GPT
GPT Text
Model ID: tranhieu13102003/gpt-6-astra
Keluarga model
GPT
Context
Tidak diperbarui
Input / 1M token
3000 Rp
Tingkat cache
53.5%
Jumlah request
3.3K
Berhasil
92.9%
Token
202.41M
Uptime 60.71%
24 jam laluSekarang
7 hari laluSekarang
Observed token response speed
Up to 500 recent requests with a measured response time
500 recent requests
Observed output speed14.1 tok/s
Response time P5011,804 ms
Response time P9547,528 ms
Samples500
Observed output speed: 16.9 tok/s · Output: 103 token · Response time: 6.1 s · 16 requests
Up to 500 recent requests with a measured response time08/11/2026 - 22:27:42
Response similarity to the reference model
The percentage reflects similarity between tested responses and reference data; it does not determine whether a model is genuine or fake.
Latest result: High matchReference data updated: 27/10/2026 - 14:11:00 · gpt-6-astra
Direct comparisons1
direct high-match checks1
Direct results for this model
Included in this model’s score
Check with my API key

Daftar harga

Input / 1M token
3000 Rp
Output / 1M token
10000 Rp
Biaya minimum / request
20 Rp
Prompt Cache 53.5%
Cache read / 1M token
1000 Rp
Cache write / 1M token
3000 Rp

Prompt berulang di-cache — pembacaan ulang jauh lebih murah daripada input, otomatis saat dipanggil via API.

Riwayat perubahan harga

Tingkat harga yang pernah diterapkan. Baris berlabel "saat ini" adalah harga yang sedang berlaku.

Sebelumnya Sejak 18/10/2026 - 14:40:29
Input / 1M token4000 Rp Output / 1M token20000 Rp Biaya minimum / request30 Rp Cache read / 1M token2000 Rp Cache write / 1M token10000 Rp
Sebelumnya Sejak 22/10/2026 - 12:31:53
Input / 1M token1500 Rp Output / 1M token7500 Rp Biaya minimum / request30 Rp Cache read / 1M token1200 Rp Cache write / 1M token6000 Rp
Saat ini Sejak 05/11/2026 - 04:06:25
Input / 1M token3000 Rp Output / 1M token10000 Rp Biaya minimum / request20 Rp Cache read / 1M token1000 Rp Cache write / 1M token3000 Rp
Estimasi biaya
Estimasi total 0 Rp
Rata-rata / request 0 Rp

Estimasi berdasarkan harga yang dipublikasikan. Jika ada cache biasanya lebih murah.

Endpoint yang didukung
https://api.xah.io/v1/chat/completions
https://api.xah.io/v1/completions
https://api.xah.io/v1/messages
https://api.xah.io/v1/responses
https://api.xah.io/v1beta/models/tranhieu13102003/gpt-6-astra:generateContent
https://api.xah.io/api/chat
https://api.xah.io/api/generate
Metode POST · application/json
Autentikasi Bearer token (API key)
Jenis API Text

Bagikan

curl 'https://api.xah.io/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "tranhieu13102003/gpt-6-astra",
    "messages": [
        {
            "role": "user",
            "content": "Halo, kamu siapa?"
        }
    ]
}'
// Node.js / Browser
const res = await fetch('https://api.xah.io/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    "model": "tranhieu13102003/gpt-6-astra",
    "messages": [
        {
            "role": "user",
            "content": "Halo, kamu siapa?"
        }
    ]
})
});
const data = await res.json();
console.log(data);
import json, requests

url = 'https://api.xah.io/v1/chat/completions'
headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
}
payload = json.loads("{\n    \"model\": \"tranhieu13102003/gpt-6-astra\",\n    \"messages\": [\n        {\n            \"role\": \"user\",\n            \"content\": \"Halo, kamu siapa?\"\n        }\n    ]\n}")

res = requests.post(url, headers=headers, json=payload, timeout=120)
print(res.status_code, res.json())
{
    "model": "tranhieu13102003/gpt-6-astra",
    "messages": [
        {
            "role": "user",
            "content": "Halo, kamu siapa?"
        }
    ]
}

Coba cepat

Kirim prompt dengan API key Anda — memakai kredit sungguhan, hasilnya stream langsung kembali.

Ulasan & komentar
★ 3.0 / 3 ulasan
Memuat ulasan...
Hubungi Dukungan
Kami selalu siap membantu Anda