Inception: Mercury 3

{"about":"### A diffusion-based text model\n\nMercury 3 is an Inception model that uses a diffusion approach to text generation. It continues the Mercury family, which the developer is building for interactive applications and tasks involving several successive model calls. In its Mercury 3 description, Inception highlights conversational support, education, data work and search-oriented agentic workflows.\n\nThe diffusion architecture is a property of the model. It does not determine an application’s response time: the outcome also depends on request size, response length and serving conditions. In Ailoot API, Mercury 3 accepts text and returns text. This interface suits explanations, document processing and preparation of the next task step based on supplied information.\n\n### A large context for connected work\n\nMercury 3 has a stated context of 1,000,000 tokens in Ailoot API. A single discussion can bring together a large collection of text material: product descriptions, rules, correspondence and output requirements. A large context is useful when the answer needs to consider several parts of a task at once—for example, comparing support instructions with contract terms to prepare a reply to a particular request.\n\nFor this type of request, label the documents, retain their titles and ask the model to identify the material supporting each conclusion. If the task has several steps, define intermediate outputs: first a list of relevant rules, then a case analysis, followed by a draft reply. This makes the result easier to verify and lets you refine one stage without describing the entire task again.\n\n### Interactive uses\n\nIn an educational conversation, Mercury 3 can help explain a solution, prepare a hint or explain a concept at a specified level. For data work, provide field descriptions, a text sample and a question to obtain an explanation of patterns or a transformation plan. For support, supply the rules and request a clear reply that takes the user’s circumstances into account.\n\nThese workflows use the text model as part of a broader process. Independent web search, browser control, access to company systems and voice conversation depend on the application’s connected tools. Mercury Voice and Mercury Decide are separate Inception products; their specialized capabilities are outside this Mercury 3 description.","alias_of":null,"aliases":[],"author":"Inception","canonical_model":"inception/mercury-3","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"inception/mercury-3","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.02,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"anthropic","fast_multiplier":1,"flex_multiplier":1,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":0.2,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/messages","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":0.2,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/responses","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":0.2,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/chat/completions","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"gemini","fast_multiplier":1,"flex_multiplier":1,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":0.2,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1beta/models/inception/mercury-3:generateContent","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"inception/mercury-3","request_model_id":"inception/mercury-3","route_label":"Ultra"}],"name":"Inception: Mercury 3","price":{"in":0.2,"in_label":null,"out":0.7,"out_label":null,"sort_in":0.2,"sort_out":0.7,"varies":false},"public_id":"inception/mercury-3","short":"Inception’s diffusion-based text model for conversations, large documents and successive knowledge-work tasks."}