Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Text
  3. Tee

Kimi K3 TEE

Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image understanding. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

  • Reasoning
  • Vision
  • Tool Calling
  • Structured Output

Added Jul 31, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$1.85
Output
$9.50
Cache read
$0.185
Compare provider prices

Specifications

Context window
1M
Max output
1M
Parameters
2.8T
Avg output (7d)
1.3K tokens
Longer than 77% of models

Benchmarks

Sourced from Design Arena.

Best Category

3D

Best Elo

1374

Best Rank Percentile

Top 7%

Ranking Distribution

13,594 battles

60%

45%

30%

15%

0%

21.8%

First

43.0%

Second

28.7%

Third

6.5%

Fourth

Category Performance

Elo
Rank
3DTop 7%Data VizTop 2%Game DevTop 6%SVGTop 9%UITop 6%WebsiteTop 3%

Models Arena

3D

Top 7%

1374

Elo

63.8%

Win

678.4s

Avg Time

#13

Rank

Game Development

Top 6%

1349

Elo

54.4%

Win

936.0s

Avg Time

#12

Rank

Data Visualization

Top 2%

1348

Elo

63.2%

Win

655.4s

Avg Time

#3

Rank

UI Component

Top 6%

1343

Elo

60.7%

Win

763.1s

Avg Time

#12

Rank

Website

Top 3%

1332

Elo

58.6%

Win

836.0s

Avg Time

#7

Rank

SVG

Top 9%

1303

Elo

59.8%

Win

439.3s

Avg Time

#13

Rank

Agents Arena

Full Stack

Top 10%

1301

Elo

61.5%

Win

N/A

Avg Time

#5

Rank

Web Apps

Top 18%

1285

Elo

59.0%

Win

N/A

Avg Time

#10

Rank

Native Apps

Top 13%

1261

Elo

57.3%

Win

N/A

Avg Time

#6

Rank

Mobile Apps

Top 11%

1261

Elo

56.9%

Win

N/A

Avg Time

#6

Rank

Agentic Game Dev

Top 18%

1202

Elo

54.0%

Win

N/A

Avg Time

#5

Rank

Updated Nov 9, 2026, 10:30 PM · Matched as Kimi K3

Design Arena

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$1.85$9.50$0.185N/AN/A
Auto
Auto (Anonymized)
$1.85$9.50$0.185N/AN/A
Chutes
Chutes
TEE verified
US
$1.94$9.97$0.194N/AN/A
Tinfoil
Tinfoil
TEE verified
US
$4.20$21.00$0.63N/AN/A
Privacy:ZDR, prompts not retainedNo training on prompts

Related text models

Compare Kimi K3 TEE with similar models from the same provider or model family.

Kimi K3.1 Pro TEE

TEE/kimi-k3.1-pro

Kimi K3.1 Pro is Moonshot AI's multimodal model post-trained from Kimi K3 for long-horizon coding, agentic workflows, and knowledge work. It always reasons, and supports image input, tool calling, and structured output with a 262,144-token context window shared by input and output. Running inside a TEE (Trusted Execution Environment) with attestation support for more private, verifiable inference.

Kimi K2.6 TEE

TEE/kimi-k2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

Kimi K3.1 Pro

moonshotai/kimi-k3.1-pro

Kimi K3.1 Pro is a multimodal reasoning model for coding, 3D creation, document analysis and multi-step tool use. It supports a 1M-token context window and text, image and video inputs. Reasoning is always enabled, with low, high and max effort levels.

Kimi K3.1 Pro Highspeed

moonshotai/kimi-k3.1-pro-highspeed

Kimi K3.1 Pro Highspeed is the faster variant of K3.1 Pro, a multimodal reasoning model for coding, 3D creation, document analysis and multi-step tool use. It supports a 1M-token context window and text, image and video inputs. Reasoning is always enabled, with low, high and max effort levels.

Kimi K3

moonshotai/kimi-k3

Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image/video understanding.

Kimi K2.7 Code High-Speed

moonshotai/kimi-k2.7-code-highspeed

Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.