Este tópico descreve como chamar os modelos da série DeepSeek na plataforma Alibaba Cloud Model Studio usando uma interface compatível com OpenAI ou o DashScope SDK.
ImportanteOs modelos deepseek-v3, deepseek-v3.1, deepseek-v3.2, deepseek-v3.2-exp, deepseek-r1, deepseek-r1-0528 e deepseek-r1-distill-qwen-7b/14b/32b serão descontinuados em 10 de outubro de 2026. Recomendamos o uso dos seguintes modelos como alternativa: qwen3.7-plus, qwen3.7-max e qwen3.6-flash.
Endpoints do service
O endpoint do service varia conforme a região. Configure a Base URL de acordo com a região selecionada (substitua {WorkspaceId} pelo ID real do Workspace). Os modelos disponíveis e os limites de taxa também variam por região. Para mais informações, consulte o documento Rate limiting.
OpenAI compatible
China (Beijing)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions
US (Virginia)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Singapore
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Germany (Frankfurt)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Japan (Tokyo)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
OpenAI compatible - Responses API
ObservaçãoA Responses API atualmente suporta apenas deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v4-pro e deepseek-v4-pro-0813, estando disponível somente nas regiões China (Beijing) e Singapore.
China (Beijing)
O base_url para chamadas via SDK: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
Endpoint HTTP: POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses
Singapore
O base_url para chamadas via SDK: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
Endpoint HTTP: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses
DashScope
China (Beijing)
O endereço de requisição HTTP é POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
US (Virginia)
O endereço de requisição HTTP é POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1"
Singapore
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
Germany (Frankfurt)
O endereço de requisição HTTP é POST https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1"
Japan (Tokyo)
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/api/v1"
OpenAI compatible
China (Beijing)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions
US (Virginia)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Singapore
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Germany (Frankfurt)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Japan (Tokyo)
O base_url para configuração de chamada via SDK é https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
OpenAI compatible - Responses API
ObservaçãoA Responses API atualmente suporta apenas deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v4-pro e deepseek-v4-pro-0813, estando disponível somente nas regiões China (Beijing) e Singapore.
Singapore
O base_url para chamadas via SDK: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
Endpoint HTTP: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses
China (Beijing)
O base_url para chamadas via SDK: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
Endpoint HTTP: POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses
DashScope
China (Beijing)
O endereço de requisição HTTP é POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
US (Virginia)
O endereço de requisição HTTP é POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1"
Singapore
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
Germany (Frankfurt)
O endereço de requisição HTTP é POST https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1"
Japan (Tokyo)
O endereço de requisição HTTP é POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
O base_url para configuração de chamada via SDK é dashscope.base_http_api_url = "https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/api/v1"
Primeiros passos
O deepseek-v4-pro é o modelo principal da série DeepSeek, destacando-se em programação, matemática e tarefas gerais. O deepseek-v4-flash-0731 é a versão mais recente lançada. Use o parâmetro enable_thinking para alternar entre os modos de raciocínio ativo e inativo. O exemplo a seguir demonstra como chamar o modelo deepseek-v4-pro no modo de raciocínio ativo.
É necessário obtain an API key e configure it as an environment variable. Caso utilize um SDK, também será preciso instale the OpenAI or DashScope SDK.
OpenAI compatible
ObservaçãoO parâmetro enable_thinking não é um parâmetro padrão da OpenAI. O SDK Python da OpenAI o transmite via extra_body, enquanto o SDK Node.js o passa como um parâmetro de nível superior. Já o parâmetro reasoning_effort é padrão da OpenAI e pode ser passado diretamente como parâmetro de nível superior.
Python
Código de exemplo
from openai import OpenAI
import os
# Initialize the OpenAI client
client = OpenAI(
# If the environment variable is not configured, replace it with your Alibaba Cloud Model Studio API key: api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
# Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
messages = [{"role": "user", "content": "Who are you?"}]
completion = client.chat.completions.create(
model="deepseek-v4-pro",
messages=messages,
# Use extra_body to set enable_thinking and enable thinking mode
extra_body={"enable_thinking": True},
stream=True,
stream_options={
"include_usage": True
},
)
reasoning_content = "" # Complete thinking process
answer_content = "" # Complete response
is_answering = False # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking Process" + "=" * 20 + "\n")
for chunk in completion:
if not chunk.choices:
print("\n" + "=" * 20 + "Token Usage" + "=" * 20 + "\n")
print(chunk.usage)
print("Request ID:", chunk.id)
continue
delta = chunk.choices[0].delta
# Collect only the thinking content
if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
if not is_answering:
print(delta.reasoning_content, end="", flush=True)
reasoning_content += delta.reasoning_content
# After receiving content, start generating the response
if hasattr(delta, "content") and delta.content:
if not is_answering:
print("\n" + "=" * 20 + "Complete Response" + "=" * 20 + "\n")
is_answering = True
print(delta.content, end="", flush=True)
answer_content += delta.content
Resposta
====================Thinking Process====================
Okay, the user asked a very simple self-introduction question: "Who are you?".
I need to clarify my identity, introduce myself as DeepSeek in a concise and friendly way, mention my creator, basic features, and the help I can provide.
I can organize the answer like this: first, state my identity directly, mention I was created by the DeepSeek company, then list some key features (free, long context, file upload, etc.), and finally end with a friendly invitation, asking if I can help.
====================Complete Response====================
Hello! I am DeepSeek, an AI assistant created by the DeepSeek company.
I can help you answer various questions, create text, analyze documents, assist with programming, and more. My main features are that I am **free to use**, have a **super long context** (I can process the entire 'The Three-Body Problem' trilogy at once), and support **file uploads** and **web search** (must be enabled manually).
Is there anything I can help you with? Whether it's for study, work, or just a casual chat, I'm happy to talk with you!
====================Token Usage====================
CompletionUsage(completion_tokens=238, prompt_tokens=5, total_tokens=243, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=93, rejected_prediction_tokens=None), prompt_tokens_details=None)
Request ID: chatcmpl-a1b2c3d4-e5f6-7890-abcd-ef1234567890
Node.js
Código de exemplo
import OpenAI from "openai";
import process from 'process';
// Initialize the OpenAI client
const openai = new OpenAI({
// If the environment variable is not configured, replace it with your Alibaba Cloud Model Studio API key: apiKey: "sk-xxx"
apiKey: process.env.DASHSCOPE_API_KEY,
// Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
baseURL: 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1'
});
let reasoningContent = ''; // Complete thinking process
let answerContent = ''; // Complete response
let isAnswering = false; // Indicates whether the response phase has started
async function main() {
try {
const messages = [{ role: 'user', content: 'Who are you?' }];
const stream = await openai.chat.completions.create({
model: 'deepseek-v4-pro',
messages,
// Note: In the Node.js SDK, non-standard parameters like enable_thinking are passed as top-level properties, not within extra_body.
enable_thinking: true,
stream: true,
stream_options: {
include_usage: true
},
});
console.log('\n' + '='.repeat(20) + 'Thinking Process' + '='.repeat(20) + '\n');
for await (const chunk of stream) {
if (!chunk.choices?.length) {
console.log('\n' + '='.repeat(20) + 'Token Usage' + '='.repeat(20) + '\n');
console.log(chunk.usage);
console.log('Request ID:', chunk.id);
continue;
}
const delta = chunk.choices[0].delta;
// Collect only the thinking content
if (delta.reasoning_content !== undefined && delta.reasoning_content !== null) {
if (!isAnswering) {
process.stdout.write(delta.reasoning_content);
}
reasoningContent += delta.reasoning_content;
}
// After receiving content, start generating the response
if (delta.content !== undefined && delta.content) {
if (!isAnswering) {
console.log('\n' + '='.repeat(20) + 'Complete Response' + '='.repeat(20) + '\n');
isAnswering = true;
}
process.stdout.write(delta.content);
answerContent += delta.content;
}
}
} catch (error) {
console.error('Error:', error);
}
}
main();
Resposta
====================Thinking Process====================
Okay, the user asked a very simple self-introduction question: "Who are you?".
I need to clarify my identity, introduce myself as DeepSeek in a concise and friendly way, mention my creator, basic features, and the help I can provide.
I can organize the answer like this: first, state my identity directly, mention I was created by the DeepSeek company, then list some key features (free, long context, file upload, etc.), and finally end with a friendly invitation, asking if I can help.
====================Complete Response====================
Hello! I am DeepSeek, an AI assistant created by the DeepSeek company.
I can help you answer various questions, create text, analyze documents, assist with programming, and more. My main features are that I am **free to use**, have a **super long context** (I can process the entire 'The Three-Body Problem' trilogy at once), and support **file uploads** and **web search** (must be enabled manually).
Is there anything I can help you with? Whether it's for study, work, or just a casual chat, I'm happy to talk with you!
====================Token Usage====================
{
prompt_tokens: 5,
completion_tokens: 243,
total_tokens: 248,
completion_tokens_details: { reasoning_tokens: 83 }
}
Request ID: chatcmpl-a1b2c3d4-e5f6-7890-abcd-ef1234567890
HTTP
Código de exemplo
curl
# Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [
{
"role": "user",
"content": "Who are you?"
}
],
"stream": true,
"stream_options": {
"include_usage": true
},
"enable_thinking": true
}'
DashScope
Python
Código de exemplo
import os
import dashscope
from dashscope import Generation
# Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
# Initialize the request parameters
messages = [{"role": "user", "content": "Who are you?"}]
completion = Generation.call(
# If the environment variable is not configured, replace it with your Alibaba Cloud Model Studio API key: api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
model="deepseek-v4-pro",
messages=messages,
result_format="message", # Set the result format to message
enable_thinking=True,
stream=True, # Enable streaming output
incremental_output=True, # Enable incremental output
)
reasoning_content = "" # Complete thinking process
answer_content = "" # Complete response
is_answering = False # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking Process" + "=" * 20 + "\n")
for chunk in completion:
message = chunk.output.choices[0].message
# Collect only the thinking content
if "reasoning_content" in message:
if not is_answering:
print(message.reasoning_content, end="", flush=True)
reasoning_content += message.reasoning_content
# After receiving content, start generating the response
if message.content:
if not is_answering:
print("\n" + "=" * 20 + "Complete Response" + "=" * 20 + "\n")
is_answering = True
print(message.content, end="", flush=True)
answer_content += message.content
print("\n" + "=" * 20 + "Token Usage" + "=" * 20 + "\n")
print(chunk.usage)
print("Request ID:", chunk.request_id)
Resposta
====================Thinking Process====================
Okay, the user asked a very simple self-introduction question: "Who are you?".
I need to clarify my identity, introduce myself as DeepSeek in a concise and friendly way, mention my creator, basic features, and the help I can provide.
I can organize the answer like this: first, state my identity directly, mention I was created by the DeepSeek company, then list some key features (free, long context, file upload, etc.), and finally end with a friendly invitation, asking if I can help.
====================Complete Response====================
Hello! I am DeepSeek, an AI assistant created by the DeepSeek company.
I can help you answer various questions, create text, analyze documents, assist with programming, and more. My main features are that I am **free to use**, have a **super long context** (I can process the entire 'The Three-Body Problem' trilogy at once), and support **file uploads** and **web search** (must be enabled manually).
Is there anything I can help you with? Whether it's for study, work, or just a casual chat, I'm happy to talk with you!
====================Token Usage====================
{"input_tokens": 6, "output_tokens": 240, "total_tokens": 246, "output_tokens_details": {"reasoning_tokens": 92}}
Request ID: 85735883-9062-9c33-a963-0bc12584ee68
Java
Código de exemplo
ImportanteA versão do DashScope Java SDK deve ser 2.19.4 ou superior.
// DashScope SDK version >= 2.19.4
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.Flowable;
import java.lang.System;
import java.util.Arrays;
public class Main {
private static StringBuilder reasoningContent = new StringBuilder();
private static StringBuilder finalContent = new StringBuilder();
private static boolean isFirstPrint = true;
private static String requestId = "";
private static void handleGenerationResult(GenerationResult message) {
requestId = message.getRequestId();
String reasoning = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
String content = message.getOutput().getChoices().get(0).getMessage().getContent();
if (reasoning != null && !reasoning.isEmpty()) {
reasoningContent.append(reasoning);
if (isFirstPrint) {
System.out.println("====================Thinking Process====================");
isFirstPrint = false;
}
System.out.print(reasoning);
}
if (content != null && !content.isEmpty()) {
finalContent.append(content);
if (!isFirstPrint) {
System.out.println("\n====================Complete Response====================");
isFirstPrint = true;
}
System.out.print(content);
}
}
private static GenerationParam buildGenerationParam(Message userMsg) {
return GenerationParam.builder()
// If the environment variable is not configured, replace the following line with your Alibaba Cloud Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("deepseek-v4-pro")
.enableThinking(true)
.incrementalOutput(true)
.resultFormat("message")
.messages(Arrays.asList(userMsg))
.build();
}
public static void streamCallWithMessage(Generation gen, Message userMsg)
throws NoApiKeyException, ApiException, InputRequiredException {
GenerationParam param = buildGenerationParam(userMsg);
Flowable<GenerationResult> result = gen.streamCall(param);
result.blockingForEach(message -> handleGenerationResult(message));
}
public static void main(String[] args) {
try {
// Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
Generation gen = new Generation("http", "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1");
Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you?").build();
streamCallWithMessage(gen, userMsg);
System.out.println("\nRequest ID: " + requestId);
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.err.println("An exception occurred: " + e.getMessage());
}
}
}
Resposta
====================Thinking Process====================
Okay, the user asked a very simple self-introduction question: "Who are you?".
I need to clarify my identity, introduce myself as DeepSeek in a concise and friendly way, mention my creator, basic features, and the help I can provide.
I can organize the answer like this: first, state my identity directly, mention I was created by the DeepSeek company, then list some key features (free, long context, file upload, etc.), and finally end with a friendly invitation, asking if I can help.
====================Complete Response====================
Hello! I am DeepSeek, an AI assistant created by the DeepSeek company.
I can help you answer various questions, create text, analyze documents, assist with programming, and more. My main features are that I am **free to use**, have a **super long context** (I can process the entire 'The Three-Body Problem' trilogy at once), and support **file uploads** and **web search** (must be enabled manually).
Is there anything I can help you with? Whether it's for study, work, or just a casual chat, I'm happy to talk with you!
HTTP
Código de exemplo
curl
# Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-DashScope-SSE: enable" \
-d '{
"model": "deepseek-v4-pro",
"input":{
"messages":[
{
"role": "user",
"content": "Who are you?"
}
]
},
"parameters":{
"enable_thinking": true,
"incremental_output": true,
"result_format": "message"
}
}'
Anthropic compatible
Autenticação: Passe sua chave de API do Model Studio no cabeçalho x-api-key ou no cabeçalho Authorization: Bearer. Para detalhes sobre parâmetros como o modo de raciocínio, consulte Anthropic-compatible Messages.
Python
Código de exemplo
import anthropic
import os
client = anthropic.Anthropic(
# If the environment variable is not configured, replace the value with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
# When you make a call, replace {WorkspaceId} with your actual Workspace ID.
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
)
message = client.messages.create(
model="deepseek-v4-pro",
max_tokens=1024,
messages=[
{"role": "user", "content": "Who are you?"}
],
stream=True,
)
for event in message:
if event.type == "content_block_delta":
if hasattr(event.delta, "thinking"):
print(event.delta.thinking, end="", flush=True)
if hasattr(event.delta, "text"):
print(event.delta.text, end="", flush=True)
HTTP
Código de exemplo
curl
# Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "deepseek-v4-pro",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Who are you?"
}
]
}'
Intensidade de inferência (reasoning_effort)
Os modelos deepseek-v4-pro, deepseek-v4-flash e deepseek-v4-flash-0731 possuem o modo de raciocínio ativado por padrão. Ajuste a intensidade da inferência através do parâmetro reasoning_effort. Os valores válidos são low, medium, high, xhigh e max. O valor padrão é high.
ObservaçãoOs valores low e medium produzem o mesmo comportamento que high. Já o valor xhigh gera o mesmo comportamento que max.
OpenAI compatible
from openai import OpenAI
import os
client = OpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"),
# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Which is greater, 9.9 or 9.11?"}],
reasoning_effort="high",
)
print(completion.choices[0].message.content)
import OpenAI from "openai";
const openai = new OpenAI({
apiKey: process.env.DASHSCOPE_API_KEY,
// China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
});
const completion = await openai.chat.completions.create({
model: "deepseek-v4-pro",
messages: [{ role: "user", content: "Which is greater, 9.9 or 9.11?" }],
reasoning_effort: "high",
});
console.log(completion.choices[0].message.content);
# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Which is greater, 9.9 or 9.11?"}],
"reasoning_effort": "high"
}'
DashScope
import os
import dashscope
from dashscope import Generation
# The following is the configuration for the China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID when making a call. Configurations vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
response = Generation.call(
api_key=os.getenv("DASHSCOPE_API_KEY"),
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Which is greater, 9.9 or 9.11?"}],
reasoning_effort="high",
result_format="message",
)
print(response.output.choices[0].message.content)
Responses API
Os modelos deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v4-pro e deepseek-v4-pro-0813 aceitam chamadas pela Responses API compatível com OpenAI. Apenas as regiões China (Beijing) e Singapore são suportadas. Para endpoints, consulte Service endpoints.
Ao invocar a Responses API, adicione as ferramentas web_search (Web search), web_extractor (Web extractor) e code_interpreter (Code Interpreter) ao parâmetro tools.
from openai import OpenAI
import os
client = OpenAI(
# If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
# The following URL is for the Singapore region. For the other region, use https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
response = client.responses.create(
model="deepseek-v4-flash",
input="Hello! Please introduce yourself in one sentence.",
# Optional: enable the web search, web extractor, and code interpreter tools
tools=[
{"type": "web_search"},
{"type": "web_extractor"},
{"type": "code_interpreter"},
],
)
# Get the model response
print(response.output_text)
import OpenAI from "openai";
const openai = new OpenAI({
// If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
apiKey: process.env.DASHSCOPE_API_KEY,
// The following URL is for the Singapore region. For the other region, use https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});
const response = await openai.responses.create({
model: "deepseek-v4-flash",
input: "Hello! Please introduce yourself in one sentence.",
// Optional: enable the web search, web extractor, and code interpreter tools
tools: [
{ type: "web_search" },
{ type: "web_extractor" },
{ type: "code_interpreter" },
],
});
// Get the model response
console.log(response.output_text);
# The following URL is for the Singapore region. For the other region, use https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"input": "Hello! Please introduce yourself in one sentence.",
"tools": [
{"type": "web_search"},
{"type": "web_extractor"},
{"type": "code_interpreter"}
]
}'
Outros recursos
| Model | |||||
|---|---|---|---|---|---|
deepseek-v4-pro | Supported | Supported | Supported | Supported | Not supported |
deepseek-v4-pro-us | Supported | Supported | Supported | Supported | Not supported |
deepseek-v4-flash-0731 | Supported | Supported | Supported | Supported | Not supported |
deepseek-v4-flash | Supported | Supported | Supported | Supported | Not supported |
deepseek-v4-flash-us | Supported | Supported | Supported | Supported | Not supported |
deepseek-v3.2 | Supported | Supported | Supported | Not supported | Not supported |
deepseek-v3.2-exp | Supported | Supported
| Not supported | Not supported | Not supported |
deepseek-v3.1 | Supported | Supported
| Supported | Not supported | Not supported |
deepseek-r1 | Supported | Supported | Supported | Not supported | Not supported |
deepseek-r1-0528 | Supported | Supported | Not supported | Not supported | Not supported |
deepseek-v3 | Supported | Supported | Supported | Not supported | Not supported |
Distilled models | Supported | Not supported | Not supported | Not supported | Not supported |
Valores padrão dos parâmetros
Model | temperature | top_p | repetition_penalty | presence_penalty | max_tokens | thinking_budget |
|---|---|---|---|---|---|---|
deepseek-v4-pro | 1,0 | 1,0 | - | - | 393.216 in total | |
deepseek-v4-pro-us | 1,0 | 1,0 | - | - | 393.216 in total | |
deepseek-v4-flash-0731 | 1,0 | 1,0 | - | - | 393.216 in total | |
deepseek-v4-flash | 1,0 | 1,0 | - | - | 393.216 in total | |
deepseek-v4-flash-us | 1,0 | 1,0 | - | - | 393.216 in total | |
deepseek-v3.2 | 1,0 | 0,95 | - | - | 65.536 | 32.768 |
deepseek-v3.2-exp | 0,6 | 0,95 | 1,0 | - | 65.536 | 32.768 |
deepseek-v3.1 | 0,6 | 0,95 | 1,0 | - | 65.536 | 32.768 |
deepseek-r1 | 0,6 | 0,95 | - | 1 | 16.384 | 32.768 |
deepseek-r1-0528 | 0,6 | 0,95 | - | 1 | 16.384 | 32.768 |
Distilled version | 0,6 | 0,95 | - | 1 | 16.384 | 16.384 |
deepseek-v3 | 0,7 | 0,6 | - | - | 16.384 | - |
- Um hífen (-) indica que o parâmetro não possui valor padrão e não pode ser definido.
- Os modelos deepseek-r1, deepseek-r1-0528 e as versões destiladas não permitem a configuração desses valores de parâmetro.
- "393.216 in total" significa que, para os modelos da série deepseek-v4, max_tokens e thinking_budget compartilham o mesmo limite, somando no máximo 393.216 tokens (comprimento máximo de saída do modelo).
- Para definições dos parâmetros, consulte OpenAI compatible - Chat.
Modelos e faturamento
- Modelos de raciocínio híbrido (use o parâmetro
enable_thinkingpara controlar o modo de raciocínio): deepseek-v4-pro, deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v3.2, deepseek-v3.2-exp e deepseek-v3.1 - Modelos exclusivos de raciocínio (sempre raciocinam antes de responder): deepseek-r1 e deepseek-r1-0528
- Modelos sem raciocínio: deepseek-v3
O deepseek-v4-pro destaca-se em programação, matemática e tarefas gerais. O deepseek-v4-flash-0731 oferece rapidez e custo-benefício. Priorize o uso do deepseek-v4-pro.
Para informações sobre comprimento de contexto e preços dos modelos, acesse o console do Model Studio.
O faturamento baseia-se na quantidade de tokens de entrada e saída.
No modo de raciocínio, a cadeia de pensamento é cobrada como tokens de saída.
FAQ
Posso enviar imagens ou documentos para fazer perguntas?
Os modelos DeepSeek aceitam apenas entrada de texto, não suportando imagens ou documentos. Para entrada de imagens, utilize o modelo Qwen-VL. Para documentos, use o modelo Qwen-Long.
Como visualizar o uso de tokens e a quantidade de chamadas?
Uma hora após a conclusão de uma chamada de modelo, acesse a página de Monitoramento de Modelos e defina os critérios de consulta, como intervalo de tempo e workspace. Em seguida, na área Models, localize o modelo desejado e clique em Monitor na coluna Actions para visualizar as estatísticas de chamadas do modelo. Para mais detalhes, consulte o documento Model monitoring.
Os dados são atualizados a cada hora. Em horários de pico, a atualização pode atrasar em até uma hora.
Códigos de erro
Se ocorrer um erro durante a execução, consulte Error codes para obter uma solução.