{"generated_at":"2026-10-14T14:17:02.794Z","board":"Cheapest 200k+ context models","units":"USD per 1M tokens","model_count":50,"preview":true,"note":"Free preview: 5 of 50 rows (newest first). Pay $0.01 on /llm/cheapest/long-context for the full board, sorted cheapest first.","models":[{"id":"sail/Qwen/Qwen3.6-35B-A3B","provider":"sail","input_per_mtok":0.05,"output_per_mtok":0.4,"cache_read_per_mtok":0.02,"cache_write_per_mtok":null,"batch_input_per_mtok":null,"batch_output_per_mtok":null,"openrouter_input_per_mtok":0.1,"openrouter_output_per_mtok":0.95,"price_agreement":"drift","source_url":null,"first_observed_at":"2026-09-26T20:17:02.789Z","confidence":"low","context_window":262144,"max_output_tokens":262144,"supports_vision":true,"supports_function_calling":true,"supports_reasoning":true},{"id":"aihubmix/coding-glm-5.3","provider":"aihubmix","input_per_mtok":0.06,"output_per_mtok":0.22,"cache_read_per_mtok":0.015,"cache_write_per_mtok":null,"batch_input_per_mtok":null,"batch_output_per_mtok":null,"openrouter_input_per_mtok":null,"openrouter_output_per_mtok":null,"price_agreement":"unverified","source_url":null,"first_observed_at":"2026-09-15T23:17:02.421Z","confidence":"medium","context_window":1048576,"max_output_tokens":131072,"supports_vision":false,"supports_function_calling":true,"supports_reasoning":true},{"id":"aihubmix/cc-glm-5.1","provider":"aihubmix","input_per_mtok":0.06,"output_per_mtok":0.22,"cache_read_per_mtok":null,"cache_write_per_mtok":null,"batch_input_per_mtok":null,"batch_output_per_mtok":null,"openrouter_input_per_mtok":null,"openrouter_output_per_mtok":null,"price_agreement":"unverified","source_url":null,"first_observed_at":"2026-09-15T23:17:02.421Z","confidence":"medium","context_window":200000,"max_output_tokens":131072,"supports_vision":false,"supports_function_calling":true,"supports_reasoning":true},{"id":"gpt-5-nano","provider":"openai","input_per_mtok":0.05,"output_per_mtok":0.4,"cache_read_per_mtok":0.005,"cache_write_per_mtok":null,"batch_input_per_mtok":0.025,"batch_output_per_mtok":0.2,"openrouter_input_per_mtok":0.05,"openrouter_output_per_mtok":0.4,"price_agreement":"match","source_url":"https://platform.openai.com/docs/pricing","first_observed_at":"2026-07-16T23:17:02.557Z","confidence":"high","context_window":272000,"max_output_tokens":128000,"supports_vision":true,"supports_function_calling":true,"supports_reasoning":true},{"id":"azure/gpt-5-nano","provider":"azure","input_per_mtok":0.05,"output_per_mtok":0.4,"cache_read_per_mtok":0.005,"cache_write_per_mtok":null,"batch_input_per_mtok":0.025,"batch_output_per_mtok":0.2,"openrouter_input_per_mtok":0.05,"openrouter_output_per_mtok":0.4,"price_agreement":"match","source_url":"https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/","first_observed_at":"2026-07-16T23:17:02.557Z","confidence":"high","context_window":272000,"max_output_tokens":128000,"supports_vision":true,"supports_function_calling":true,"supports_reasoning":true}],"next_refresh_at":"2026-10-14T15:22:03.313Z","see_also":[{"path":"/llm/prices","price":"$0.02","why":"every model across every provider, not just this slice"},{"path":"/llm/cheapest","price":"$0.01","why":"rank by blended cost for your own token mix"},{"path":"/llm/price-changes","price":"$0.03","why":"what repriced since your last pull"}]}