Vertex API is a drop-in OpenAI replacement. If your code works with OpenAI, it works with us — just change the base URL.
Sign up at api.vertexapi.net — you'll get $1 free credit instantly. No credit card required.
Go to Dashboard → Tokens → Create Token, copy your sk-... key.
Replace https://api.openai.com/v1 with https://api.vertexapi.net/v1 and use your new key. That's it.
from openai import OpenAI
client = OpenAI(
api_key="sk-your-key-here",
base_url="https://api.vertexapi.net/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
max_tokens=100
)
print(response.choices[0].message.content)
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'sk-your-key-here',
baseURL: 'https://api.vertexapi.net/v1',
});
const response = await client.chat.completions.create({
model: 'deepseek-v4-flash',
messages: [{ role: 'user', content: 'Hello!' }],
max_tokens: 100,
});
console.log(response.choices[0].message.content);
curl https://api.vertexapi.net/v1/chat/completions \
-H "Authorization: Bearer sk-your-key-here" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello!"}],
"max_tokens": 100
}'
| Model | Tier | Input / 1M | Output / 1M | Best For |
|---|---|---|---|---|
| deepseek-v4-flash | Standard | $0.40 | $1.20 | Fast & cheap, coding, chat |
| deepseek-v4-pro | Standard | $1.00 | $2.50 | General purpose, reasoning |
| MiniMax-M2.7 | Standard | $0.80 | $3.00 | Agent tasks, fast responses |
| MiniMax-M3 | Pro | $1.50 | $6.00 | Complex reasoning, long context |
| kimi-k2.6 | Pro | $2.50 | $8.00 | 256K context, agent workflows |
| qwen-max | Enterprise | $4.00 | $12.00 | Complex reasoning, long docs |
| glm-5v-turbo | Enterprise | $3.00 | $10.00 | Multi-modal, agent tasks |
| Tier | Access | Free Credit | How to Unlock |
|---|---|---|---|
| Standard | DeepSeek V4-Flash, V4-Pro, MiniMax M2.7 | $1 on sign-up | Automatic |
| Pro | All Standard + MiniMax M3, Kimi K2.6 | — | Top up $10+ |
| Enterprise | All 7 models + Qwen-Max, GLM-5V-Turbo | — | Top up $50+ |
Vertex API supports streaming responses. Just add "stream": true to your request:
stream = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")