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 visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.
Context window
This model accepts 262K tokens in one request (~197K words of text).
What fits in one request
- FitsShort documentAbout 1,500 words of text
- FitsLong documentAbout 37K words of text
- FitsSmall codebaseAbout 150K words of text
- Won't fitFull novelAbout 375K words of text
Specifications
Context size, pricing, and release info in one place.
- Context window
- 262,144 tokens (262K)
- Max output tokens
- 262,144 tokens (262K)
- Speed tier
- balanced
- Provider
- Moonshot
- Release date
- Jan 2026
- Input cost
- $0.600/M / 1M tokens
- Output cost
- $3.00/M / 1M tokens
Capabilities
See which features this model supports, such as vision, tools, and streaming.
- Vision
- Accepts image inputs alongside text
- Supported
- Tool use
- Can call external tools and APIs
- Supported
- Function calling
- Structured function call interface
- Supported
- Extended thinking
- Shows its chain-of-thought reasoning
- Supported
- Streaming
- Returns tokens as they are generated
- Supported
- Prompt caching
- Reuse repeated prompt prefixes cheaply
- Supported
- Web search
- Can browse the web during a request
- Not supported
- Batch API
- Process many requests asynchronously
- Not supported
Best for
Jump to a guide or ranking that matches each workload.
Compare Kimi K2.5
Open a side-by-side comparison with one click.
- Kimi K2.5 vs Amazon Titan Text Express
Kimi K2.5 has 524% larger context window
- Kimi K2.5 vs Amazon Titan Text Lite
Kimi K2.5 has 524% larger context window
- Kimi K2.5 vs Amazon Titan Text Premier
Kimi K2.5 has 524% larger context window
- Kimi K2.5 vs Claude Instant
Kimi K2.5 has 162% larger context window
- Kimi K2.5 vs Anthropic Claude
Kimi K2.5 has 162% larger context window
- Kimi K2.5 vs Codellama 34b Instruct
Kimi K2.5 has 6300% larger context window
Frequently asked questions
Short answers about context size and how this model behaves.
More from Moonshot
Other models by Moonshot in our catalog.
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model