Kimi K2.5
by MoonshotAI
Kimi K2.5 pricing, context window and specs
Kimi K2.5 is a MoonshotAI model with a 262,144 token context window. It costs $0.60 per million input tokens and $3.00 per million output tokens, and supports image input, reasoning, tool calling and structured output.
Kimi K2.5 specs
Provider
MoonshotAI
Model ID
kimi-k2.5
Input price
$0.60 per 1M tokens
Cached input price
$0.10 per 1M tokens
Output price
$3.00 per 1M tokens
Context window
262,144 tokens
Modalities
Text and images in, text out
Tool calling
โ Supported
Structured output
โ Supported
Reasoning
โ Supported
Vision
โ Supported
Prices checked on
When to use Kimi K2.5
Pick Kimi K2.5 as an everyday model when you need solid quality without paying top-tier prices.
Drafting and analysis. Writing, summarising and answering questions over your own data.
Problems that need thinking. It can reason through a task before it answers.
Agents that use tools. It supports tool calling and structured output, so it can act and hand back clean JSON.
Large inputs. The 262,144 token context window fits long documents and transcripts in one request.
Reading images. It accepts screenshots, scans and photos alongside text.
If you need more capability, Kimi K2.6 costs $0.95 per million input tokens.
Cost calculator
What Kimi K2.5 costs at your volume
Pick a workload or move the sliders. The estimate uses the prices in the table above.
Templates
Templates you can run with Kimi K2.5
Ready-made workflows and agents. Copy one, pick Kimi K2.5 in the AI step and run it.
Workflow
3
uses
AI Visibility Checker
Paste a customer question to see how ChatGPT and Gemini answer it and which brands and sources they mention.
tom_alan
Workflow
1
uses
Community Co-Host Leads From Referring Organizations
For community program managers and executives, this workflow reads a program website and its live backlinks to identify organizations worth approaching as potential event co-hosts. It returns a prioritized table with each referring page and an evidence-based reason to reconnect.

Fetch Hive
Agent
1
uses
Google SEO Keyword Research Agent
Tell it what you want to create and the country and language, and it picks the keyword worth targeting with the evidence behind it.
tom_alan
Build with it
Use Kimi K2.5 in Fetch Hive
Fetch Hive is an AI agent builder. Pick this model in any prompt, workflow or agent step, or call it from your own code with one API request.
Call Kimi K2.5 through the AI Gateway
1
Create a prompt and pick the model
Write your prompt in Fetch Hive and choose this model from the model library. Add a fallback model if you want a backup.
2
Deploy the prompt
Deploying gives the prompt a deployment name and a variant that your code can call.
3
Send one POST request
Call the invoke endpoint with your API key. Usage is charged to your AI wallet at the provider list price, and each call uses one task.
Compare
Compare Kimi K2.5 with similar models
List prices per 1M tokens and context window, next to the models people most often weigh it against.
Kimi K2.6
Kimi K2.7 Code
Qwen3.5 397B A17b
FAQ




