Cody
en
ENESFRDEJAKOPT-BRPLAR
Agents
Cody Assist logoCody AssistKnowledge and supportCody Convert logoCody ConvertProactive website agentCody Clear logoCody ClearCompliance-gradeCody Live logoCody LiveAvatars and experiences
All agentsPricing
Resources
BlogUse casesPrompt librarySkill libraryModel library
Company
AboutContact
All models
Text & reasoningLive
Moonshot AI

Kimi K3

Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.

Open provider docsSee key factsPricing & comparisons

Plain-English overview

What Kimi K3 actually is

Kimi K3 can work across text and images while retaining up to one million tokens of context. Moonshot emphasizes long coding and agent workflows, with reasoning levels and tool use available through its direct developer platform and selected partners.

Direct pricing separates cached and uncached input, which can make repeated large contexts much cheaper when an application is designed to reuse them. OpenRouter and other providers have their own rates and operational policies.

Good fit for

  • Large codebase and document work
  • Agents that repeatedly reuse a long context
  • Multimodal reasoning through a direct or gateway API

Category comparison

The facts that matter for text models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Context window
1M tokensMaximum combined prompt and working context documented by the provider.
Maximum output
Not separately published for the direct APIProvider-published response limit, where available.
Knowledge cutoff
Not publishedLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.
Input price
$3 / 1M uncached; $0.30 cachedCurrent standard list price per million input tokens unless noted.
Output price
$15 / 1MCurrent standard list price per million output tokens unless noted.
Inputs
Text, imageMedia types accepted by the listed model endpoint.
Tools & agents
Tools, agent workflows, reasoning levels, dynamic tool loading on supported routesSelected native tools and agent-building capabilities, not an exhaustive list.

Pricing & comparisons

Estimate your cost

Set your usage. Your estimate updates as you type.

Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.

One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.

Advanced options

Kimi K3

Moonshot AI

Estimated total (USD)

No reviewed rate

For the usage above · USD · API pricing, not a subscription

How this estimate works

Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.

API and provider access

Where to get Kimi K3

Moonshot AIKimi K3 announcementOfficial release, model ID, context, reasoning controls, and direct token pricing.Kimi PlatformKimi developer platformDirect API keys, documentation, and current service access.OpenRouterKimi K3 on OpenRouterAlternative provider routing and live gateway pricing.

Availability

Regions and access stage

Available through the Kimi developer platform and selected providers including OpenRouter and QwenCloud.

The direct Kimi platform operates under Moonshot's published terms; third-party region and country support depends on the chosen provider.

Check live availability

Data and training

The route matters.

Moonshot's API privacy and model-use terms allow submitted content to be stored and used to provide, maintain, develop, and improve the service. Obtain appropriate enterprise terms before sending sensitive material.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

Kimi K3 FAQ

What is Kimi K3?

Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents. Kimi K3 can work across text and images while retaining up to one million tokens of context. Moonshot emphasizes long coding and agent workflows, with reasoning levels and tool use available through its direct developer platform and selected partners.

When was Kimi K3 released?

Kimi K3 was released on July 22, 2026 according to the cited provider materials.

Where can I access Kimi K3?

Available through the Kimi developer platform and selected providers including OpenRouter and QwenCloud. The access routes listed in this guide are Moonshot AI, Kimi Platform, and OpenRouter.

How much does Kimi K3 cost?

$3 uncached input · $15 output / 1M tokens direct. Moonshot also lists $0.30 per million cached input tokens. OpenRouter and other hosted routes use different prices.

Where is Kimi K3 available?

Available through the Kimi developer platform and selected providers including OpenRouter and QwenCloud. The direct Kimi platform operates under Moonshot's published terms; third-party region and country support depends on the chosen provider.

Is my Kimi K3 API data used for training?

Moonshot's API privacy and model-use terms allow submitted content to be stored and used to provide, maintain, develop, and improve the service. Obtain appropriate enterprise terms before sending sensitive material. The policy belongs to the provider route and account terms, so verify it again before production use.

Price comparison

One price per model, using the same input/output mix. We weight each API rate by its share of one million total tokens and use the lowest matching reviewed route. This is a comparison rate, not a cost per task or a quality score. Tokenizers, caching, reasoning and long context can change your actual bill.

Blended token costper 1M total tokens · USD

75% input + 25% output · no cache discounts

  1. $0.20
    GPT-6 Luna

    OpenAI

  2. $0.2625
    Mistral Small 4

    Mistral AI

  3. $0.45
    GPT-5.6 Luna

    OpenAI

  4. $1.50
    Gemini 3.8 Flash

    Google

  5. $2.00
    Claude Haiku 4.5

    Anthropic

  6. $4.00
    GPT-6 Sol

    OpenAI

  7. $4.00
    Claude Sonnet 5

    Anthropic

  8. $4.50
    GPT-5.6 Terra

    OpenAI

  9. $8.00
    Daybreak Blue

    OpenAI

  10. $8.00
    Claude Opus 5.5

    Anthropic

  11. $8.00
    GPT-5.6 Sol

    OpenAI

  12. $10.00
    Claude Opus 5

    Anthropic

  13. $20.00
    Claude Fable 5

    Anthropic

  14. $20.00
    GPT-6 Astra

    OpenAI

  15. $20.00
    Claude Fable 5.1

    Anthropic

Related comparisons

Head-to-head comparisons

View category →

  1. Kimi K3 vs Claude Opus 5.5

    A Claude model for large code changes, detailed research and business tasks that take many steps.

    Open full comparison

  2. Kimi K3 vs GPT-5.6 Terra

    A lower-cost GPT-5.6 option for coding, analysis and assistants that use tools.

    Open full comparison

  3. Kimi K3 vs GPT-5.6 Luna

    The budget GPT-5.6 tier for processing many short, repeatable tasks.

    Open full comparison

  4. Kimi K3 vs Claude Fable 5

    The original Fable model for complex coding and multi-step work, retained for existing integrations.

    Open full comparison

  5. Kimi K3 vs Claude Opus 5

    A Claude model for substantial code changes, reasoning and business workflows with many steps.

    Open full comparison

  6. Kimi K3 vs Claude Sonnet 5

    A lower-priced Claude option for everyday coding, writing and tool-assisted work.

    Open full comparison

  7. Kimi K3 vs Claude Haiku 4.5

    A compact Claude model for quick replies, classification and narrowly scoped assistants.

    Open full comparison

  8. Kimi K3 vs GPT-6 Astra

    OpenAI's most capable model for difficult end-to-end work, combining frontier reasoning with a million-token context window and a broad set of agent tools.

    Open full comparison

  9. Kimi K3 vs GPT-5.6 Sol

    OpenAI's flagship general model for difficult coding, analysis, and professional work, with a very large context window and a broad native tool set.

    Open full comparison

  10. Kimi K3 vs Claude Fable 5.1

    Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.

    Open full comparison

  11. Kimi K3 vs Gemini 3.8 Flash

    Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.

    Open full comparison

  12. Kimi K3 vs Grok 4.6

    SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools.

    Open full comparison

  13. Kimi K3 vs Grok 4.20 Multi-Agent Beta

    A specialist Grok model that sends several AI agents to investigate a difficult question in parallel, then combines their work into one researched answer.

    Open full comparison

  14. Kimi K3 vs Inkling

    Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.

    Open full comparison

  15. Kimi K3 vs Mistral Medium 3.5

    Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.

    Open full comparison

  16. Kimi K3 vs Mistral Small 4

    Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint.

    Open full comparison

  17. Kimi K3 vs Qwen3.8 Max

    Alibaba's frontier Qwen model for long-context reasoning, coding, tools, and understanding text, images, and video.

    Open full comparison

  18. Kimi K3 vs MiniMax M3

    MiniMax's million-token multimodal model for coding, agents, computer use, and long projects at a low direct API price.

    Open full comparison

  19. Kimi K3 vs GLM-5.3

    Z.ai's open-weight long-context reasoning model for coding, tools, and agentic work across self-hosted and managed routes.

    Open full comparison

  20. Kimi K3 vs Falcon-H1R-7B

    TII's compact open reasoning model for text tasks, long contexts, and self-hosted function-calling workflows.

    Open full comparison

  21. Kimi K3 vs Falcon-H1-34B-Instruct

    TII's 34B open instruction model for multilingual text, coding, and controlled self-hosted applications.

    Open full comparison

  22. Kimi K3 vs Muse Spark 1.3

    Meta's latest multimodal reasoning model for long-running agents, coding, tools, and complex user collaboration.

    Open full comparison

  23. Kimi K3 vs Celeris-1 Magnus

    Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.

    Open full comparison

  24. Kimi K3 vs NVIDIA Nemotron 3 Ultra

    NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.

    Open full comparison

  25. Kimi K3 vs NVIDIA Nemotron 3.5 Lightning

    NVIDIA's compact 30B mixture-of-experts model for efficient specialist agents and high-volume text workflows.

    Open full comparison

  26. Kimi K3 vs Qwen3.8-Flash

    Alibaba's efficient million-context multimodal model for fast agents, coding, document work, vision, video understanding, and tool use.

    Open full comparison

  27. Kimi K3 vs DeepSeek-V4-Pro

    DeepSeek's flagship million-context text model for difficult reasoning, coding, long-running agents, tools, and very large outputs.

    Open full comparison

  28. Kimi K3 vs DeepSeek-V4-Flash

    DeepSeek's lower-cost V4 model for high-volume reasoning, coding, agents, and million-token text workloads.

    Open full comparison