All Moonshot AI models
M

Kimi K2.5

Moonshot AI · released 6 months ago

Kimi K2.5 is a Moonshot AI model with a 262K token context window — about 370 pages of text. It reads Text and Images and replies in Text. It can show its reasoning before it answers.

$0.655

input / 1M tokens

$3.28

output / 1M tokens

262K

context — about 370 pages

0.59¢

a client proposal

Pricing

Input
$0.655 per million tokens
Output
$3.28 per million tokens
Cached input
$0.109 per million tokens

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
Moonshot AI
Released
6 months ago (2026-01-27)
Context window
262K tokens — about 370 pages
Max output
262K tokens per reply
Input
Text and Images
Output
Text
Reasoning
Shows its thinking before answering

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$0.59$1.180 tokens250k500k750k1000k
Kimi K2.5

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

Kimi K2.5

Moonshot AI

0.29¢

for this task

44% input · 56% output

Full pricing →

Your $5 welcome credit covers about 1,695 of these.

Compare Kimi K2.5

Closest in price on a typical task:

Kimi K2.5 vs Qwen3 VL 235B A22B Thinking →Kimi K2.5 vs Relace Apply 3 →Kimi K2.5 vs Kimi K2 0905 →Kimi K2.5 vs Kimi K2 Thinking →Any other combination →

Questions, answered

How much does Kimi K2.5 cost on Alyph?

Kimi K2.5 costs $0.655 per million input tokens and $3.28 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.59¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is Kimi K2.5's context window?

262K tokens — about 370 pages. Replies can be up to 262K tokens long.

Can Kimi K2.5 read images and files?

Kimi K2.5 reads Text and Images. Drop a file onto the canvas and it becomes part of the context — the only limit is the context window.

Does Kimi K2.5 show its reasoning?

Yes. Kimi K2.5 can expose its thinking before the final answer, so you can watch how it got there.

Test Kimi K2.5 against Qwen3 VL 235B A22B Thinking

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.

Sign up free Try the demo