Moonshot AI Models
Usage
78.6B
426K
21 of 31
- kimi-k3
- kimi-k2.6
- coding-kimi-k3
- kimi-k2.5
- kimi-k2.7-code-highspeed
- coding-kimi-k3-free
- kimi-k2.7-code
- kimi-for-coding-free
- 4 more models
- kimi-k3
- kimi-k2.5
- kimi-k2.6
- coding-kimi-k3
- kimi-k2.7-code
- coding-kimi-k3-free
- kimi-k2.7-code-highspeed
- k2.6-code-preview-free
- 13 more models
Which models that traffic went to
- Kimi K382.9%65.2B
- Kimi K2.64.1%3.2B
- Coding Kimi K33.9%3.1B
- Kimi K2.53.2%2.5B
- Kimi K2.7 Code Highspeed2.2%1.7B
- Coding Kimi K3 (free)1.9%1.5B
- Kimi K2.7 Code1.8%1.4B
- Kimi For Coding (free)<0.1%13.8M
- 4 more models<0.1%18.6M
- Kimi K349.9%212K
- Kimi K2.522.5%96K
- Kimi K2.610.4%44.5K
- Coding Kimi K37.3%31.1K
- Kimi K2.7 Code4.3%18.1K
- Coding Kimi K3 (free)4.1%17.6K
- Kimi K2.7 Code Highspeed1.0%4.3K
- K2.6 Code Preview (free)0.2%667
- 13 more models0.3%1.1K
All 31 Moonshot AI Models
Open in model list| Modalities | |||||||
|---|---|---|---|---|---|---|---|
| coding-kimi-k3-free | Takes text, vision, video, returns text. | 1.05M | — | FreeFree/M | Free/M | 73 tok/s | 0.91 s |
| coding-kimi-k3 | Takes text, vision, video, returns text. | 1.05M | — | $0.44$1.6133/M | $0.066/M | 73 tok/s | 0.91 s |
| kimi-k3 | Takes text, vision, video, returns text. | 1.05M | — | $3$15/M | $0.3/M | 73 tok/s | 0.91 s |
| k2.6-code-preview-free | Takes text, vision, video, returns text. | 262K | 256K | FreeFree/M | — | — | — |
| cc-k2.6-code-preview | Takes text, vision, video. Output modality not published. | 262K | — | $0.2$0.2/M | $0.02/M | — | — |
| kimi-k2-thinking | Takes text, returns text. | 262K | — | $0.548$2.192/M | $0.137/M | 44 tok/s | 1.94 s |
| kimi-k2.5 | Takes text, vision, video, returns text. | 262K | — | $0.6$3/M | $0.105/M | 80 tok/s | 1.31 s |
| kimi-k2.6 | Takes text, vision, video, returns text. | 262K | 33K | $0.95$3.9995/M | $0.1608/M | 103 tok/s | 1.55 s |
| kimi-k2.7-code | Takes text, vision, video, returns text. | 262K | 33K | $0.95$3.9995/M | $0.1608/M | 43 tok/s | 1.65 s |
| kimi-k2-turbo-preview | Takes text, returns text. | 262K | 8K | $1.2$4.8/M | $0.3/M | 20 tok/s | 3.06 s |
| kimi-k2.7-code-highspeed | Takes text, vision, video, returns text. | 262K | 33K | $1.9$7.999/M | $0.3217/M | 28 tok/s | 3.92 s |
| kimi-for-coding-free | Takes text, vision, video, returns text. | 256K | 33K | FreeFree/M | — | — | — |
| sf-kimi-k2-thinking | 256K | — | $0.548$2.192/M | — | 42 tok/s | 1.63 s | |
| kimi-k2-0711 | Takes text, returns text. | 131K | 16K | $0.54$2.16/M | — | 50 tok/s | 0.78 s |
| cc-kimi-for-coding | — | — | $0.2$0.2/M | $0.02/M | — | — | |
| moonshotai/Moonlight-16B-A3B-Instruct | — | — | $0.2$0.2/M | — | — | — | |
| cc-kimi-dev-72b | — | — | $0.32$1.28/M | — | — | — | |
| moonshotai/Kimi-Dev-72B | — | — | $0.32$1.28/M | — | — | — | |
| kimi-k2-instruct | Takes text, returns text. | — | — | $0.54$2.16/M | — | 40 tok/s | 0.10 s |
| alicloud-kimi-k2-instruct | — | — | $0.548$2.192/M | — | 30 tok/s | 2.87 s | |
| alicloud-kimi-k2-thinking | — | — | $0.548$2.192/M | — | — | — | |
| cc-kimi-k2-thinking | — | — | $0.548$2.192/M | — | — | — | |
| cc-kimi-k2-instruct | Takes text, returns text. | — | — | $1.1$3.3/M | — | — | — |
| cc-kimi-k2-instruct-0905 | Takes text, returns text. | — | — | $1.1$3.3/M | — | — | — |
| moonshot-v1-8k | — | — | $2$2/M | — | — | — | |
| moonshot-v1-8k-vision-preview | — | — | $2$2/M | — | — | — | |
| moonshot-v1-32k | — | — | $4$4/M | — | — | — | |
| moonshot-v1-32k-vision-preview | — | — | $4$4/M | — | — | — | |
| moonshot-v1-128k | — | — | $10$10/M | — | — | — | |
| moonshot-v1-128k-vision-preview | — | — | $10$10/M | — | — | — | |
| kimi-thinking-preview | — | — | $30$30/M | — | — | — |
Moonshot AI on AIHubMix
Which Moonshot AI model should I start with?
coding-kimi-k3-free is free on input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to kimi-thinking-preview when answer quality matters more than cost, or to coding-kimi-k3 for long-form reasoning.
Which of these models reason before answering?
10 of the 31 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.
Why are there several entries for the same model?
Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (moonshotai/…), and some differ only in capitalisation, kept so older integrations keep working.
The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.
How is cached input billed?
The Cache read column is the rate for input tokens served from the prompt cache — for example cc-k2.6-code-preview bills cache hits at 10% of the input rate and cc-kimi-for-coding bills cache hits at 10% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.
Do I need a separate Moonshot AI account?
No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.
Start calling Moonshot AI in one line
One key, one endpoint, 881 models across 39 model authors.
