Moonshot
Kimi API
Moonshot's Kimi models — a frontier tier and a coding-specialised one.
2
моделей в линейке
Kimi splits by specialisation rather than by size: K3 is Moonshot's frontier model for long-context reasoning and agentic tool use, and K2.7 Code is tuned for repository-scale edits and agentic software tasks. The two are priced within about six percent of each other on input, so the choice is about what the model was trained for, not about budget.
Коротко
- От
- 1.48 coins / 1 млн токенов
Модели этого семейства
| Модель | От | Режимы | Открыть |
|---|---|---|---|
| Kimi K3Moonshot's frontier model — long-context reasoning and agentic tool use. | 1.48 coins/ 1 млн токенов | — | ОткрытьДокументация |
| Kimi K2.7 CodeCoding-specialised Kimi tier tuned for repository-scale edits and agentic software tasks. | 1.57 coins/ 1 млн токенов | — | ОткрытьДокументация |
Цены
| Модель | Вариант | Цена |
|---|---|---|
| Kimi K3 | input | 1.48 coins/ 1 млн токенов |
| Kimi K3 | output | 7.4 coins/ 1 млн токенов |
| Kimi K3 | cacheRead | 0.148 coins/ 1 млн токенов |
| Kimi K2.7 Code | input | 1.57 coins/ 1 млн токенов |
| Kimi K2.7 Code | output | 7.13 coins/ 1 млн токенов |
| Kimi K2.7 Code | cacheRead | 0.265 coins/ 1 млн токенов |
Что выбрать
Kimi K3
Long-context reasoning and agentic tool use — the general frontier tier.
Kimi K2.7 Code
Repository-scale code edits and agentic software work, where a coding-tuned model beats a general one.
Сильные стороны
- A coding-specialised tier that is not just the general model with a different prompt.
- Input prices sit within about six percent of each other, so specialisation does not cost extra.
- Prompt caching on both tiers.
- OpenAI-protocol compatible.
Ограничения
- K3's cache reads are discounted to a tenth of input while K2.7 Code only reaches about a sixth, so caching pays back differently per tier.
- Output costs four and a half to five times input on both tiers.
- Only two tiers, both at a similar price point — no cheap volume option.
Описание линейки от самого вендора: Moonshot AI — docs