MoonshotAI: Kimi Latest
~moonshotai/kimi-latest · Moonshot AIUnmeasurable- Declared family
- Router
- Declared tokenizer tag
- Router
- Entered catalogue
- 27 April 2026
- Measurement
- Excluded: a router, not one stable model
- Evidence confidence
- Unknown
This catalogue entry is an alias: a name that points at another model rather than a model of its own. Its serving contract is listed below; the identity evidence lives on the record of the model it serves.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Not measured yet | we measured it |
| How its API is set up | Set up identically to 1 other listing, field for field | api_afde644c |
| How much it can read and write | Reads up to 1,048,576 tokens at onceOpenRouter's listing shows 943,718 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. | its own listing |
| Whether it thinks before answering | Reasons when asked to, at max, high, low, max by default | its own listing |
This model always redirects to the latest model in the Kimi family.
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}