Elorian: Glimpse

{"about":"### Reasoning about events and space\n\nGlimpse is an Elorian model developed around visual understanding of the physical world. It specializes in maintaining a representation of an object as it moves and the viewpoint changes, connecting actions to consequences and analyzing relationships between parts of a scene. The developer’s official examples demonstrate motion analysis, counting objects while tracking their state and reconstructing the order of events.\n\nGlimpse’s distinctive approach is to revisit visual evidence during problem-solving. In Elorian’s environment, the model can re-examine a relevant area, compare observations and refine its initial interpretation. This explains its focus on tasks where naming objects is insufficient: it must understand what changed, which objects remain the same and how an observation differs from an assumption.\n\n### How to use it in Ailoot API\n\nIn Ailoot API, Glimpse is connected for text input and text output. You can provide a scene description, a sequence of observations, an event transcript or prepared captions and ask questions about that material. Processing the images or videos themselves is outside the model’s current interface.\n\nA practical request can contain an observation log: who did what, when it happened and what was visible before and after the action. Ask for a timeline, a separation of observed facts from possible explanations, and a list of details still needed to reach a conclusion. This format works with a textual representation of the task and explicitly preserves the distinction between supplied information and interpretation.\n\n### What to consider when defining the task\n\nFor a spatial question, identify the observation point and describe the objects’ positions relative to one another. For a sequence of events, retain timestamps and consistent participant labels. If the source text does not say whether motion continued between two observations, ask the model to consider plausible alternatives rather than select a single explanation.\n\nGlimpse has a stated context of 262,144 tokens in Ailoot API, allowing substantial descriptions and discussion history to be included in a request. The result remains text: an explanation, an event table or a list of questions about the source material. Do not automatically extend the capabilities of Elorian’s agent environment, including its visual tools and subtask coordination, to this text interface.","alias_of":null,"aliases":[],"author":"Elorian","canonical_model":"elorian/glimpse","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"elorian/glimpse","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.12,"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":1.2,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/messages","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"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":1.2,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/responses","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"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":1.2,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"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":1.2,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1beta/models/elorian/glimpse:generateContent","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"elorian/glimpse","request_model_id":"elorian/glimpse","route_label":"Ultra"}],"name":"Elorian: Glimpse","price":{"in":1.2,"in_label":null,"out":6.0,"out_label":null,"sort_in":1.2,"sort_out":6.0,"varies":false},"public_id":"elorian/glimpse","short":"An Elorian model for reasoning about scenes and physical events; in Ailoot API, it works with text descriptions and questions."}