Gemini 3.1 ProAPI
Gemini 3.1 Pro — Google's flagship for coding, agents, and cross-modal analysis.
Harga input
$0.70
per 1M tokens
Harga output
$4.20
per 1M tokens
Prompt caching
Kirim cache_control pada prefiks stabil — hit cache ditagih sepersekian dari harga input. Tulis cache ditagih dengan tarif tulis penyedia: 1,25× input di Claude dan GPT-5.6+, harga input di model lain.
Dihitung otomatis sebagai input × 0.1
Untuk prompt di atas 200K token, seluruh permintaan ditagih $1.4 input / $6.3 output per juta token.
Spesifikasi
- ID model
gemini-3-1-pro- Endpoint
POST /v1/chat/completions- Kategori
- Text
- Penyedia
- Jendela konteks (token)
- 1,048,576
- Output maks. (token)
- 65,536
- Kemampuan
- visionfunctionstreamingthinkinglong-context
Kompatibilitas drop-in OpenAI
Arahkan SDK OpenAI kamu ke api.kunavo.com/v1 dan ganti ID model. Tanpa perubahan streaming, tanpa SDK baru.
Lihat dokumenGemini API pricing guideCoba sendiri
Atur KUNAVO_API_KEY dari /app/keys dan jalankan snippet di bawah.
curl https://api.kunavo.com/v1/chat/completions \
-H "Authorization: Bearer $KUNAVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-1-pro",
"messages": [
{"role": "user", "content": "Hello, Gemini 3.1 Pro"}
],
"stream": false
}'Kunavo vs memanggil Google langsung
Model Gemini 3.1 Pro dan responsnya sama persis. Yang diubah gateway adalah akun, SDK, dan tagihan — ini perbandingan jujurnya.
| Kunavo | Google langsung | |
|---|---|---|
| Harga (per 1M tokens) | $0.70 / $4.20 (−65%) | $2.00 / $12.00 |
| Akun | Satu akun Kunavo, kunci dalam 2 menit, isi ulang minimum $10 | Akun Google beserta pengaturan penagihannya sendiri |
| SDK | Tetap pakai OpenAI SDK — ganti base_url, isi model dengan "gemini-3-1-pro" | SDK milik Google, atau lapisan kompatibel-OpenAI bila tersedia |
| Kunci yang sama juga menjangkau | Claude, Gemini, GPT plus model gambar, video, dan audio | Hanya katalog Google sendiri |
| Penagihan | Satu saldo Stripe, bayar sesuai pemakaian, tidak pernah hangus; permintaan gagal tidak ditagih | Faktur terpisah untuk tiap penyedia |
| Batas laju | Kapasitas gateway bersama, tanpa batas kontraktual per akun | Batas tier Google sendiri, dinaikkan lewat riwayat pemakaian atau kontrak |
Pilih Google langsung bila Anda butuh batas laju kontraktual, SLA enterprise, atau fitur khusus penyedia sejak hari pertama. Kunavo cocok bila Anda ingin satu kunci, satu saldo, dan harga per token lebih rendah di semua penyedia.
FAQ
How much does Gemini 3.1 Pro cost?
On Kunavo, Gemini 3.1 Pro is $0.70 per 1M input tokens and $4.20 per 1M output tokens — about 65% under Google's official price. Failed requests are never billed, and it's pay-as-you-go — you only pay for successful calls.
Can I call Gemini 3.1 Pro with the OpenAI SDK?
Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gemini-3-1-pro". Requests and responses are OpenAI-compatible.
What endpoint does Gemini 3.1 Pro use?
Gemini 3.1 Pro is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.
What is Gemini 3.1 Pro good for?
Gemini 3.1 Pro is a text model from Google, with support for vision, function, streaming, thinking, long-context.
What is different from calling Google directly?
The model is the same, at about 65% under Google's list price. What changes is around it: one key and one Stripe balance instead of a Google account with its own billing, the OpenAI SDK with base_url swapped instead of a provider-specific SDK, and the same key also reaching Claude, Gemini, GPT, image, video and audio models. The tradeoff is that gateway capacity is shared — if you need a contractual rate limit or an enterprise SLA on Gemini 3.1 Pro specifically, go direct to Google.
Is Gemini 3.1 Pro cheaper on Kunavo?
Yes — Gemini 3.1 Pro is about 65% under Google's official list price on Kunavo, with no subscription and no minimum monthly spend. You pay per token from a $10 top-up, failed requests are never billed, and the balance never expires.