---
title: Gemini API Quickstart
description: "Gemini API quickstart: make your first call through apiToken.sale with curl or the Google GenAI SDK — native generateContent, SSE streaming, 50% off."
url: https://apitoken.sale/docs/learn/gemini-api-quickstart
language: en
---

# Gemini API quickstart: first call with curl and the Google GenAI SDK

This Gemini API quickstart gets a first working call done in minutes: one curl against the native generateContent route, then the same call from the official Google GenAI SDK in Python or JavaScript. Only the base URL and the key header change — supported requests keep Google's own request shapes, streaming and usage metadata.

## One endpoint, the native Gemini protocol

To make your first Gemini API call through apiToken.sale, keep the Google protocol exactly as documented and change only two values: the base URL becomes https://router.apitoken.sale and the key is your apiToken.sale key, sent as the x-goog-api-key header. Every request and response keeps the native generateContent shape, so Google's documentation and SDK samples apply to the models and fields this endpoint supports. A few Google features are not available here: cachedContent and external file URIs are rejected (send files as inlineData), and the model list is limited to the published catalogue — the error table below lists each case.

One key and one prepaid balance cover every supported provider — Gemini alongside Claude and GPT. Gemini usage is metered at official Google token rates, and a flat 50% discount is applied before the cost is drawn from your balance. No Google Cloud project or billing account is involved on your side.

> For Antigravity CLI, use the one-command setup: curl -fsSL https://apitoken.sale/setup/connect.sh | bash. On Windows PowerShell use irm https://apitoken.sale/setup/connect.ps1 | iex. It installs the native agy command and imports every Gemini model enabled for your key. No Google sign-in is needed.

## Create the key and list your catalog

1. Create a free apiToken.sale account and open the dashboard — no approval step or waitlist.
2. Generate one API key. It looks like sk-pool-… and works for Gemini, Claude and GPT alike.
3. Top up any whole-dollar amount by card or crypto; the prepaid balance does not expire.
4. Export the key as APITOKEN_API_KEY, then list the models your key can actually call:

```
curl https://router.apitoken.sale/v1beta/models \
  -H "x-goog-api-key: $APITOKEN_API_KEY"
```

Pick an explicit model ID from that response. gemini-3.6-flash is the right default for a first text call; a client library's built-in default may not be in the gateway catalog, and the router only serves the IDs it lists.

## First call: generateContent with curl

```
curl https://router.apitoken.sale/v1beta/models/gemini-3.6-flash:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Reply with exactly: connected"}]}]}'
```

The response is the standard Google shape: read candidates[0].content.parts and join the text parts. The same JSON carries usageMetadata with prompt, candidate and total token counts, so token- and cost-tracking code works from the very first call.

Before sending a large prompt, call :countTokens on the same model path. It returns a token count without generating anything — a free input estimate before you spend on generation.

## Stream tokens with streamGenerateContent

```
curl "https://router.apitoken.sale/v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse" \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Count from one to five"}]}]}'
```

The ?alt=sse query switches the response to server-sent events: each event is one incremental chunk in the same candidate structure, and the terminal event carries the aggregate usageMetadata. In the SDKs the same route is reached through generate_content_stream in Python and generateContentStream in JavaScript.

Stream anything user-facing so the first tokens render immediately. For batch jobs where only the final text matters, plain generateContent is simpler to parse and retry.

## Official SDKs: Python and JavaScript

```
import os
from google import genai
from google.genai import types

client = genai.Client(
    api_key=os.environ["APITOKEN_API_KEY"],
    http_options=types.HttpOptions(base_url="https://router.apitoken.sale"),
)

response = client.models.generate_content(
    model="gemini-3.6-flash",
    contents="Reply with exactly: connected",
)
print(response.text)
```

```
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.APITOKEN_API_KEY,
  httpOptions: { baseUrl: "https://router.apitoken.sale" },
});

const response = await ai.models.generateContent({
  model: "gemini-3.6-flash",
  contents: "Reply with exactly: connected",
});
console.log(response.text);
```

- Pass the bare base URL https://router.apitoken.sale; do not append /v1beta in SDK configuration.
- Pass a concrete model ID such as gemini-3.6-flash — never rely on a client default.
- Keep APITOKEN_API_KEY in the environment rather than in source code.

> If every SDK request returns 404, check the request path for a doubled /v1beta/v1beta segment. The SDK appends its API version itself; configuring the host with /v1beta already included produces the doubled path.

## What the first calls cost

Gemini calls settle at the exact official Google rate legs — input, cached input and output — and the flat 50% discount is applied on top. Post-discount prices per 1M tokens for the common text models:

| Model | Input / cached / output per 1M | Good first job |
| --- | --- | --- |
| gemini-3.6-flash | $0.375 / $0.0375 / $1.875 | Everyday coding, chat and agents |
| gemini-3.1-flash-lite | $0.125 / $0.0125 / $0.75 | Classification, extraction, routing |
| gemini-2.5-flash-lite | $0.05 / $0.005 / $0.20 | Cheapest high-volume text |
| gemini-3.1-pro-preview | $1 / $0.10 / $6 | Hardest reasoning and review |

[Full Gemini rate card, including long-context rates](/docs/learn/gemini-api-pricing)

[Every supported model ID and price](/models)

## Troubleshooting the first response

| Status | Likely cause | Fix |
| --- | --- | --- |
| 400 | Missing or wrong x-goog-api-key (INVALID_ARGUMENT, reason API_KEY_INVALID), or a field this endpoint cannot honour (FILE_URI_UNSUPPORTED / CACHED_CONTENT_UNSUPPORTED) | Re-check the key and header; send files as inlineData; omit cachedContent |
| 404 | Doubled /v1beta, or a model ID not in the catalog | Pass the bare host; pick an ID from GET /v1beta/models |
| 402 FAILED_PRECONDITION | Prepaid balance exhausted — HTTP 402, not RESOURCE_EXHAUSTED and not 429 | Top up any whole-dollar amount in the dashboard |

Do not send Authorization: Bearer or the Anthropic x-api-key header on the native Gemini routes — x-goog-api-key is the only credential they accept. Because the wire format is unchanged, reverting to Google's own endpoint later is a one-line base-URL change.

[Choose between Pro, Flash and Flash-Lite](/docs/learn/gemini-pro-vs-flash-vs-flash-lite)

## Frequently asked questions

### Does the official Google GenAI SDK work with apiToken.sale?

Yes. Set HttpOptions(base_url) in Python or httpOptions.baseUrl in JavaScript to https://router.apitoken.sale and pass the apiToken.sale key; request and response shapes stay native.

### Which header authenticates Gemini API requests?

x-goog-api-key carrying your sk-pool key. The native Gemini routes do not accept Authorization: Bearer or the Anthropic x-api-key header.

### How do I stream Gemini output?

Call /v1beta/models/{model}:streamGenerateContent?alt=sse with x-goog-api-key, or use the SDK's generate_content_stream / generateContentStream method. The terminal SSE event carries the aggregate usageMetadata.

### Why does a doubled /v1beta return 404?

The Google SDK appends its API version to the configured host. Configure only the bare host so the final request contains exactly one /v1beta segment.

### Which Gemini model should I call first?

Start with gemini-3.6-flash for general text and coding work. Move bulk classification to a Flash-Lite model and the hardest reasoning to gemini-3.1-pro-preview.

### Is countTokens free to call?

Yes. Calling :countTokens on the model path returns a token count without generating, so you can estimate input size before paying for a generation.

---
Get a key: https://apitoken.sale/register
More guides: https://apitoken.sale/docs/learn