If this is useful, a ❤️ helps others find it.
Everything I keep looking up when building with Gemini — in one place.
Models (2026)
| Model | Context | Best for |
|---|---|---|
| gemini-2.5-flash-preview | 1M tokens | General use, thinking, fast |
| gemini-2.5-pro-preview | 1M tokens | Complex reasoning, best quality |
| gemini-1.5-flash | 1M tokens | Stable, production-ready |
| gemini-1.5-pro | 2M tokens | Longest context |
| gemini-2.0-flash-lite | 1M tokens | Lowest latency, highest volume |
For most use cases: gemini-2.5-flash-preview
Free Tier Limits (Google AI Studio)
| Model | RPM | TPM | RPD |
|---|---|---|---|
| Gemini 2.5 Flash Preview | 10 | 250,000 | 500 |
| Gemini 1.5 Flash | 15 | 1,000,000 | 1,500 |
| Gemini 1.5 Pro | 2 | 32,000 | 50 |
| Gemini 2.0 Flash Lite | 30 | 1,000,000 | 1,500 |
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day
Basic Request (REST)
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview:generateContent \
-H "Content-Type: application/json" \
-H "x-goog-api-key: YOUR_API_KEY" \
-d '{
"contents": [{"parts": [{"text": "Your prompt here"}]}]
}'
With System Prompt
{
"system_instruction": {
"parts": [{"text": "You are a helpful assistant."}]
},
"contents": [
{"role": "user", "parts": [{"text": "Your prompt here"}]}
]
}
Streaming
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview:streamGenerateContent \
-H "Content-Type: application/json" \
-H "x-goog-api-key: YOUR_API_KEY" \
-d '{"contents": [{"parts": [{"text": "Tell me a story"}]}]}'
In Rust (reqwest)
use reqwest::Client;
use serde_json::json;
pub async fn call_gemini(prompt: &str, api_key: &str) -> Result {
let client = Client::new();
let url = format!(
"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview:generateContent?key={}",
api_key
);
let body = json!({
"contents": [{"parts": [{"text": prompt}]}]
});
let res = client.post(&url).json(&body).send().await?;
let data: serde_json::Value = res.json().await?;
let text = data["candidates"][0]["content"]["parts"][0]["text"]
.as_str()
.unwrap_or("")
.to_string();
Ok(text)
}
Error Codes
| Code | Meaning | Fix |
|---|---|---|
| 400 | Bad request / token limit | Shorten prompt |
| 403 | Invalid API key | Check key |
| 429 | Rate limit hit | Wait and retry |
| 500 | Internal error | Retry |
| 503 | Overloaded | Wait 2s, retry once |
Token Counting (rough guide)
- 1 token ≈ 4 characters in English
- 1 token ≈ 2–3 characters in Japanese
- 100 lines of logcat ≈ 3,000–5,000 tokens
- 1 page of PDF text ≈ 500–800 tokens
Get a Free API Key
- Go to aistudio.google.com
- Sign in with Google
- Click "Get API Key"
- Done — no credit card required
Hiyoko PDF Vault → https://hiyokoko.gumroad.com/l/HiyokoPDFVault
X → @hiyoyok
