Kimi K2.5

Open weightVisionTools

MoonshotAI · Released January 2026

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...

It belongs to Moonshot AI's Kimi K2 family, open-weight models known for agentic tool use, with Code and Thinking variants for their namesake strengths.

Facts and pricing

Provider
MoonshotAI
Context window
262K tokens
Input price
4.1 credits / 1M tokens ($0.38 raw)
Output price
22.3 credits / 1M tokens ($2.02 raw)
Vision (image input)
Yes
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Kimi K2.5 now

Ask Kimi K2.5 anything. Your prompt opens in the Zeplik app with this model selected.

Kimi K2.5

What Kimi K2.5 is best for

Example prompts

Prompts that suit a open weight model like Kimi K2.5:

MoonshotAI family

ModelContextInput cr/MOutput cr/MReleased
Kimi K2.7 Code262K7.938.5June 2026
Kimi K2.6262K7.237.5April 2026
Kimi K2.5262K4.122.3January 2026
Kimi K2 Thinking262K6.627.5November 2025
Kimi K2 0905262K6.627.5September 2025
Kimi K2 0711131K6.325.3July 2025

Frequently asked questions

What is Kimi K2.5?
Kimi K2.5 is an AI model by MoonshotAI. 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...
How much does Kimi K2.5 cost on Zeplik?
Input tokens cost 4.1 credits per million and output tokens 22.3 credits per million (1 credit = $0.10; the raw provider rates are $0.38 and $2.02 per million). New accounts start with free credits.
How long can a conversation with Kimi K2.5 be?
Kimi K2.5 has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
Does Kimi K2.5 support images and tools?
Kimi K2.5 accepts image input and supports tool calling.

Related models

Kimi K2.7 CodeCoding

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

262K ctx38.5 cr/M outJune 2026
Kimi K2.6Open weight

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

262K ctx37.5 cr/M outApril 2026
Kimi K2 ThinkingOpen weight

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

262K ctx27.5 cr/M outNovember 2025
Kimi K2 0905Open weight

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

262K ctx27.5 cr/M outSeptember 2025
Kimi K2 0711Open weight

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

131K ctx25.3 cr/M outJuly 2025
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
Kimi K2.5 - MoonshotAI AI Model | Zeplik Chat