Kimi K3
FrontierVisionToolsMoonshotAI · Released July 2026
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
It belongs to Moonshot AI's Kimi K2 family, open-weight models known for agentic tool use, with Code and Thinking variants for their namesake strengths.
Facts and pricing
- Provider
- MoonshotAI
- Context window
- 1.0M tokens
- Input price
- 33.0 credits / 1M tokens ($3.00 raw)
- Output price
- 165 credits / 1M tokens ($15.00 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Kimi K3 now
What Kimi K3 is best for
- Hard problems where answer quality matters more than cost: strategy, analysis, difficult writing
- Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a frontier model like Kimi K3:
- Review this business plan and give me the three hardest questions an investor would ask
- Rewrite this announcement so it lands with both engineers and executives
- I am choosing between two job offers, help me think through the tradeoffs
- Draft a technical design doc for a rate limiter, including failure modes
MoonshotAI family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Kimi K3 | 1.0M | 33.0 | 165 | July 2026 |
| Kimi K2.7 Code | 262K | 7.4 | 37.4 | June 2026 |
| Kimi K2.7 Code (batch) | 262K | 10.5 | 44.0 | June 2026 |
| Kimi K2.6 | 262K | 6.0 | 25.1 | April 2026 |
| Kimi K2.5 | 262K | 5.0 | 24.8 | January 2026 |
| Kimi K2 Thinking | 262K | 6.6 | 27.5 | November 2025 |
| Kimi K2 0905 | 262K | 6.6 | 27.5 | September 2025 |
| Kimi K2 0711 | 131K | 6.3 | 25.3 | July 2025 |
Frequently asked questions
- What is Kimi K3?
- Kimi K3 is an AI model by MoonshotAI. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
- How much does Kimi K3 cost on Zeplik?
- Input tokens cost 33.0 credits per million and output tokens 165 credits per million (1 credit = $0.10; the raw provider rates are $3.00 and $15.00 per million). New accounts start with free credits.
- How long can a conversation with Kimi K3 be?
- Kimi K3 has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
- Does Kimi K3 support images and tools?
- Kimi K3 accepts image input and supports tool calling.
Related models
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
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...
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
More you can do with Kimi K3
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Kimi K3 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.