Independent

Apodex 1.1Terbuka

Specialized open-weight coding and reasoning model based on optimized architecture.

#765dirilis 20 Jul 2026·Open Weights·72B
text128K ctx
Penyedia APIJalankan Model →Peringkat
Inteligensi
0.0 #765
Tingkat 100% teratas
Kecepatan output
145 t/s
ITL 6.9 ms/tok
Harga gabungan (3:1)
$0.35 /1M
Input $0.2/M · Output $0.8/M
Konteks
128K
≈ 328 halaman A4 · output maks 16,384

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Apodex 1.1
Claude Mythos Preview (#1)
Average (68)
Coding (63)Mathematics (61)Hard Science (GPQA) (62)Agentic & Tool Use (63)Knowledge (MMLU) (65)Vision / Multimodal (25)

Sumbu radar diaproksimasi dari skor kategori jika pengukuran benchmark langsung tidak tersedia — lihat Metodologi.

Kelebihan & Trade-off

Di mana ia menang

  • Open weights — self-host, fine-tune and audit with no vendor lock-in
  • 145 tok/s output — fast enough for real-time agents
  • Very low blended price — $0.35/1M mixed tokens
  • Cheap prompt-cache reads at $0.02/1M

Kasus Penggunaan Killer

SWE-bench agents
Issue-to-PR resolution across multi-file repos — refactor, test and verify autonomously.

Quickstart Developer & API

Atur HF_TOKEN dulu — dapatkan kunci API
curl https://router.huggingface.co/v1/chat/completions \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "content-type: application/json" \
  -d '{
    "model": "apodex-1-1",
    "messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
  }'

Sumber Daya & Tautan Resmi

Deployment API

Bandingkan host & latensi

Throughput, TTFT, dan harga cache di Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock, dan Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Lihat matriks penyedia →

Skor per sumber

Skor per kategori

Hasil benchmark

Spesifikasi Live & Arsitektur

Di balik kap
Dense · 72B
  • Prompt caching supported — cached input reads at $0.02/1M tokens.
Tanggal rilis
20 Jul 2026
Arsitektur
Dense · 72B
Parameter
72B
Lisensi
Open Weights
Jendela konteks
131,072 tokens
Output maks
16,384 tokens
Modalitas
text
Harga cache
baca $0.02 · tulis $0.25 /1M
Penalaran
—
Harga input
$0.2/M
Harga output
$0.8/M
Kecepatan output
145 t/s
Waktu ke token pertama
—
Data diperbarui
26 Okt 2026

Estimasi tagihan bulanan

Estimasi pengeluaran bulanan
$0.00
Menghitung penghematan vs GPT-4o…

Kutip & sematkan

Badge Markdown GitHub
Loading badge markdown...
BibTeX
@misc{llmpodium2026apodex11,
  title = {Benchmark Analysis and Intelligence Evaluation of Apodex 1.1},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/apodex-1-1}
}

Sematkan Lencana Skor

Tambahkan lencana Podium Score langsung ke README GitHub atau Hugging Face Anda — menautkan ke peringkat langsung.

Pratinjau
Apodex 1.1 LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Lainnya dari Independent

Model Alternatif

Alternatif terdekat untuk Apodex 1.1 berdasarkan kemampuan, harga, dan skor benchmark.

0 / 4