Model prices / Moonshot AI / Kimi K2 Instruct
Kimi K2 InstructOpen weights
Moonshot AI · released 2025-07-11
No price from the maker itself is on record for Kimi K2 Instruct. The lowest of 5 providers is NanoGPT: $0.4 per 1M input tokens and $1.8 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 16.4K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestmoonshotai/ | $0.4 | $1.8 | $0.2 | Lowest | Official docs |
NNanoGPTmoonshotai/ | $0.4 | $1.8 | $0.2 | Official docs | |
EEden AIdeepinfra/ | $0.5 | $2 | — | Official docs | |
JJiekou.AImoonshotai/ | $0.57 | $2.3 | — | Official docs | |
 Novita AImoonshotai/ | $0.57 | $2.3 | — | Official docs | |
 Hugging Facemoonshotai/ | $1 | $3 | — | Official docs | |
NNanoGPTDeprecatedkimi-k2-instruct-fast | $0.4 | $1.8 | $0.2 | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 16.4K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Knowledge cutoff
- 2024-10
- Open weights
- Yes
- Released
- 2025-07-11
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.