MoonshotAI: Kimi K2.5

moonshotai · Released Jan 27, 2026
DFO score #117 / 749
22.1 leaderboard score
Speed #290 / 355
51.3 tok/s
Input Price #490 / 749
$0.500 per 1M tokens
Output Price #527 / 749
$2.50 per 1M tokens
Context #208 / 749
262,144 tokens

Analysis Summary

MoonshotAI’s Kimi K2.5 is a text-and-image model with a 262K context window, tool use, and function calling. Its intelligence index is 23.5, while its coding index is 46.8. The supplied results also show strong tool-task performance, with useful instruction-following and long-context measurements. Together, these signals point to a capable workflow model, particularly for coding and multimodal assistance.

It is a practical candidate for code support, image-aware analysis, and document-heavy tasks that benefit from a larger context. The agentic index of 21.7 is not as strong as its coding result, so teams should still test multi-step execution and require review for consequential tool actions. Its listed input and output prices are 0.45 and 2.25.

Consider it for specialist and secondary production workloads where its context, vision, and coding capabilities match the task. Validate output quality on client-specific prompts before expanding use.

Assessed September 23, 2026

Editorial notes

Kimi K2.5 pairs a 262K context window and vision with strong measured coding, tool-use, and instruction-following results at listed input and output prices of 0.45 and 2.25.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

Kimi K2.5 pairs a 262K context window and vision with strong measured coding, tool-use, and instruction-following results at listed input and output prices of 0.45 and 2.25.

#117 of 749 overall Down 5 this week

Benchmarks

Intelligence Index 15.0 #116 of 454 · Artificial Analysis
Coding Index 29.9 #76 of 199 · Artificial Analysis
Agentic Index 13.8 #67 of 181 · Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following Not rated Arena rating
GPQA Diamond 87.9%
HLE 29.4%
SciCode 49%
TerminalBench Hard 34.8%
τ²-Bench 95.9%
IFBench 70.2%
LCR 65.3%

Artificial Analysis data refreshed Nov 16, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.

Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.

How MoonshotAI: Kimi K2.5 compares

MoonshotAI: Kimi K2.5 ranks #116 of 454 AI models we track for overall intelligence, #76 of 199 for coding, #67 of 181 for agentic tasks. Its 262K-token context window is larger than 72% of the models we list. At $0.50 per million input tokens it is cheaper than 35% of comparable models.

Position in the field
DFO score: ahead of 85% of models #116
Speed: faster than 18% of models #290
Price: cheaper than 35% of models #490
Context: larger than 72% of models #208
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
MoonshotAI: Kimi K2.5 $0.50 in $2.50 out
Anthropic: Claude Fable 5.2 $8.00 in $40.00 out
Google: Gemini 4 Carbon $2.00 in $10.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.50 $0.000500
Output $2.50 $0.002500

What would MoonshotAI: Kimi K2.5 cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$3.96/mo MoonshotAI: Kimi K2.5 $0.0013 per request
$63.36/mo Anthropic: Claude Fable 5.2 $0.02 per request
$15.84/mo Google: Gemini 4 Carbon · best value $0.0053 per request

Full calculator with 749 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save MoonshotAI: Kimi K2.5 for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About MoonshotAI: Kimi K2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed..

Frequently asked questions about MoonshotAI: Kimi K2.5

How much does MoonshotAI: Kimi K2.5 cost?

MoonshotAI: Kimi K2.5 costs $0.50 per million input tokens and $2.50 per million output tokens.

What is the context window of MoonshotAI: Kimi K2.5?

MoonshotAI: Kimi K2.5 has a context window of 262,144 tokens (262K).

Is MoonshotAI: Kimi K2.5 good for coding?

On our coding benchmark index, MoonshotAI: Kimi K2.5 ranks #76 of 199 models, placing it in the broader range of the field for code generation and debugging.

What can MoonshotAI: Kimi K2.5 do?

MoonshotAI: Kimi K2.5 supports image/vision input, tool use, and function calling.

Who created MoonshotAI: Kimi K2.5?

MoonshotAI: Kimi K2.5 is developed by MoonshotAI and was released on January 27, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.