All models
Text & reasoningStable
Moonshot AIKimi K3
Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
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)
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
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 availabilityData 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 policyFrequently 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
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Small 4$0.15
Mistral AI
- Gemini 3.8 Flash$0.75
Google
- GPT-5.6 Sol$4.00
OpenAI
- GPT-6 Astra$10.00
OpenAI
- Claude Fable 5.1$10.00
Anthropic
- Mistral Small 4$0.60
Mistral AI
- Gemini 3.8 Flash$3.75
Google
- GPT-5.6 Sol$20.00
OpenAI
- GPT-6 Astra$50.00
OpenAI
- Claude Fable 5.1$50.00
Anthropic
Related comparisons
Head-to-head comparisons
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 comparisonKimi 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 comparisonKimi 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 comparisonKimi 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 comparisonKimi 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 comparisonKimi 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 comparisonKimi K3 vs Inkling
Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.
Open full comparisonKimi 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 comparisonKimi 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 comparisonKimi K3 vs Qwen3.8 Max
Alibaba's frontier Qwen model for long-context reasoning, coding, tools, and understanding text, images, and video.
Open full comparisonKimi 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 comparisonKimi 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 comparisonKimi K3 vs Falcon-H1R-7B
TII's compact open reasoning model for text tasks, long contexts, and self-hosted function-calling workflows.
Open full comparisonKimi K3 vs Falcon-H1-34B-Instruct
TII's 34B open instruction model for multilingual text, coding, and controlled self-hosted applications.
Open full comparisonKimi K3 vs Muse Spark 1.3
Meta's latest multimodal reasoning model for long-running agents, coding, tools, and complex user collaboration.
Open full comparisonKimi K3 vs Celeris-1 Magnus
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
Open full comparisonKimi 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 comparisonKimi 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 comparisonKimi 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 comparisonKimi 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 comparisonKimi 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
