Quickstart: Your First Request in 5 Minutes
From signup to your first API call — create a key, swap the base_url, pick a model, with minimal working examples for the OpenAI, Claude and Gemini protocols.
1. Create an API key
- Open the signup page — email is enough
- Go to the console → API tokens → create token
- Copy the
sk-key and store it safely (it's shown in full only once)
New accounts include trial credits — enough to run every example below.
2. Know your endpoints
| Protocol | Base URL | Use for |
|---|---|---|
| OpenAI-compatible | https://api.zaimod.com/v1 | Nearly all SDKs, plugins, clients |
| Anthropic-native | https://api.zaimod.com | Full Claude features (thinking, native tools) |
| Gemini-native | https://api.zaimod.com/v1beta/models/{model}:generateContent | Gemini-native features |
When in doubt, use the OpenAI-compatible endpoint — it's the default everywhere.
3. First request
Python
pip install openaifrom openai import OpenAI
client = OpenAI(
api_key="sk-your-zaimod-key",
base_url="https://api.zaimod.com/v1",
)
resp = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Introduce yourself in two sentences."}],
)
print(resp.choices[0].message.content)
print(resp.usage) # token metering for this callNode.js
npm install openaiimport OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ZAIMOD_API_KEY,
baseURL: "https://api.zaimod.com/v1",
});
const res = await client.chat.completions.create({
model: "claude-sonnet-5",
messages: [{ role: "user", content: "Explain API gateways in 3 sentences." }],
});
console.log(res.choices[0].message.content);cURL
curl https://api.zaimod.com/v1/chat/completions \
-H "Authorization: Bearer $ZAIMOD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-lite-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'4. Switching models = switching a string
One endpoint, any vendor — just change model:
- OpenAI:
gpt-4o-mini,gpt-4.1,gpt-5.6-terra - Claude:
claude-sonnet-5,claude-opus-4-7 - Gemini:
gemini-3.1-flash-lite-preview,gemini-3.1-pro-preview - DeepSeek:
deepseek-v4-flash - Chinese vendors:
qwen3.5-plus,doubao-seed-2-0-pro-260215,glm-5.2
Full catalogue: the models page; unit prices: the pricing page.
5. Common parameters
| Parameter | What it does |
|---|---|
stream: true | SSE streaming, typewriter output |
max_tokens | Caps output length — your first cost lever |
temperature | 0–2, lower is more deterministic |
tools | Function calling / tool use |
response_format | {"type": "json_object"} structured output |
Next steps
If something fails, read the response body first: 401 = key problem, 404 = model name typo, 429 = rate limit.