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 K2.5 Thinking

Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.

  • Reasoning
  • Vision
  • Tool Calling
  • Parallel Tool Calls

Added Jan 26, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.626
Output
$3.22
Cache read
$0.105
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
1T / 32B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1449.5

Overall Rank

#81 / 421

Votes

73,872

Confidence Interval

1446.2 - 1452.8

Category Scores

Coding

#77 / 416

20,552 votes

1502.1

Math

#54 / 404

4,120 votes

1469.8

Longer Query

#80 / 399

29,372 votes

1457.5

Creative Writing

#82 / 419

12,080 votes

1422.0

Instruction Following

#81 / 421

23,900 votes

1439.0

Hard Prompts

#85 / 421

47,318 votes

1471.2

Additional Categories
22

Industry Mathematical

#53 / 401

3,965 votes

1476.0

Japanese

#70 / 288

834 votes

1423.4

Chinese

#72 / 395

4,503 votes

1494.4

Expert

#72 / 371

6,876 votes

1482.4

Korean

#73 / 289

1,298 votes

1411.2

German

#78 / 320

1,287 votes

1449.4

Industry Software And It Services

#78 / 421

29,429 votes

1489.4

Hard Prompts English

#79 / 419

20,838 votes

1479.1

Spanish

#80 / 303

2,501 votes

1446.2

English

#82 / 421

31,437 votes

1460.8

Industry Entertainment And Sports And Media

#82 / 419

15,269 votes

1420.3

Exclude Ties

#83 / 421

53,795 votes

1450.2

Industry Life And Physical And Social Science

#83 / 419

11,636 votes

1470.0

Industry Medicine And Healthcare

#83 / 390

5,087 votes

1466.8

Non English

#84 / 421

42,432 votes

1434.8

Polish

#86 / 244

1,520 votes

1446.6

Multi Turn

#87 / 419

13,038 votes

1452.1

Industry Writing And Literature And Language

#88 / 420

17,671 votes

1426.3

Russian

#89 / 385

8,718 votes

1442.5

French

#93 / 301

2,595 votes

1463.9

Industry Legal And Government

#105 / 393

5,576 votes

1446.3

Industry Business And Management And Financial Operations

#108 / 414

14,258 votes

1440.0

Published 2026-11-09 · Matched as Kimi K2.5 (Thinking) · CC BY 4.0

LMArena Dataset

Leaderboard results

These leaderboards tested Kimi K2.5, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026

Epoch Capabilities Index

148.8

#67 of 115

SWE-bench Verified

73.8%

#16 of 28

SimpleQA Verified

34.3%

#57 of 82

EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

Creative Writing v3

1579

#48 of 96

Longform Writing

74.9

#28 of 97

EQ-Bench 3

1530

#14 of 49

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

55.2

#22 of 149

UGI Willingness

2.5

#95 of 149

UGI Writing

62.4

#31 of 149

Filtered and ranked to models on NanoGPT.

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)
$0.626$3.22$0.105N/AN/A
Auto
Auto (Anonymized)
$0.626$3.22$0.105N/AN/A
MegaNova
MegaNova
US
$0.472$2.36$0.0735N/AN/A
AtlasCloud
AtlasCloud
INT4
US
$0.514$2.63$0.21N/AN/A
SiliconFlow
SiliconFlow
INT4
SG
$0.525$2.63$0.157N/AN/A
Venice
Venice
US
$0.559$3.49$0.219N/AN/A
Novita
Novita
US
$0.63$3.15$0.105N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclearMay train on prompts
Batch API
ProviderInputOutputCached input
Auto
Automoonshotai/kimi-k2.5:thinking
$0.626/M$3.22/M$0.105/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 K2.5 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.