API
API cailagOpenAI API
cailagAIDeepSeekGLMMoonshotMiniMax35+
- OpenAI APIbase_url
- 88
- 3
Base URL
https://cailag.xin/v1Authorization: Bearer YOUR_API_KEYContent-Type: application/json
Python
Pythonfrom openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://cailag.xin/v1"
)
response = client.chat.completions.create(
model="deepseek-chat",
messages=[
{"role": "system", "content": "AI"},
{"role": "user", "content": "Python"}
],
temperature=0.7,
max_tokens=2000
)
print(response.choices[0].message.content)
cURL
cURLcurl https://cailag.xin/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-chat",
"messages": [
{"role": "system", "content": "AI"},
{"role": "user", "content": "Python"}
],
"temperature": 0.7,
"max_tokens": 2000
}'
Node.js
Node.jsimport OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://cailag.xin/v1'
});
const response = await client.chat.completions.create({
model: 'deepseek-chat',
messages: [
{ role: 'system', content: 'AI' },
{ role: 'user', content: 'Python' }
],
temperature: 0.7,
max_tokens: 2000
});
console.log(response.choices[0].message.content);
(Chat Completions)
cailagAPI
POST
https://cailag.xin/v1/chat/completions
| model | string | ID deepseek-chatqwen-plusglm-4-plus |
|
| messages | array | rolesystem/user/assistant content |
|
| temperature | float | 0-20.7 | |
| top_p | float | 0-1temperature | |
| max_tokens | integer | token | |
| stream | boolean | false | |
| stop | string/array | 4 | |
| presence_penalty | float | -2.02.0 | |
| frequency_penalty | float | -2.02.0 | |
| n | integer | 1 | |
| user | string |
messages
| role | string | systemuserassistant |
| content | string | |
| name | string |
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1700000000,
"model": "deepseek-chat",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "AI"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 25,
"completion_tokens": 42,
"total_tokens": 67
}
}
"stream": true
Pythonfrom openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://cailag.xin/v1"
)
stream = client.chat.completions.create(
model="deepseek-chat",
messages=[{"role": "user", "content": ""}],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
Server-Sent Events (SSE) chunk
delta chunk finish_reason "stop"
GET
https://cailag.xin/v1/models
cURLcurl https://cailag.xin/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"
cailag35+
DeepSeek
deepseek-chat
V4-Flash
¥0.81 / ¥1.62
deepseek-reasoner
V4-Flash
¥0.81 / ¥1.62
deepseek-v4-flash
V4 Flash
¥0.81 / ¥1.62
deepseek-v4-flash-none
V4 Flash
¥0.81 / ¥1.62
deepseek-v4-flash-max
V4 Flash
¥0.81 / ¥1.62
deepseek-v4-pro
Pro
¥2.41 / ¥4.83
deepseek-v4-pro-none
Pro
¥2.41 / ¥4.83
deepseek-v4-pro-max
Pro
¥2.41 / ¥4.83
qwen-turbo
¥0.24 / ¥0.48
qwen-plus
¥0.68 / ¥1.70
qwen-max
¥2.40 / ¥17.40
qwen-long
¥0.50 / ¥3.63
qwen-math-turbo
¥0.50 / ¥2.08
qwen3-235b-a22b
Qwen3 MoE
¥2.00 / ¥14.50
qwen-vl-max
¥1.60 / ¥4.00
qwen-vl-plus
¥0.80 / ¥2.00
qwen3-vl-plus
Qwen3
¥3.00 / ¥21.75
qwen3-vl-max
Qwen3
¥3.40 / ¥8.50
qwen-coder-plus
¥0.85 / ¥8.50
GLM
glm-4-flash
glm-4-flashx
¥0.08 / ¥0.08
glm-4-air
¥0.40 / ¥0.40
glm-4-long
¥0.85 / ¥0.85
glm-4-plus
¥4.26 / ¥4.26
glm-4.7-flashx
4.7
¥0.43 / ¥2.55
glm-4.5-air
4.5
¥0.68 / ¥1.70
glm-4.7
4.7
¥1.70 / ¥6.80
glm-5
GLM-5
¥3.41 / ¥15.34
glm-5-turbo
GLM-5
¥4.26 / ¥18.73
glm-5.1
GLM-5.1
¥5.11 / ¥20.44
glm-z1-air
¥0.45 / ¥0.45
glm-z1-flashx
¥0.09 / ¥0.09
glm-4v-plus
¥3.61 / ¥3.61
glm-4.6v
¥0.90 / ¥2.70
glm-4.6v-flashx
¥0.13 / ¥1.35
step-3.5-flash
3.5
¥3.40 / ¥6.80
step-3.5-mini
3.5
step-3.5-pro
3.5
step-2-flash
Step-2
step-2-mini
Step-2
step-2-pro
Step-2
step-1.5v-flash
1.5
step-1.5v-mini
1.5
step-1-flash
Step-1
step-1-mini
Step-1
hunyuan-a13b
A13B
qwen3.5-397b
Qwen3.5 397B MoE
ling-flash-2.0
Flash 2.0
ling-mini-2.0
Mini 2.0
deepseek-v4-pro-sf
DeepSeek V4 Pro()
seed-oss-36b
Seed OSS 36B
step-3.5-flash-sf
Step-3.5 Flash()
deepseek-v3.2-pro
DeepSeek V3.2 Pro
Moonshot
moonshot-v1-8k
8K
moonshot-v1-32k
32K
moonshot-v1-128k
128K
k2.5
Kimi K2.5
k2.6
Kimi K2.6
MiniMax
MiniMax-M2.7
M2.7
MiniMax-M2.5
M2.5
MiniMax-M2
M2
MiniMax-Text-01
Text-01
Doubao
doubao-seed-2.0-pro
Seed 2.0
doubao-seed-2.0-code
Seed 2.0
doubao-seed-1.8
Seed 1.8
doubao-seed-2.0-lite
Seed 2.0
doubao-seed-2.0-mini
Seed 2.0
doubao-seed-character
doubao-seed-code
doubao-seed-1.6-lite
Seed 1.6
API
401
API Key Authorization
403
400
404
APIID
429
500
502
503
{
"error": {
"message": "Incorrect API key provided",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}
cailagtoken
- tokensystem prompt
- token
8
| glm-4-flash | ||
| 8 | glm-4-flashx, qwen-turbo | |
| 8.5 | qwen-plus, glm-4.7 | |
| / | 8.5 | glm-5, deepseek-v4-pro |
| / | 9 | glm-4v-plus, glm-4.6v |
- "¥XX""¥XX"
- 2020%
deepseek-chat
# 1000 tokens 500 tokens
= 1000 / 1,000,000 × ¥0.81 = ¥0.00081
= 500 / 1,000,000 × ¥1.62 = ¥0.00081
= ¥0.00162
#
= 1000/1M × ¥1.00 + 500/1M × ¥2.00 = ¥0.002
= ¥0.002 - ¥0.00162 = ¥0.00038 (19%)
cailagOpenAI APIAPI
Cursor
AI
# Cursor
1. Settings → Models
2. OpenAI API Key cailag API Key3. Override OpenAI Base URL https://cailag.xin4. deepseek-chatqwen-plus 5. Continue (VS Code / JetBrains)
VS CodeJetBrainsAI
// Continue config.json { "models": [ { "title": "cailag DeepSeek", "provider": "openai", "model": "deepseek-chat", "apiBase": "https://cailag.xin/v1", "apiKey": "sk-" }, { "title": "cailag Qwen", "provider": "openai", "model": "qwen-plus", "apiBase": "https://cailag.xin/v1", "apiKey": "sk-" } ]}ChatBox
AIWindows/Mac/Linux
# ChatBox 1. → OpenAI2. API Host https://cailag.xin3. API Key cailag 4. Open WebUI
AI
# Open WebUI 1. → Settings → Connections2. OpenAI API 3. Base URL: https://cailag.xin/v14. API Key: sk-5. cailag Dify / FastGPT
AIAI
# Dify 1. → → OpenAI-API2. API Base URL: https://cailag.xin/v13. API Key: sk-4. deepseek-chat / qwen-plus \# FastGPT 1. CHAT_API_KEY=sk- OPENAI_BASE_URL=https://cailag.xin/v1LangChain / LlamaIndex
Python/JS AIAI
# LangChain Python rom langchain_openai import ChatOpenAI\llm = ChatOpenAI( model="deepseek-chat", openai_api_base="https://cailag.xin/v1", openai_api_key="sk-")
esponse = llm.invoke("")print(response.content)\# LlamaIndex Python rom llama_index.llms.openai import OpenAI\llm = OpenAI( model="qwen-plus", api_base="https://cailag.xin/v1", api_key="sk-")Obsidian (Text Generator)
ObsidianAI
# Obsidian Text Generator 1. Text Generator 2. Settings → API Base URL: https://cailag.xin/v13. API Key: sk-4. GitHub Copilot
GitHub Copilot
# copilot-gpt4-service 1. copilot-gpt4-service2. API_TYPE=openai OPENAI_API_KEY=sk- OPENAI_API_BASE=https://cailag.xin/v13. VS Code 4. cailag CopilotCherry Studio
AI
# Cherry Studio 1. → 2. OpenAI 3. API https://cailag.xin4. API Keysk-5. deepseek-chat / qwen-plus 6. Lobe Chat
AI
# Lobe Chat 1. → → OpenAI2. API https://cailag.xin/v13. API Keysk-4. \# OPENAI_API_KEY=sk-OPENAI_PROXY_URL=https://cailag.xin/v1AionUI
AI
# AionUI 1. API 2. 3. API Base URLhttps://cailag.xin/v14. API Keysk-5. OpenCat
iOS/MacAIAPI
# OpenCat 1. → API2. OpenAI 3. API Proxyhttps://cailag.xin/v14. API Keysk-5. AMA
AI
# AMA 1. → 2. OpenAI 3. Base URLhttps://cailag.xin/v14. API Keysk-5.
API Key
→ → API Key
HTTPPythonNode.jsSDKOpenAI SDKcURLJavaGoPHPREST API
OpenAI
1. base_url https://cailag.xin/v1
2. api_key cailagAPI Key
API403
"stream": true OpenAIServer-Sent Events (SSE)
1. API Key
2.
3. ID
4. 502
5. QQ(1098023544)
HTTPS
SLA 226894892@qq.com 198-9681-5373