Moonshot AI · LLMs & Coding
Kimi K3
Catalog data · checked Nov 16, 2026
Kimi K3 is a language model from Moonshot AI, released in July 2026. It reads text, images and video and writes text, with a context window of 1.05M tokens and up to 1.05M output tokens per answer. It costs $3 per million input tokens and $15 per million output tokens. That puts it in the upper price range: 88% of the 185 paid language models we track cost less.
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
More prices
| Cached input (read) | $0.3 /1M |
| Cache write | $3 /1M |
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $6.15 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.48 |
| 10,000 product descriptions300 input and 200 output tokens per text | $39 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $11.25 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare Kimi K3 with
Questions & answers
How much does Kimi K3 cost?
Kimi K3 costs $3 per 1 million input tokens and $15 per 1 million output tokens (USD, list price checked Nov 16, 2026).
How large is the context window of Kimi K3?
Kimi K3 can process up to 1,048,576 tokens per request and return up to 1,048,576 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does Kimi K3 support tool calling?
Yes. The API accepts tool (function) definitions and also supports structured JSON output.
Can Kimi K3 read images?
Yes, image input is supported.
