AITOT

Kalkulator

Kalkulator Biaya Embeddings AI

Estimasi biaya embed sekali pakai dan berulang di 9+ provider. Masukkan ukuran corpus, strategi chunk, frekuensi refresh.

Harga diperbarui:

AITOT Embeddings Cost calculator memperkirakan one-time corpus embedding plus recurring re-embed di 9 provider — OpenAI text-embedding-3-small/large, Cohere Embed v4, Voyage 3, Jina v3, BGE-M3, Mistral, Google, Azure.

Untuk corpus 1M dokumen @ 500 token = 500M token. OpenAI text-embedding-3-small: $10. text-embedding-3-large: $65. Cohere Embed v4: $50. Mayoritas bills one-time kecil.

Toggle refresh frequency. Di atas 5B token/bulan, self-hosted BGE-M3 di H100 kalahkan OpenAI.

Termurah · tahun 1

Together · BGE-M3

1024 dim · 8,192 max token

$2

ProviderModel$ / 1M tokenBiaya embed sekaliBiaya bulananTahun 1
TogetherBGE-M3

1024 dim · Self-host open weights for $0

$0.008$0.40$0.14$2
Togetherbge-large-en-v1.5

1024 dim

$0.008$0.40$0.14$2
Fireworksnomic-embed-text-v1.5

768 dim

$0.008$0.40$0.14$2
Jina AIjina-embeddings-v3

1024 dim · configurable

$0.012$0.60$0.21$3
Jina AIjina-embeddings-v4

2048 dim · configurable

$0.018$0.90$0.31$5
OpenAItext-embedding-3-small

1536 dim · configurable

$0.02$1.00$0.35$5
Voyage AIvoyage-4-lite

512 dim · 200M tokens free

$0.02$1.00$0.35$5
Voyage AIvoyage-3-lite

512 dim

$0.02$1.00$0.35$5
Amazon BedrockTitan Embed v2

1024 dim · configurable

$0.02$1.00$0.35$5
Voyage AIvoyage-4

1024 dim · configurable · 200M tokens free

$0.06$3.00$1.05$16
Voyage AIvoyage-3

1024 dim

$0.06$3.00$1.05$16
Cohereembed-english-v3.0

1024 dim

$0.10$5.00$1.75$26
Cohereembed-multilingual-v3.0

1024 dim

$0.10$5.00$1.75$26
Cohereembed-english-light-v3.0

384 dim · Smaller, cheaper at inference

$0.10$5.00$1.75$26
Mistralmistral-embed

1024 dim

$0.10$5.00$1.75$26
Voyage AIvoyage-4-large

1024 dim · configurable · Top MTEB 2026; 200M tokens free

$0.12$6.00$2.10$31
OpenAItext-embedding-3-large

3072 dim · configurable · Matryoshka — truncate to 256/512/1024 without retrain

$0.13$6.50$2.28$34
GoogleGemini Embedding

3072 dim · configurable · Text-only

$0.15$7.50$2.63$39
Voyage AIvoyage-3-large

1024 dim · configurable · Legacy v3; consider voyage-4-large

$0.18$9.00$3.15$47
Voyage AIvoyage-code-3

1024 dim · Optimized for code retrieval

$0.18$9.00$3.15$47
GoogleGemini Embedding 2

3072 dim · configurable · Multimodal: text $0.20, image $0.45, audio $6.50, video $12 per 1M tokens

$0.20$10.00$3.50$52

Frekuensi 0,25 berarti re-embed corpus tiap 4 bulan. Model bertanda "configurable" mendukung pemotongan Matryoshka — dapat menurunkan dimensi tanpa re-embedding.

Yang dilakukan kalkulator ini

9 provider dibandingkan

OpenAI 3-small/large, Cohere v4, Voyage 3, Jina, Mistral, Google, Azure, BGE-M3.

One-time + recurring

Embed cost awal + re-embed cost bulanan terpisah.

Slider refresh frequency

Modelkan seberapa sering re-embed.

Break-even self-host

Bandingkan managed APIs dengan BGE-M3 di H100. Break-even ~2B token/bulan.

Truncation dimensi

Matryoshka models izinkan truncate dimensions.

Modeling query tokens

Embedding cost simetris — query tokens hitung juga.

Perbandingan cepat

Biaya embed corpus 500M tokens + 50M query tokens/bulan

ProviderOne-timeBulanan$/1M tokens
Jina v3$9$0.90$0.018
Voyage 3 Lite$10$1$0.02
OpenAI text-embed-3-small$10$1$0.02
Cohere Embed v4 Light$50$5$0.10
Voyage 3 Large$65$6.50$0.13
OpenAI text-embed-3-large$65$6.50$0.13
Self-host BGE-M3 (H100)~$45~$1,300flat /bulan

Self-host menang di atas ~2B token/bulan total throughput.

Cara menggunakan kalkulator

Hitung one-time corpus embedding + recurring re-embed di 9 provider.

  1. 1

    Masukkan ukuran corpus

    Token di corpus penuh. Dokumen × token/dok.

  2. 2

    Set refresh frequency

    0 = tidak pernah, 1 = bulanan, 4 = mingguan.

  3. 3

    Tambah query volume

    Query tokens bulanan.

  4. 4

    Bandingkan dan pilih

    Sort berdasarkan biaya bulanan. Self-host BGE-M3 menang >2B token/bulan.

Kenapa pakai kalkulator ini

  • ✓9 provider diperbarui bulanan
  • ✓One-time + recurring split
  • ✓Break-even self-host dimodelkan
  • ✓Matryoshka truncation
  • ✓Query tokens termasuk
  • ✓Tanpa login

Pertanyaan yang sering diajukan

Provider embeddings termurah 2026?+
Untuk embed corpus sekali: Voyage 3 Lite di $0.02/M token. OpenAI text-embedding-3-small di $0.02/M. Cohere Embed v4 Light di $0.10/M. Jina v3 di $0.018/M. BGE M3 self-host efektif gratis di skala. Untuk kualitas+harga, OpenAI text-embedding-3-large di $0.13/M.
Berapa biaya embed corpus 1M dokumen?+
Di 500 token/dokumen rata-rata × 1M dokumen = 500M token. OpenAI text-embedding-3-small: $10. OpenAI text-embedding-3-large: $65. Cohere Embed v4: $50. Mayoritas embed sekali kecil — yang scale adalah re-embedding recurring dari update dokumen.
Seberapa sering re-embed corpus?+
Data statis (legal, ilmiah): tahunan atau perubahan schema. Dokumen sering update: re-embed delta mingguan hanya chunks berubah. Jangan batch-re-embed data tak berubah — pakai change-detection di hash atau last-modified.
1536 atau 3072 dimensi embeddings?+
1536 (default OpenAI) cukup untuk 90% use case. 3072 menang di retrieval long-context (legal, ilmiah). 1536 storage 2× lebih murah dan query lebih cepat. Pakai Matryoshka truncation untuk test 512 → 1024 → 1536 — gain sering plateau di 1024.
Self-host BGE-M3 benar lebih murah dari OpenAI embeddings?+
Di atas ~5B token embedded/bulan, ya. BGE-M3 di satu H100 ($1.85–$2.50/jam) jalankan ~2M token/detik — itu 5T token/bulan di $1.3k/bulan flat. OpenAI text-embedding-3-large di $0.13/M = $650 per miliar token, jadi self-host menang di atas ~2B token/bulan.
Embeddings dihitung per token atau per dokumen?+
Selalu per input token. Kalkulator konversi doc count × token/doc rata-rata jadi token billable. OpenAI, Cohere, Voyage, Jina semua charge per juta input token tak peduli dimensi. Storage terpisah (dibayar ke vector DB).