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 assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Moonshot AI

Kimi K2.6 Thinking

Kimi K2.6 Thinking is the reasoning-optimized K2.6 variant for deeper multi-step planning and execution. It is tuned for long-horizon coding and design workflows, including complex orchestration across many specialized sub-agents and autonomous end-to-end output generation.

  • Reasoning
  • Vision
  • Tool Calling
  • Parallel Tool Calls

Added Apr 16, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.389
Output
$1.64
Cache read
$0.0656
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
1T / 32B
Total / active
Avg output (7d)
3.8K tokens
Longer than 99% of models

Benchmarks

Sourced from LMArena.

Arena Score

1460.8

Overall Rank

#61 / 421

Votes

39,573

Confidence Interval

1456.4 - 1465.3

Category Scores

Coding

#46 / 416

10,975 votes

1516.2

Math

#38 / 404

2,048 votes

1479.1

Longer Query

#52 / 399

16,720 votes

1477.7

Creative Writing

#71 / 419

6,211 votes

1432.2

Instruction Following

#59 / 421

13,020 votes

1455.4

Hard Prompts

#59 / 421

25,755 votes

1485.3

Additional Categories
22

Chinese

#39 / 395

2,279 votes

1517.4

Expert

#41 / 371

3,789 votes

1503.0

Industry Mathematical

#44 / 401

2,165 votes

1484.8

Industry Software And It Services

#50 / 421

15,874 votes

1503.2

Korean

#52 / 289

705 votes

1424.7

Japanese

#55 / 288

493 votes

1438.8

German

#58 / 320

741 votes

1462.3

Spanish

#59 / 303

1,362 votes

1460.3

Non English

#60 / 421

21,598 votes

1448.6

Hard Prompts English

#61 / 419

12,328 votes

1488.0

Exclude Ties

#62 / 421

29,304 votes

1464.6

English

#63 / 421

17,975 votes

1469.0

French

#66 / 301

1,558 votes

1477.5

Industry Business And Management And Financial Operations

#68 / 414

7,832 votes

1455.3

Industry Life And Physical And Social Science

#68 / 419

6,616 votes

1477.6

Industry Legal And Government

#71 / 393

2,983 votes

1463.8

Industry Entertainment And Sports And Media

#72 / 419

8,161 votes

1429.6

Industry Medicine And Healthcare

#73 / 390

2,895 votes

1472.3

Industry Writing And Literature And Language

#73 / 420

9,458 votes

1441.1

Russian

#73 / 385

4,200 votes

1452.9

Multi Turn

#78 / 419

6,898 votes

1461.7

Polish

#92 / 244

756 votes

1442.2

Published 2026-11-09 · Matched as Kimi K2.6

LMArena Dataset

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)
$0.57$2.40$0.114N/AN/A
Auto
Auto (Anonymized)
$0.389$1.64$0.0656N/AN/A
Baidu
Baidu
59% off
FP4
CN
$0.998$0.409$4.20$1.72$0.168$0.06890.9s57 tps
Chutes
Chutes
INT4
US
$0.41$1.89$0.0411.6s45 tps
Moonshot
Moonshot
SG
$0.546$2.72N/A4.2s25 tps
StreamLake
StreamLake
37% off
FP8
CN
$0.998$0.628$4.20$2.65$0.168$0.1061.3s34.5 tps
CoreWeave
CoreWeave
FP4
US
$0.682$3.58$0.1570.5s63 tps
Crusoe
Crusoe
BF16
US
$0.735$3.68$0.3670.7s70.5 tps
Parasail
Parasail
INT4
US
$0.787$3.68$0.1681.4s48 tps
Inceptron
Inceptron
INT4
EU
$0.839$3.94$0.220.7s48 tps
Novita
Novita
US
$0.84$3.57$0.1684s20 tps
Kitani
Kitani
GLB
$0.998$4.20$0.168N/AN/A
Ollama
Ollama
UNK
$0.998$4.20$0.168N/AN/A
Sail Research (ASAP)
Sail Research (ASAP)
FP8
GLB
$1.05$4.20$0.21N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsBest latency and throughput are highlighted.
Batch API
ProviderInputOutputCached input
Auto
Automoonshotai/kimi-k2.6:thinking
$0.389/M$1.64/M$0.0656/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Kimi K2.6 Thinking with similar models from the same provider or model family.

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.

Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.

Kimi Latest

moonshotai/kimi-latest

Always points to the newest recommended Kimi model, currently Kimi K3.1 Pro. Reasoning is always enabled. Select Kimi K3 explicitly to retain its checkpoint and pricing; K3.1 Pro Highspeed is available separately.