Moonshot AI

Kimi K3.1 ProOpen

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

#3released Oct 20, 2026·Open Weights·2.8T MoE
textimage1.0M ctxreasoning
Intelligence
94.2 #3
AAQI 68.0
Output Speed
45 t/s
ITL 22.2 ms/tok
Blended price (3:1)
$8 /1M
In $4/M · Out $20/M
Context
1.0M
≈ 2,500 A4 pages · max out 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)

Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.

Strengths & Trade-offs

Where it wins

  • 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+

Trade-offs to watch

  • 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

Killer Use Cases

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.

Developer Quickstart & API

Set MOONSHOT_API_KEY first — get an API key
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."}]
  }'

Official Resources & Links

API deployment

Compare hosts & latency

Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
View providers matrix →

Scores by Source

Head-to-head Live Matchups

Live Specs & Architecture

Under the hood
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
Release date
Oct 20, 2026
Architecture
Kimi K3.1 Pro — 2.8T MoE, ~40B active
Parameters
2.8T MoE
License
Open Weights
Context Window
1,000,000 tokens
Max Output
131,072 tokens
Modalities
text + image
Cache Pricing
read $0.4 · write $5 /1M
Reasoning
Effort levels
Input Price
$4/M
Output Price
$20/M
Output Speed
45 t/s
Time to First Token
—
Data Updated
Oct 22, 2026
Hardware & Local Inference
Data: Convly AI (CC BY 4.0) ↗
Min GPU
Multi-node cluster (e.g. 2× 8-GPU H200 141GB nodes)

Estimated monthly bill

Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...

Cite & embed

GitHub Markdown badge
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}
}

Embed Score Badge

Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.

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

More from Moonshot AI

Alternative Models

Closest alternatives to Kimi K3.1 Pro based on capabilities, pricing, and benchmark scores.

0 / 4