DeepSeek V3.2
DeepSeek V3.2 by DeepSeek, through an OpenAI-compatible chat completions API.
deepseek-v3.2获取 API 密钥价格 美元 / 每百万 token
| Token | 每 100 万 token |
|---|---|
| 输入 | $0.257 |
| 缓存输入 | $0.257 |
| 缓存写入(5 分钟) | $0.257 |
| 缓存写入(1 小时) | $0.257 |
| 输出 | $0.3855 |
推理 token 按输出计费。每个回答的 usage 中都带有 cost_usd,即从你的余额中扣除的金额;没有得到回答的请求费用为 $0.00。
请求
curl https://api.revana.si/v1/chat/completions \
-H "Authorization: Bearer $REVANA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v3.2","messages":[{"role":"user","content":"Write a haiku about routing."}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.revana.si/v1", api_key=os.environ["REVANA_API_KEY"])
reply = client.chat.completions.create(
model="deepseek-v3.2",
messages=[{"role": "user", "content": "Write a haiku about routing."}],
)
print(reply.choices[0].message.content)任意 OpenAI SDK 都可使用:把 base URL 设为 https://api.revana.si/v1。流式输出、工具调用等内容见 chat completions 文档。
详情
deepseek-v3.2POST /v1/chat/completions1 条线路
目前只有一条线路。没有得到回答的请求不会扣费。
About the DeepSeek V3.2 API
How much does the DeepSeek V3.2 API cost?
DeepSeek V3.2 costs $0.257 per million input tokens, $0.257 per million cached input tokens and $0.3855 per million output tokens on Revana. You pay from prepaid credit for the tokens each request used, with no subscription or minimum.
How do I call DeepSeek V3.2 from code?
Use any OpenAI SDK with base URL https://api.revana.si/v1 and your Revana API key, and set model to "deepseek-v3.2". POST /v1/chat/completions takes the OpenAI request body, streamed or not.
请求失败了会怎样?
没有得到回答的请求不产生任何费用。
Is DeepSeek V3.2 on Revana the same model?
是的。Revana 会把你的请求原样传给 DeepSeek 的模型,并以 OpenAI 格式返回它的回答,以及它报告的用量和该请求的费用。
DeepSeek 的更多模型
- DeepSeek R1 每 100 万 token 输入 $0.56 / 输出 $2.24
- DeepSeek V4 Flash 每 100 万 token 输入 $0.4286 / 输出 $1.2857
- DeepSeek V4 Pro 每 100 万 token 输入 $0.396 / 输出 $1.188
- DeepSeek V4.1 Flash 每 100 万 token 输入 $0.09 / 输出 $0.36