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://platform.moonshot.ai/docs/pricing/chat#product-pricing 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://platform.moonshot.ai/docs/pricing/chat#product-pricing.

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.

Moonshot AI

Kimi K2.5

Kimi K2.5 is Moonshot AI's successor to the K2 family: multimodal inputs, upgraded frontend coding, and a context window of 262.1K tokens, available through AI Gateway via Moonshot AI, Novita AI, Bedrock. Your use is subject to Moonshot AI's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $0.60, Output $3, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

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

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Kimi K2.5 by Moonshot AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Kimi K2.5

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

Moonshot AI

Legal:Terms•Privacy

262K

$0.60/M

$3/M

Read$0.10/M

—

01/26/2026

Novita AI

Legal:Terms•Privacy

262K

0.9 s

41 tps

$0.60/M

$3/M

Read$0.10/M

—

01/26/2026

Bedrock

Legal:Terms•Privacy

256K

0.7 s

50 tps

$0.60/M

$3/M

—

01/26/2026

Getting started

Call Kimi K2.5 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Kimi K2.5 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `moonshotai/kimi-k2.5`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Kimi K2.5 supports up to `262,144` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 262K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK moonshotai provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['moonshotai', 'novita'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'moonshotai/kimi-k2.5',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Moonshot AI

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

moonshotai/kimi-k3-fast

1.5 s

98 tps

$4.50/M

$22.50/M

Read$0.45/M

—

07/27/2026

moonshotai/kimi-k3

0.4 s

443 tps

$2.50/M+1 more

$12.75/M+1 more

Read$0.29/M

—

+11

07/16/2026

moonshotai/kimi-k2.7-code-highspeed

262K

1.0 s

146 tps

$1.90/M

$8/M

Read$0.38/M

—

06/15/2026

moonshotai/kimi-k2.7-code

262K

0.8 s

223 tps

$0.68/M+1 more

$3.40/M+1 more

Read$0.14/M

—

06/12/2026

moonshotai/kimi-k2.6

262K

0.5 s

68 tps

$0.80/M

$3.40/M

Read$0.16/M

—

04/20/2026

moonshotai/kimi-k2

131K

1.6 s

41 tps

$0.57/M

$2.30/M

—

07/11/2025

Copy link to headingAbout Kimi K2.5

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.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Evaluate Kimi K2.5 against your specific use case. The expanded capabilities may not justify the cost relative to K2 variants for every workload.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Kimi K2.5

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 when

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

Copy link to headingConclusion

Kimi K2.5 adds multimodal inputs and frontend coding emphasis to the Kimi line on AI Gateway, alongside agent, coding, and vision workloads. As of January 26, 2026, it's the K2 successor listed for those combined use cases on AI Gateway.

Copy link to headingFrequently 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://platform.moonshot.ai/docs/pricing/chat#product-pricing 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://platform.moonshot.ai/docs/pricing/chat#product-pricing.
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.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Kimi K2.5

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

Tool calling

Copy link to headingMore models by Moonshot AI

Copy link to headingAbout Kimi K2.5

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Kimi K2.5

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions