// Guide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
| name | pricing |
| description | Guide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data. |
Token pricing is defined in src/models.rs using compile-time phf (perfect hash function) maps for fast lookups.
ModelInfo entry to MODEL_INDEX (line 65 in src/models.rs) with:
pricing: Use PricingStructure::Flat { input_per_1m, output_per_1m } for flat-rate models, or PricingStructure::Tiered for tiered pricingcaching: Use the appropriate CachingSupport variant (None, OpenAI, Anthropic, or Google)is_estimated: Set to true if pricing is not officially publishedMODEL_ALIASES mapping to the canonical model nameSee existing entries in src/models.rs for the pattern.
Use models::calculate_total_cost() when an analyzer doesn't provide cost data.
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.
Reference for Splitrail's core data types. Use when working with ConversationMessage, Stats, DailyStats, or other type definitions.