DeepSeek model

R1

DeepSeek: R1. Compară prețurile API, furnizorul, lungimea contextului, capabilitățile, use case-urile, latența și alternativele. Chinese Q&A, general chat. $0.132 / 1M tokens / $0.47 / 1M tokens. 163.8k tokens.

DeepSeekPlatform curatedCatalog
StreamingTool callingJSON modeLong context
Preț input$0.132 / 1M tokens
Preț output$0.47 / 1M tokens
Lungimea contextului163.8k tokens
Output maxim8.2k tokens

Ce este R1 in NextModel?

DeepSeek: R1. Compară prețurile API, furnizorul, lungimea contextului, capabilitățile, use case-urile, latența și alternativele. Chinese Q&A, general chat. $0.132 / 1M tokens / $0.47 / 1M tokens. 163.8k tokens.

Cele mai bune cazuri de utilizare

  • Chinese Q&A
  • general chat

Exemplu compatibil OpenAI

Păstrează stilul SDK OpenAI, trimite base_url către NextModel și folosește ID-ul din catalog deepseek--deepseek-r1.

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.nextmodel.app/v1"
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-r1",
    messages=[{"role": "user", "content": "Hello from NextModel"}]
)

print(resp.choices[0].message.content)

Alternative similare

DeepSeekCatalog

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

$0.038 / 1M tokensInput$0.152 / 1M tokensOutput163.8kContext
Best forChinese Q&A, general chat
RoutingConfigured
StreamingTool callingJSON modeLong context
Platform curatedNextModel gateway catalog (Go origin)
View details
DeepSeekCatalog

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

$0.038 / 1M tokensInput$0.146 / 1M tokensOutput163.8kContext
Best forChinese Q&A, general chat
RoutingConfigured
StreamingTool callingJSON modeLong context
Platform curatedNextModel gateway catalog (Go origin)
View details
DeepSeekCatalog

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

$0.041 / 1M tokensInput$0.149 / 1M tokensOutput163.8kContext
Best forChinese Q&A, general chat
RoutingConfigured
StreamingTool callingJSON modeLong context
Platform curatedNextModel gateway catalog (Go origin)
View details

FAQ

DeepSeek: R1 FAQ