Unlock exclusive introductory pricing for the newly launched Gemini 3.5 Flash.
D

DeepSeek V4 Pro

Entrada:$0.416/M
Salida:$0.832/M
Publicado:Apr 23, 2026

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

Nuevo
Popular
Uso comercial

Playground para DeepSeek V4 Pro

Explora el Playground de DeepSeek V4 Pro โ€” un entorno interactivo para probar modelos y ejecutar consultas en tiempo real. Prueba prompts, ajusta parรกmetros e itera instantรกneamente para acelerar el desarrollo y validar casos de uso.

Technical specifications

ItemDeepSeek-V4-Pro
ProviderDeepSeek
API model namedeepseek-v4-pro
Base URLshttps://api.deepseek.com and https://api.deepseek.com/anthropic
Input typeText
Output typeText, tool calls, reasoning output
Context length1,000,000 tokens
Max output384,000 tokens
Reasoning modesNon-thinking, thinking (default)
Agent/coding defaultsreasoning_effort can be set as high; complex agent requests may use max
Supported featuresJSON Output, Tool Calls, Chat Prefix Completion (beta), FIM Completion (beta in non-thinking mode)
Local/open-weights release1.6T total parameters, 49B activated parameters, FP4 + FP8 mixed precision
License (model card)MIT
Reference model cardDeepSeek-V4-Pro preview on Hugging Face

What is DeepSeek-V4-Pro?

DeepSeek-V4-Pro is the stronger member of DeepSeekโ€™s V4 preview family. The official model card describes it as a 1.6T-parameter MoE model with 49B activated parameters and a one-million-token context window, aimed at long-horizon knowledge work, code generation, and agent tasks. The API docs expose it through the standard DeepSeek chat-completions surface and support both OpenAI and Anthropic SDK styles.

Main features

  • Million-token context: DeepSeek documents a 1M-token context length, which makes the model suitable for very large document sets, repositories, and multi-step agent sessions.
  • Two reasoning modes: The API supports non-thinking and thinking modes; thinking is the default, and the docs note that complex agent requests such as Claude Code or OpenCode may automatically use max effort.
  • Tool-call capable: DeepSeekโ€™s thinking mode supports tool calls, which is important for agents that need search, file operations, or external functions.
  • Long-context efficiency: The model card says V4 uses a hybrid attention design with Compressed Sparse Attention and Heavily Compressed Attention to reduce long-context compute and KV cache cost relative to V3.2. ๎ˆ€cite๎ˆ‚turn980363view2๎ˆ
  • Coding and reasoning focus: DeepSeek says the V4-Pro-Max reasoning mode advances coding benchmarks and closes much of the gap with leading closed-source models on reasoning and agentic tasks. ๎ˆ€cite๎ˆ‚turn980363view2๎ˆ
  • SDK flexibility: It can be accessed through standard OpenAI-compatible chat completions or via DeepSeekโ€™s Anthropic-compatible endpoint for tool-oriented workflows.

Benchmark performance

The official DeepSeek model card reports the following evaluation results for the base model family and for the V4-Pro-Max comparison set. In the base-model table, V4-Pro scores higher than V3.2-Base on several knowledge and long-context benchmarks, including MMLU-Pro (73.5 vs. 65.5), FACTS Parametric (62.6 vs. 27.1), and LongBench-V2 (51.5 vs. 40.2).

BenchmarkV3.2-BaseV4-Flash-BaseV4-Pro-Base
MMLU-Pro (EM)65.568.373.5
FACTS Parametric (EM)27.133.962.6
HumanEval (Pass@1)62.869.576.8
LongBench-V2 (EM)40.244.751.5

The same model card also shows V4-Pro-Max remaining competitive with top frontier models on selected tasks. For example, it posts 87.5 on MMLU-Pro, 57.9 on SimpleQA-Verified, 90.1 on GPQA Diamond, and 67.9 on Terminal Bench 2.0 in the published comparison table.

DeepSeek-V4-Pro vs DeepSeek-V4-Flash vs DeepSeek-V3.2

ModelBest fitContextNotes
DeepSeek-V4-ProHeavy reasoning, coding, agents, large documents1MLargest V4 model, 49B activated parameters, strongest overall capacity in the series. ๎ˆ€cite๎ˆ‚turn980363view2๎ˆ‚turn980363view0๎ˆ
DeepSeek-V4-FlashFaster, lighter general use1MSmaller 284B/13B model, still supports thinking and tool calls. ๎ˆ€cite๎ˆ‚turn980363view2๎ˆ‚turn980363view0๎ˆ
DeepSeek-V3.2Previous-generation long-context baseline128K in earlier API docs; V4 uses a different 1M context designUseful as a reference point for efficiency gains; V4-Proโ€™s model card reports large reductions in long-context FLOPs and KV cache versus V3.2. ๎ˆ€cite๎ˆ‚turn321011view1๎ˆ‚turn980363view2๎ˆ

Best use cases

  • Repository-scale coding assistants and refactoring tools
  • Long-document analysis and synthesis
  • Tool-using agents that need multi-turn reasoning
  • Technical support workflows that benefit from long memory and structured outputs
  • Chinese and multilingual knowledge tasks where the model card shows strong benchmark performance

How to access and use Deepseek v4 pro API

Step 1: Sign Up for API Key

Log in toย cometapi.com. If you are not our user yet, please register first. Sign into yourย CometAPI console. Get the access credential API key of the interface. Click โ€œAdd Tokenโ€ at the API token in the personal center, get the token key: sk-xxxxx and submit.

Step 2: Send Requests toย Deepseek v4 proAPI

Select the โ€œdeepseek-v4-proโ€ endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace <YOUR_API_KEY> with your actual CometAPI key from your account.ย Where to call it:ย ย Anthropic Messagesย format andย Chatย format.

Insert your question or request into the content fieldโ€”this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results

Process the API response to get the generated answer. After processing, the API responds with the task status and output data.Enable features such as streaming, prompt caching, or long-context handling via standard parameters.

Preguntas frecuentes

Precios para DeepSeek V4 Pro

Explora precios competitivos para DeepSeek V4 Pro, diseรฑado para adaptarse a diversos presupuestos y necesidades de uso. Nuestros planes flexibles garantizan que solo pagues por lo que uses, facilitando el escalado a medida que crecen tus requisitos. Descubre cรณmo DeepSeek V4 Pro puede mejorar tus proyectos mientras mantienes los costos manejables.

ModelComet Price (USD / M Tokens)Official Price (USD / M Tokens)Discount
deepseek-v4-pro
Entrada:$0.416/M
Salida:$0.832/M
Entrada:$0.52/M
Salida:$1.04/M
-20%

Cรณdigo de ejemplo y API para DeepSeek V4 Pro

Accede a cรณdigo de muestra completo y recursos de API para DeepSeek V4 Pro para agilizar tu proceso de integraciรณn. Nuestra documentaciรณn detallada proporciona orientaciรณn paso a paso, ayudรกndote a aprovechar todo el potencial de DeepSeek V4 Pro en tus proyectos.

#!/usr/bin/env bash
# Get your CometAPI key from https://www.cometapi.com/console/token
# Export it as: export COMETAPI_KEY="your-key-here"

if ! command -v jq >/dev/null 2>&1; then
  echo "jq is required to parse streamed reasoning_content in this shell example." >&2
  exit 1
fi

thinking=false

curl --silent --no-buffer --location --request POST "https://api.cometapi.com/v1/chat/completions" \
  --header "Authorization: Bearer $COMETAPI_KEY" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Which number is greater, 9.11 or 9.8? Answer with one sentence."}
    ],
    "thinking": {"type": "enabled"},
    "reasoning_effort": "high",
    "max_tokens": 256,
    "stream": true
  }' | while IFS= read -r line; do
    case "$line" in
      data:\ *) data=${line#data: } ;;
      *) continue ;;
    esac

    [ "$data" = "[DONE]" ] && break

    reasoning=$(printf '%s' "$data" | jq -r '.choices[0].delta.reasoning_content // empty')
    content=$(printf '%s' "$data" | jq -r '.choices[0].delta.content // empty')

    if [ -n "$reasoning" ]; then
      if [ "$thinking" = false ]; then
        printf '<reasoning>
'
        thinking=true
      fi
      printf '%s' "$reasoning"
    fi

    if [ -n "$content" ]; then
      if [ "$thinking" = true ]; then
        printf '
</reasoning>

<answer>
'
        thinking=false
      fi
      printf '%s' "$content"
    fi
  done

printf '
'

cURL Code Example

#!/usr/bin/env bash
# Get your CometAPI key from https://www.cometapi.com/console/token
# Export it as: export COMETAPI_KEY="your-key-here"

if ! command -v jq >/dev/null 2>&1; then
  echo "jq is required to parse streamed reasoning_content in this shell example." >&2
  exit 1
fi

thinking=false

curl --silent --no-buffer --location --request POST "https://api.cometapi.com/v1/chat/completions" \
  --header "Authorization: Bearer $COMETAPI_KEY" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Which number is greater, 9.11 or 9.8? Answer with one sentence."}
    ],
    "thinking": {"type": "enabled"},
    "reasoning_effort": "high",
    "max_tokens": 256,
    "stream": true
  }' | while IFS= read -r line; do
    case "$line" in
      data:\ *) data=${line#data: } ;;
      *) continue ;;
    esac

    [ "$data" = "[DONE]" ] && break

    reasoning=$(printf '%s' "$data" | jq -r '.choices[0].delta.reasoning_content // empty')
    content=$(printf '%s' "$data" | jq -r '.choices[0].delta.content // empty')

    if [ -n "$reasoning" ]; then
      if [ "$thinking" = false ]; then
        printf '<reasoning>\n'
        thinking=true
      fi
      printf '%s' "$reasoning"
    fi

    if [ -n "$content" ]; then
      if [ "$thinking" = true ]; then
        printf '\n</reasoning>\n\n<answer>\n'
        thinking=false
      fi
      printf '%s' "$content"
    fi
  done

printf '\n'

Python Code Example

from openai import OpenAI
import os

# Get your CometAPI key from https://www.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com/v1"

client = OpenAI(base_url=BASE_URL, api_key=COMETAPI_KEY)

stream = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which number is greater, 9.11 or 9.8? Answer with one sentence."},
    ],
    stream=True,
    max_tokens=256,
    reasoning_effort="high",
    extra_body={"thinking": {"type": "enabled"}},
)

thinking = False
for chunk in stream:
    delta = chunk.choices[0].delta
    reasoning = (delta.model_extra or {}).get("reasoning_content") or ""
    content = delta.content or ""

    if reasoning:
        if not thinking:
            print("<reasoning>")
            thinking = True
        print(reasoning, end="", flush=True)

    if content:
        if thinking:
            print("\n</reasoning>\n\n<answer>")
            thinking = False
        print(content, end="", flush=True)

print()

JavaScript Code Example

import OpenAI from "openai";

// Get your CometAPI key from https://www.cometapi.com/console/token, and paste it here
const api_key = process.env.COMETAPI_KEY || "<YOUR_COMETAPI_KEY>";
const base_url = "https://api.cometapi.com/v1";

const client = new OpenAI({
  apiKey: api_key,
  baseURL: base_url,
});

const stream = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Which number is greater, 9.11 or 9.8? Answer with one sentence." },
  ],
  thinking: { type: "enabled" },
  reasoning_effort: "high",
  max_tokens: 256,
  stream: true,
});

let thinking = false;
for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta ?? {};
  const reasoning = delta.reasoning_content ?? "";
  const content = delta.content ?? "";

  if (reasoning) {
    if (!thinking) {
      process.stdout.write("<reasoning>\n");
      thinking = true;
    }
    process.stdout.write(reasoning);
  }

  if (content) {
    if (thinking) {
      process.stdout.write("\n</reasoning>\n\n<answer>\n");
      thinking = false;
    }
    process.stdout.write(content);
  }
}

process.stdout.write("\n");

Uptime

Tasa de รฉxito de solicitudes en los รบltimos 30 dรญas, que refleja la fiabilidad de cada proveedor de modelos. CometAPI monitorea todos los proveedores conectados en tiempo real, las 24 horas del dรญa, los 7 dรญas de la semana.

RespondLIVE
2871msAvg. Response
UptimeLIVE
100.0%Avg. Uptime

Versiones de DeepSeek V4 Pro

La razรณn por la cual DeepSeek V4 Pro tiene mรบltiples instantรกneas puede incluir factores potenciales como variaciones en la salida tras actualizaciones que requieren instantรกneas anteriores para mantener la coherencia, ofrecer a los desarrolladores un perรญodo de transiciรณn para adaptaciรณn y migraciรณn, y diferentes instantรกneas que corresponden a endpoints globales o regionales para optimizar la experiencia del usuario. Para conocer las diferencias detalladas entre versiones, consulte la documentaciรณn oficial.

Version
deepseek-v4-pro