OpenAI
GPT-4o
gpt-4oKonteks
128K
Input / 1M token
$2.50
Output / 1M token
$10.00
Rumus weighted token
1× provider × 4× tier
Tentang model ini
GPT-4o
OpenAI's GPT-4o — multimodal flagship combining strong general intelligence with vision, audio (via separate endpoint), and reliable tool calling. The default safe choice for new builds.
Rilis
2024-05
Batas data latih
2023-10
Parameter
Not disclosed
Paling cocok untuk
Kasus penggunaan
- ✓General-purpose chat
- ✓Vision + document understanding
- ✓Agentic workflows with function calling
- ✓Multilingual customer support
Kelebihan
Yang dikerjakan dengan baik
- ●Reliable tool calling + structured output
- ●Strong multilingual quality
- ●Vision built in
- ●128K context window
- ●Battle-tested at production scale
Keterbatasan
Pahami trade-off-nya
- !Trails newer models on coding (Claude Sonnet 4.6, Qwen 2.5 Coder)
- !Knowledge cutoff trails competitors
- !Premium pricing relative to open-weights at similar quality
Benchmark
Skor terpublikasi
Skor dari model card resmi dan leaderboard publik. Makin tinggi makin baik kecuali disebutkan lain.
| Benchmark | Skor | Mengukur |
|---|---|---|
| MMLU | 88.7 | General knowledge across 57 subjects |
| HumanEval | 90.2 | Python code generation, pass@1 |
| MATH | 76.6 | Mathematics, mixed difficulty |
| GPQA | 53.6 | Graduate-level science questions |
Contoh kode
Chat completion dengan GPT-4o
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted token
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Paket Pro: 20 jt weighted token/bulan. Multiplier gabungan 4×: 5,000,000 raw token tersedia.
Alternatif
Model serupa di katalog kami
Beban kerja yang cocok dengan GPT-4o sering cocok dengan ini juga. Bandingkan benchmark dan harga sebelum menetapkan default.