# Kimi K2.5

Moonshot AI's generation after K2, with coverage across agent tasks, coding, visual understanding, and general-purpose use in its published materials.

- **Model ID:** `moonshotai/kimi-k2.5`
- **Type:** chat
- **Providers:** novita, bedrock
- **Context window:** 262,144
- **Maximum output tokens:** 262,144
- **Pricing:** $0.6/1M input tokens, $3/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/kimi-k2.5

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'moonshotai/kimi-k2.5',
  prompt: 'Why is the sky blue?'
})
```

## About

Kimi K2.5, released on January 26, 2026, is the generation after the K2 line. Moonshot AI describes K2.5 across agent tasks, coding, visual understanding, and general intelligence benchmarks in its release materials. K2.5 extends both text-based and visual tasks.

Frontend code generation is a highlighted change. Moonshot AI documents more capable frontend coding, including interactive UI with dynamic layouts and animations, beyond bare syntax-level output.

Access K2.5 through AI Gateway by setting the model string to `moonshotai/kimi-k2.5`. No extra provider accounts are required for gateway-managed access. AI Gateway's observability layer tracks token usage and costs across requests, which helps when usage patterns vary.

Kimi K2.5 is available through AI Gateway at $0.6 per million input tokens and $3 per million output tokens.

## What to consider

Evaluate Kimi K2.5 against your specific use case. The expanded capabilities may not justify the cost relative to K2 variants for every workload.

## When to use

### Best For

- Frontend code generation that needs interactive UI output with dynamic layouts, animations, and interactive components
- Workloads spanning multiple capability areas (agent tasks, coding, visual understanding, and general intelligence) within the same pipeline
- Projects in the Kimi family where earlier K2 variants lack multimodal or frontend scope you need
- Teams building general-purpose AI assistants that must handle diverse task types from a single model

### Consider Alternatives When

- You need extended chain-of-thought reasoning traces. Kimi K2 Thinking is built for that
- Your workload is well-served by the September 2025 K2 checkpoint and K2.5's added scope isn't needed
- Speed is the primary requirement and you don't need K2.5's broader capabilities. Kimi K2 Turbo or K2 Thinking Turbo are better fits
- Cost per token is the dominant factor and K2 variants meet your quality bar

## Best for

- **Interactive frontend code:** Generating UI with dynamic layouts, animations, and interactive components
- **Multi-capability pipelines:** Workloads spanning agent tasks, coding, visual understanding, and general intelligence in one pipeline
- **Multimodal or frontend gaps:** Kimi-family projects where earlier K2 variants lack the visual or frontend scope you need
- **General-purpose assistants:** Teams building AI assistants that must handle diverse task types from a single model

## Consider alternatives

- **Extended reasoning traces:** Kimi K2 Thinking is built for explicit chain-of-thought output
- **Sufficient K2 checkpoint:** The September 2025 K2 checkpoint covers your workload and K2.5's added scope isn't needed
- **Speed-first workloads:** Kimi K2 Turbo or K2 Thinking Turbo are better fits when you don't need K2.5's broader capabilities
- **Cost-sensitive deployments:** K2 variants may meet your quality bar at lower cost per token

## Frequently asked questions

### What makes Kimi K2.5 different from earlier K2 models?

It's the successor generation after K2. It adds frontend coding and visual inputs in Moonshot AI's documentation, which earlier K2-focused releases did not emphasize.

### Does Kimi K2.5 support visual or image inputs?

Yes for vision-style tasks in Moonshot AI's materials. Confirm input modalities and limits on https://deepinfra.com/moonshotai/Kimi-K2.5 before you build a vision pipeline.

### What kind of frontend code can Kimi K2.5 generate?

Moonshot AI documents interactive user interfaces with dynamic layouts and animations, not only static markup.

### Is Kimi K2.5 open source?

Yes. Moonshot AI ships K2.5 as open source in the same lineage as other open-weight Kimi models.

### When was Kimi K2.5 released on AI Gateway?

Kimi K2.5 became available through AI Gateway on January 26, 2026. Timing and scope are documented in the K2.5 on AI Gateway changelog post and on https://deepinfra.com/moonshotai/Kimi-K2.5.

### Should I use K2.5 or K2 Thinking for complex reasoning tasks?

Use K2 Thinking when you need extended chain-of-thought traces (math proofs, step-by-step algorithm design). K2.5 covers broad tasks including reasoning, but K2 Thinking is the match when explicit deliberation is the main requirement.

### How do I use Kimi K2.5 with the AI SDK?

Set the model to `moonshotai/kimi-k2.5` in your AI SDK call. No other configuration changes are required.

## Links

- [Model page](https://vercel.com/ai-gateway/models/kimi-k2.5)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://deepinfra.com/moonshotai/Kimi-K2.5)
- [Provider pricing](https://deepinfra.com/pricing)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.