Moonshot AI

Kimi K3.1 HighspeedOpen

Latency-optimized serving tier of Kimi K3.1 — 1M context at flash-class throughput.

#13released Oct 20, 2026·Open Weights·2.8T MoE
textimage1.0M ctxreasoning
Intelligence
91.5 #13
AAQI 60.0
Output Speed
130 t/s
ITL 7.7 ms/tok
Blended price (3:1)
$3.13 /1M
In $1.5/M · Out $8/M
Context
1.0M
≈ 2,500 A4 pages · max out 65,536

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Kimi K3.1 Highspeed
Claude Mythos Preview (#1)
Average (68)
Coding (60)Mathematics (88)Hard Science (GPQA) (92)Agentic & Tool Use (74)Knowledge (MMLU) (38)Vision / Multimodal (90)

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

Strengths & Trade-offs

Where it wins

  • 130 tok/s — fastest 1M-context open model
  • Roughly half the Pro tier’s blended price
  • Same agentic tool-use lineage as K3.1 Pro

Trade-offs to watch

  • Caps reasoning effort vs. Pro — drops on the hardest tasks
  • 65K output window vs. 131K on Pro
  • Still needs multi-node serving to self-host

Killer Use Cases

Real-time agent loops
High-throughput tool calling for interactive copilots.
High-volume RAG
Cheap 1M-context reads over large corpora.
Voice-adjacent LLM backends
Sub-second first token keeps spoken agents snappy.

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-highspeed",
    "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 Highspeed — 2.8T MoE, speculative decode
  • Same K3.1 weights served with aggressive speculative decoding
  • Sub-600ms TTFT at 130 tok/s on dedicated capacity
  • 1M context retained; 65K max output
  • Lower reasoning-effort ceiling than the Pro tier
Release date
Oct 20, 2026
Architecture
Kimi K3.1 Highspeed — 2.8T MoE, speculative decode
Parameters
2.8T MoE
License
Open Weights
Context Window
1,000,000 tokens
Max Output
65,536 tokens
Modalities
text + image
Cache Pricing
read $0.15 · write $1.88 /1M
Reasoning
Effort levels
Input Price
$1.5/M
Output Price
$8/M
Output Speed
130 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{llmpodium2026kimik31highspeed,
  title = {Benchmark Analysis and Intelligence Evaluation of Kimi K3.1 Highspeed},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/kimi-k3-1-highspeed}
}

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 Highspeed LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

More from Moonshot AI

Alternative Models

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

0 / 4