Moonshot AI

Kimi K3.1 ProTerbuka

Moonshot’s 2.8T-parameter MoE flagship with 1M context, native multimodality and frontier reasoning.

#3dirilis 20 Okt 2026·Open Weights·2.8T MoE
textimage1.0M ctxpenalaran
Inteligensi
94.2 #3
AAQI 68.0
Kecepatan output
45 t/s
ITL 22.2 ms/tok
Harga gabungan (3:1)
$8 /1M
Input $4/M · Output $20/M
Konteks
1.0M
≈ 2,500 halaman A4 · output maks 131,072

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Kimi K3.1 Pro
Claude Mythos Preview (#1)
Average (68)
Coding (72)Mathematics (95)Hard Science (GPQA) (98)Agentic & Tool Use (82)Knowledge (MMLU) (45)Vision / Multimodal (96)

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

Kelebihan & Trade-off

Di mana ia menang

  • Top-3 podium score — frontier reasoning and agentic tool use
  • 1M context with open weights
  • Strong SWE-bench / Terminal-Bench results for long-horizon coding
  • Multimodal document and chart understanding at 96+

Hal yang perlu diperhatikan

  • Multi-node cluster required for self-hosting (2.8T MoE)
  • 45 tok/s output — slower than flash-tier peers
  • Premium pricing vs. smaller open models

Kasus Penggunaan Killer

Long-horizon coding agents
131K output window rewrites whole files; leads SWE-bench-class leaderboards.
Agentic browsing & research
Tool-use loops over 1M-token contexts — the K-line’s signature workload.
Multimodal enterprise RAG
Charts, scans and PDFs ingested natively alongside text.

Quickstart Developer & API

Atur MOONSHOT_API_KEY dulu — dapatkan kunci API
curl https://api.moonshot.ai/v1/chat/completions \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "kimi-k3-1-pro",
    "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

Duel Head-to-head Live

Spesifikasi Live & Arsitektur

Di balik kap
Kimi K3.1 Pro — 2.8T MoE, ~40B active
  • Sparse MoE routing — ~40B active per token out of 2.8T total
  • Native multimodality: text + vision in a single weight set
  • Reasoning effort levels with a 131K max output window
  • INT4 checkpoints for cheaper multi-node serving
Tanggal rilis
20 Okt 2026
Arsitektur
Kimi K3.1 Pro — 2.8T MoE, ~40B active
Parameter
2.8T MoE
Lisensi
Open Weights
Jendela konteks
1,000,000 tokens
Output maks
131,072 tokens
Modalitas
text + image
Harga cache
baca $0.4 · tulis $5 /1M
Penalaran
Level effort
Harga input
$4/M
Harga output
$20/M
Kecepatan output
45 t/s
Waktu ke token pertama
—
Data diperbarui
22 Okt 2026
Perangkat Keras & Inferensi Lokal
Data: Convly AI (CC BY 4.0) ↗
GPU Min.
Multi-node cluster (e.g. 2× 8-GPU H200 141GB nodes)

Estimasi tagihan bulanan

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

Kutip & sematkan

Badge Markdown GitHub
Loading badge markdown...
BibTeX
@misc{llmpodium2026kimik31pro,
  title = {Benchmark Analysis and Intelligence Evaluation of Kimi K3.1 Pro},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/kimi-k3-1-pro}
}

Sematkan Lencana Skor

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

Pratinjau
Kimi K3.1 Pro LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Lainnya dari Moonshot AI

Model Alternatif

Alternatif terdekat untuk Kimi K3.1 Pro berdasarkan kemampuan, harga, dan skor benchmark.

0 / 4