance is insufficient",
        "type": "billing_error",
        "param": null,
        "code": 402
    }
}

{
    "error": {
        "message": "Permission denied",
        "type": "permission_error",
        "param": null,
        "code": 403
    }
}

{
    "error": {
        "message": "Resource not found",
        "type": "invalid_request_error",
        "param": null,
        "code": 404
    }
}

{
    "error": {
        "message": "Conflict",
        "type": "conflict_error",
        "param": null,
        "code": 409
    }
}

{
    "error": {
        "message": "Rate limit reached for requests",
        "type": "rate_limit_error",
        "param": null,
        "code": 429
    }
}

{
    "error": {
        "message": "An internal server error occurred",
        "type": "server_error",
        "param": null,
        "code": 500
    }
}

{
    "error": {
        "message": "Service unavailable",
        "type": "server_error",
        "param": null,
        "code": 503
    }
}

POST

chat

completions

curl -X POST https://api.vibetool.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

import openai

client = openai.OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.vibetool.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

const response = await fetch('https://api.vibetool.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'deepseek/deepseek-v4-flash',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});
const data = await response.json();
console.log(data.choices[0].message.content);

package main

import (
	"bytes"
	"fmt"
	"net/http"
)

func main() {
	url := "https://api.vibetool.ai/v1/chat/completions"
	payload := []byte(`{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello!"}]}`)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	fmt.Println("Status:", resp.Status)
}

{
  "id": "chat_202601201327_c17f839a",
  "object": "chat.completion",
  "model": "deepseek/deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 10,
    "total_tokens": 18
  }
}

{
    "error": {
        "message": "Invalid request",
        "type": "invalid_request_error",
        "param": null,
        "code": 400
    }
}

{
    "error": {
        "message": "Invalid API Key provided",
        "type": "authentication_error",
        "param": null,
        "code": 401
    }
}

{
    "error": {
        "message": "Your credit balance is insufficient",
        "type": "billing_error",
        "param": null,
        "code": 402
    }
}

{
    "error": {
        "message": "Permission denied",
        "type": "permission_error",
        "param": null,
        "code": 403
    }
}

{
    "error": {
        "message": "Resource not found",
        "type": "invalid_request_error",
        "param": null,
        "code": 404
    }
}

{
    "error": {
        "message": "Conflict",
        "type": "conflict_error",
        "param": null,
        "code": 409
    }
}

{
    "error": {
        "message": "Rate limit reached for requests",
        "type": "rate_limit_error",
        "param": null,
        "code": 429
    }
}

{
    "error": {
        "message": "An internal server error occurred",
        "type": "server_error",
        "param": null,
        "code": 500
    }
}

{
    "error": {
        "message": "Service unavailable",
        "type": "server_error",
        "param": null,
        "code": 503
    }
}

Overview

DeepSeek V4 Flash is DeepSeek’s speed-first Mixture-of-Experts model, engineered to deliver fast inference without sacrificing the quality you’d expect from a large-scale architecture. With 284 billion total parameters and only 13 billion activated per forward pass, V4 Flash achieves an exceptional throughput-to-quality ratio—making it ideal for latency-sensitive applications where you still need capable, coherent outputs. Its massive 1 million token context window sets it apart from most models in its class, enabling long-document analysis, extended multi-turn conversations, and large codebase comprehension in a single request. Routing DeepSeek V4 Flash through Vibetool gives you a clean, OpenAI-compatible interface with no vendor-specific SDK to learn. One API key, one endpoint, and a simple model slug are all you need to start sending requests. This makes it straightforward to benchmark V4 Flash against other models in your stack, swap it in for cost-sensitive workloads, or build pipelines that need to process very long inputs—like entire repositories, lengthy legal documents, or multi-session chat histories—without chunking or summarization hacks.

Model Slug: deepseek/deepseek-v4-flashUse this exact slug when making API requests to Vibetool.

Model Specifications

Architecture: Mixture-of-Experts (MoE)
Total Parameters: 284B
Activated Parameters: 13B
Context Window: 1,048,576 tokens (1M)
Input Modalities: Text
Output Modalities: Text

Pricing

Pricing: See vibetool.ai/pricing for current rates.

Use Cases

Long-Document Processing: Analyze entire books, legal contracts, or large codebases in a single request thanks to the 1M-token context window.
High-Throughput Pipelines: Power batch processing, classification, and summarization workflows where speed and cost efficiency are critical.
Extended Multi-Turn Assistants: Maintain coherent, context-rich conversations across very long sessions without losing earlier context.
Rapid Prototyping: Iterate quickly on prompts and features with fast response times during development and experimentation.

curl -X POST https://api.vibetool.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

import openai

client = openai.OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.vibetool.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

const response = await fetch('https://api.vibetool.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'deepseek/deepseek-v4-flash',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});
const data = await response.json();
console.log(data.choices[0].message.content);

package main

import (
	"bytes"
	"fmt"
	"net/http"
)

func main() {
	url := "https://api.vibetool.ai/v1/chat/completions"
	payload := []byte(`{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello!"}]}`)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	fmt.Println("Status:", resp.Status)
}

{
  "id": "chat_202601201327_c17f839a",
  "object": "chat.completion",
  "model": "deepseek/deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 10,
    "total_tokens": 18
  }
}

{
    "error": {
        "message": "Invalid request",
        "type": "invalid_request_error",
        "param": null,
        "code": 400
    }
}

{
    "error": {
        "message": "Invalid API Key provided",
        "type": "authentication_error",
        "param": null,
        "code": 401
    }
}

{
    "error": {
        "message": "Your credit balance is insufficient",
        "type": "billing_error",
        "param": null,
        "code": 402
    }
}

{
    "error": {
        "message": "Permission denied",
        "type": "permission_error",
        "param": null,
        "code": 403
    }
}

{
    "error": {
        "message": "Resource not found",
        "type": "invalid_request_error",
        "param": null,
        "code": 404
    }
}

{
    "error": {
        "message": "Conflict",
        "type": "conflict_error",
        "param": null,
        "code": 409
    }
}

{
    "error": {
        "message": "Rate limit reached for requests",
        "type": "rate_limit_error",
        "param": null,
        "code": 429
    }
}

{
    "error": {
        "message": "An internal server error occurred",
        "type": "server_error",
        "param": null,
        "code": 500
    }
}

{
    "error": {
        "message": "Service unavailable",
        "type": "server_error",
        "param": null,
        "code": 503
    }
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model

enum<string>

required

Available options:

deepseek-v4-flash

messages

object[]

required

Show child attributes

stream

boolean

default:false

temperature

number

Required range: 0 <= x <= 2

max_tokens

integer

Response

Chat completion

string

object

string

Example:

"chat.completion"

model

string

choices

object[]

usage

object

Getting Started

Text Generation

Image Generation

Video Generation

DeepSeek V4 Flash

Overview

Model Specifications

Pricing

Use Cases

Authorizations

Body

Response

​Overview

​Model Specifications

​Pricing

​Use Cases

Authorizations

Body

Response

Overview

Model Specifications

Pricing

Use Cases