> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.singularityapi.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.singularityapi.dev/_mcp/server.

# Quickstart

Four steps: create a key, send a request, check the receipt, then go deeper.

## 1. Get an API key

Open the dashboard at `https://app.singularityapi.dev`, go to **API keys**, and click **Create**.

> **Warning**
>
> Your key (`sapi_...`) is shown once, at creation. Copy it somewhere safe — you cannot view it again.

New accounts start with a \$0.00 balance — add credit in the dashboard to make your first request.

## 2. Make your first request

Set `SINGULARITY_API_KEY` in your environment and send a chat completion. The example model here is `deepseek-v4-flash`; see [Models & Pricing](/get-started/models-pricing) for the full catalog.

**`cURL`**

```bash title="cURL"
curl https://api.singularityapi.dev/v1/chat/completions \
  -H "Authorization: Bearer $SINGULARITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Say hello."}]
  }'
```

**`Python`**

```python title="Python"
from openai import OpenAI

client = OpenAI(
    base_url="https://api.singularityapi.dev/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(response.choices[0].message.content)
```

**`JavaScript`**

```javascript title="JavaScript"
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.singularityapi.dev/v1",
  apiKey: "YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Say hello." }],
});
console.log(response.choices[0].message.content);
```

## 3. Check the receipt

Every response carries an `x-singularity-request-id` and an `x-singularity-receipt-id` header. Pull the receipt for the exact tokens, cost, and latency of that request:

**`cURL`**

```bash title="cURL"
curl https://api.singularityapi.dev/v1/receipts/RECEIPT_ID \
  -H "Authorization: Bearer $SINGULARITY_API_KEY"
```

**`Python`**

```python title="Python"
import httpx

api_key = "YOUR_API_KEY"
receipt = httpx.get(
    "https://api.singularityapi.dev/v1/receipts/RECEIPT_ID",
    headers={"Authorization": f"Bearer {api_key}"},
).json()
print(receipt["total_cost_usd"], receipt["usage"], receipt["latency_ms"])
```

**`JavaScript`**

```javascript title="JavaScript"
const apiKey = "YOUR_API_KEY";
const receipt = await fetch(
  "https://api.singularityapi.dev/v1/receipts/RECEIPT_ID",
  { headers: { Authorization: `Bearer ${apiKey}` } },
).then((r) => r.json());
console.log(receipt.total_cost_usd, receipt.usage, receipt.latency_ms);
```

Every answer, on the record.

## 4. Next steps

#### [Models & Pricing](/get-started/models-pricing)

See every model, its limits, and its exact price.

#### [Contracts](/platform/contracts)

Give your calls a permanent, dashboard-controlled model name.

#### [Streaming](/platform/streaming)

Stream responses over standard OpenAI-compatible SSE.

#### [Errors & Rate Limits](/api/errors-rate-limits)

Handle the error envelope and the rate limit.