MoonshotAI: Kimi K3moonshotai
Bottom Line
MoonshotAI: Kimi K3: $0.24/1M input, $10.80/1M output, 1.0M context. 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...
API Pricing (per 1M tokens)
| Input | $0.24 |
| Output | $10.80 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $2.88 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 944K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, image, video → text |
More from moonshotai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the MoonshotAI: Kimi K3 API cost?
MoonshotAI: Kimi K3 costs $0.24/1M input tokens and $10.80/1M output tokens. Blended cost at a 3:1 ratio is about $2.88/1M tokens.
What is the context window of MoonshotAI: Kimi K3?
MoonshotAI: Kimi K3 supports a 1.0M token context window with up to 944K output tokens.
Is MoonshotAI: Kimi K3 worth it?
MoonshotAI: Kimi K3 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.