# kimi-k3.1-pro-highspeed [Canonical model page](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `moonshot-ai-kimi-k3-1-pro-highspeed`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about kimi-k3.1-pro-highspeed AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed#model-answer-identity) · [Access](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed#model-answer-access) · [Token limits](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed#model-answer-context) · [Inputs & outputs](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed#model-answer-modalities) · [Model details](https://headlessthrones.com/models/moonshot-ai-kimi-k3-1-pro-highspeed#model-answer-research) ### Which kimi-k3.1-pro-highspeed does this page describe? kimi-k3.1-pro-highspeed is a model record from **Moonshot AI** in the Kimi family. [Source](https://platform.kimi.com/docs/api/models-overview) The recorded model identifier or checkpoint is `kimi-k3.1-pro-highspeed`. Use that exact identifier when checking documentation or a provider listing. [Source](https://platform.kimi.com/docs/api/models-overview) ### How can you access kimi-k3.1-pro-highspeed? The catalog documents **API** access for kimi-k3.1-pro-highspeed. [Source](https://platform.kimi.com/docs/api/models-overview) As of the catalog check, this version was listed as available. [Source](https://platform.kimi.com/docs/api/models-overview) For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription. ### What are kimi-k3.1-pro-highspeed's context and output limits? The documented **context window is 1,000,000 tokens**. [Source](https://platform.kimi.com/docs/api/models-overview) A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance. Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity. ### What can kimi-k3.1-pro-highspeed receive and generate? Documented outputs: **text**. [Source](https://platform.kimi.com/docs/api/models-overview) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What distinguishes kimi-k3.1-pro-highspeed? These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results. **Reasoning controls**: The parameter reference explicitly applies K3 constraints to this exact K3.1 variant: reasoning\_effort accepts low, high or max, with max as default; preserved thinking stays enabled. [Source](https://platform.kimi.com/docs/api/models-overview) **Tool and sampling constraints**: tool\_choice accepts auto, none and required. temperature is fixed at 1, top\_p at 0.95, n at 1, and presence/frequency penalties at 0; other fixed-parameter values can error. [Source](https://platform.kimi.com/docs/api/models-overview) **Message preservation**: For multi-turn conversations and tool use, return the full assistant message, including any reasoning\_content, to the next messages array. [Source](https://platform.kimi.com/docs/api/models-overview) **Catalog qualifications:** Listed in the current parameter overview; that page says parameters are shared with kimi-k3. [Source](https://platform.kimi.com/docs/api/models-overview) **Evidence still missing here:** complete input/output pricing and knowledge and training-data cutoffs. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other Kimi models from Moonshot AI. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [Kimi-Dev-72B](https://headlessthrones.com/models/moonshot-ai-kimi-dev-72b) Open weights ### [Kimi-K2-Base](https://headlessthrones.com/models/moonshot-ai-kimi-k2-base) Open weights ### [Kimi-K2-Instruct](https://headlessthrones.com/models/moonshot-ai-kimi-k2-instruct) Open weights ### [Kimi-K2-Instruct-0905](https://headlessthrones.com/models/moonshot-ai-kimi-k2-instruct-0905) Open weights ### [Kimi-K2-Thinking](https://headlessthrones.com/models/moonshot-ai-kimi-k2-thinking) Open weights ### [Kimi-K2.5](https://headlessthrones.com/models/moonshot-ai-kimi-k2-5) Open weights