k3.1-pro-highspeed

{"about":"Kimi K3.1 Pro Highspeed is a distinct K3.1 Pro variant that Moonshot AI introduced alongside the series’ main model. The developer presents it as a version focused on interaction speed. In Ailoot API, it has its own listing and the exact identifier `k3.1-pro-highspeed`, allowing you to select it separately from the regular K3.1 Pro.\n\n### For iterative work\n\nUse this variant in a text workflow where the result is refined over several messages: first analyze the task, then choose an approach, and finally prepare usable text or code. For example, provide a program fragment and the desired behavior, receive a proposal, add constraints and ask for a specific section to be revised.\n\nAnother use case is material analysis. Add excerpts from several documents, state your questions and ask for a brief conclusion followed by an explanation for each source. For a long discussion, retain the goal, accepted decisions and open questions so that the next response has a clear foundation.\n\n### What to include in a request\n\n- The task and output type: an explanation, plan, program code or analytical text.\n- Source data with section names and their order of priority.\n- Constraints to consider when preparing the response.\n- Verification criteria: which conditions must hold and which details must be explained.\n\nYou can ask for a comparison of options, step-by-step instructions or an explanation of a code change. For calculations, specify the units and source values; for a report, state the audience, structure and length. These details make the result easier to use in subsequent work.\n\n### Format and size\n\nThe listing accepts text input and returns text. You can supply instructions, conversation history, documents in text form and code. Standard has limits of up to 262,144 input tokens and 65,536 response tokens. Account for history and supplied material when composing a large request. For substantial work, establish an overall plan, then examine individual parts in sequence and retain intermediate conclusions.","alias_of":null,"aliases":[],"author":"MoonshotAI","canonical_model":"k3.1-pro-highspeed","ctx":262144,"formats":["chat","gemini","messages","responses"],"id":"k3.1-pro-highspeed","input":["text"],"kind":"text","max_out":65536,"methods":[{"cache_read":0.2,"cache_write":4.0,"cache_write_1h":null,"cache_write_5m":4.0,"conditional_meter":null,"ctx":262144,"family":"anthropic","fast_multiplier":null,"flex_multiplier":null,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":4.0,"input":["text"],"label":"Anthropic Messages","max_out":65536,"max_tool_calls":null,"out":20.0,"output":["text"],"path":"/v1/messages","request_model_id":"k3.1-pro-highspeed","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.2,"cache_write":4.0,"cache_write_1h":null,"cache_write_5m":4.0,"conditional_meter":null,"ctx":262144,"family":"openai","fast_multiplier":null,"flex_multiplier":null,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":4.0,"input":["text"],"label":"OpenAI Responses","max_out":65536,"max_tool_calls":null,"out":20.0,"output":["text"],"path":"/v1/responses","request_model_id":"k3.1-pro-highspeed","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.2,"cache_write":4.0,"cache_write_1h":null,"cache_write_5m":4.0,"conditional_meter":null,"ctx":262144,"family":"openai","fast_multiplier":null,"flex_multiplier":null,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":4.0,"input":["text"],"label":"OpenAI Chat","max_out":65536,"max_tool_calls":null,"out":20.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"k3.1-pro-highspeed","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.2,"cache_write":4.0,"cache_write_1h":null,"cache_write_5m":4.0,"conditional_meter":null,"ctx":262144,"family":"gemini","fast_multiplier":null,"flex_multiplier":null,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":4.0,"input":["text"],"label":"Gemini generateContent","max_out":65536,"max_tool_calls":null,"out":20.0,"output":["text"],"path":"/v1beta/models/{model}:generateContent","request_model_id":"k3.1-pro-highspeed","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"k3.1-pro-highspeed","request_model_id":"k3.1-pro-highspeed","route_label":"Core"}],"name":"k3.1-pro-highspeed","price":{"in":4.0,"in_label":null,"out":20.0,"out_label":null,"sort_in":4.0,"sort_out":20.0,"varies":false},"public_id":"k3.1-pro-highspeed","short":"Kimi K3.1 Pro Highspeed is a distinct K3.1 Pro variant for text conversations, material analysis and code preparation through iterative work."}