Source: https://ailoot.ai/models/en/unbiased-pareto-26-9/ Canonical: https://ailoot.ai/models/en/unbiased-pareto-26-9/ Language: en # Pareto 26.9 [Markdown](https://ailoot.ai/models/en/unbiased-pareto-26-9/index.md) · [JSON](https://ailoot.ai/models/en/unbiased-pareto-26-9/facts.json) ## [Pareto 26.9](https://ailoot.ai/models/en/unbiased-pareto-26-9/) `unbiased/pareto-26.9` UnbiasedTextInput $0.005 / 1KOutput $0.015 / 1K The earlier version of Unbiased’s composite text model, with a 262,144-token context for explicitly pinned workflows. ### An earlier Pareto release Pareto 26.9 is a distinct version of Unbiased’s composite model. In the Pareto family, a request is processed with the participation of several frontier and open models, and their results are combined into one response. The user works with a single Pareto model rather than selecting each component manually. The developer states that the set of underlying models can change. Version 26.9 remained available after the stable 26.10 release. Its exact identifier, `unbiased/pareto-26.9`, lets an application explicitly select the previous release. This is useful for existing workflows and comparisons that need to name the version being used instead of moving automatically to the next one. Pinning the name does not make the internal model composition immutable. ### Working with supplied material In Ailoot API, this version accepts text and produces a text response. Its context window is 262,144 tokens, including instructions, history, source material and the response; the model’s metadata lists output of up to 131,072 tokens. Release 26.10 has a larger context window, so when choosing 26.9, select genuinely relevant documents and passages in advance. A workflow can center on comparing several texts. Provide requirements, proposed solutions and selection criteria, then request a comparison table with reasoning for each criterion. For a long document, define the purpose of the analysis: identifying contradictions, preparing a focused summary, collecting questions for the author or drafting a revised structure. Naming the source passages helps link conclusions to data within the request. ### Technical conversations When analyzing a programming task, include the relevant code and the execution result already obtained in your environment. Ask the model to explain the observation, propose a change and list the signs by which its result can be verified. In the next message, provide the verification outcome. This ties the text conversation to a real task without assuming that the model itself can access files or the runtime environment. When preparing new text, specify the audience, outline and desired level of detail. The response could be a document draft, a summary of source data, a differences list or a sequence of next actions; your request determines the specific format. Pareto 26.9 is available through Messages, Responses, Chat Completions and text-based generateContent. These formats describe client integration options. In this connection, material is supplied as text; choosing a request format does not add images, code execution or access to external systems. ### Available through Ailoot API Input types `text` Output types `text` Context Not specified in the catalogue Max. output Not specified in the catalogue Input $0.005 */ 1K* Output $0.015 */ 1K* Cache read $0.0005 */ 1K* Input types `text` Output types `text` Context Not specified in the catalogue Max. output Not specified in the catalogue Input $0.005 */ 1K* Output $0.015 */ 1K* Cache read $0.0005 */ 1K* Input types `text` Output types `text` Context Not specified in the catalogue Max. output Not specified in the catalogue Input $0.005 */ 1K* Output $0.015 */ 1K* Cache read $0.0005 */ 1K* Input types `text` Output types `text` Context Not specified in the catalogue Max. output Not specified in the catalogue Input $0.005 */ 1K* Output $0.015 */ 1K* Cache read $0.0005 */ 1K* `unbiased/pareto-26.9` · JSON ``` {"about":"### An earlier Pareto release\n\nPareto 26.9 is a distinct version of Unbiased’s composite model. In the Pareto family, a request is processed with the participation of several frontier and open models, and their results are combined into one response. The user works with a single Pareto model rather than selecting each component manually. The developer states that the set of underlying models can change.\n\nVersion 26.9 remained available after the stable 26.10 release. Its exact identifier, `unbiased/pareto-26.9`, lets an application explicitly select the previous release. This is useful for existing workflows and comparisons that need to name the version being used instead of moving automatically to the next one. Pinning the name does not make the internal model composition immutable.\n\n### Working with supplied material\n\nIn Ailoot API, this version accepts text and produces a text response. Its context window is 262,144 tokens, including instructions, history, source material and the response; the model’s metadata lists output of up to 131,072 tokens. Release 26.10 has a larger context window, so when choosing 26.9, select genuinely relevant documents and passages in advance.\n\nA workflow can center on comparing several texts. Provide requirements, proposed solutions and selection criteria, then request a comparison table with reasoning for each criterion. For a long document, define the purpose of the analysis: identifying contradictions, preparing a focused summary, collecting questions for the author or drafting a revised structure. Naming the source passages helps link conclusions to data within the request.\n\n### Technical conversations\n\nWhen analyzing a programming task, include the relevant code and the execution result already obtained in your environment. Ask the model to explain the observation, propose a change and list the signs by which its result can be verified. In the next message, provide the verification outcome. This ties the text conversation to a real task without assuming that the model itself can access files or the runtime environment.\n\nWhen preparing new text, specify the audience, outline and desired level of detail. The response could be a document draft, a summary of source data, a differences list or a sequence of next actions; your request determines the specific format.\n\nPareto 26.9 is available through Messages, Responses, Chat Completions and text-based generateContent. These formats describe client integration options. In this connection, material is supplied as text; choosing a request format does not add images, code execution or access to external systems.","alias_of":null,"aliases":[],"author":"Unbiased","canonical_model":"unbiased/pareto-26.9","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"unbiased/pareto-26.9","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.5,"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":5.0,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":15.0,"output":["text"],"path":"/v1/messages","request_model_id":"unbiased/pareto-26.9","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.5,"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":5.0,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":15.0,"output":["text"],"path":"/v1/responses","request_model_id":"unbiased/pareto-26.9","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.5,"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":5.0,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":15.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"unbiased/pareto-26.9","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.5,"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":5.0,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":15.0,"output":["text"],"path":"/v1beta/models/unbiased/pareto-26.9:generateContent","request_model_id":"unbiased/pareto-26.9","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"unbiased/pareto-26.9","request_model_id":"unbiased/pareto-26.9","route_label":"Ultra"}],"name":"Pareto 26.9","price":{"in":5.0,"in_label":null,"out":15.0,"out_label":null,"sort_in":5.0,"sort_out":15.0,"varies":false},"public_id":"unbiased/pareto-26.9","short":"The earlier version of Unbiased’s composite text model, with a 262,144-token context for explicitly pinned workflows."} ``` ## Questions How do I choose a model for my task? First identify the required input and output: text, image, audio or video. Then compare compatible API methods, the exact model ID or current alias target, price and billing unit. GET /v1/models is free and lists models available to your key. Does each model support every API method and media type? Use the API methods and input/output types listed on the model card. Support for text, images, audio or video depends on the selected model and method; check their request example before sending your data. What is the difference between a model ID and an alias? An exact model ID names a specific model. An alias points to a model and its target can change. Check the current alias target in the catalogue; use the exact ID when your integration needs a specific model. How do I compare prices before sending a request? Check the model card for the price and billing unit of the selected API method. Compare the same unit and input/output type; request history shows actual usage and the charged amount. What does a subscription give me? A discount on token purchases for regular use. Choose a plan for your request volume; subscription terms and pricing are shown at checkout. How do I apply a promo code for up to 50% off? Enter the promo code when buying tokens. The total updates according to the promotion terms; you can see the discount before paying. ## Ailoot · The company and its project portfolio Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control. The company and its project portfolio: millions of customers; monthly sales in the billions. Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.