model-mix

1# Model Mix
2 
3See where your tokens and dollars go by model family, and where to re-route work.
4 
5## Input
6 
7The user provides: **$ARGUMENTS**
8 
9This may be: empty (analyze the whole fleet), "today" / "this week" / a date range, or a focus like "where is Opus overused?". When empty, analyze all data from `/api/pricing/cost` and `/api/sessions`.
10 
11## Data Sources
12 
13| Endpoint | Returns |
14|----------|---------|
15| `GET /api/pricing/cost` | `{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` — per-model token and cost split |
16| `GET /api/pricing` | `{ pricing: [{ model_pattern, display_name, input_per_mtok, output_per_mtok, cache_read_per_mtok, cache_write_per_mtok }] }` — rates per family |
17| `GET /api/analytics` | `tokens` totals (total_input, total_output, total_cache_read, total_cache_write — baselines pre-summed), `agent_types` for delegation context |
18| `GET /api/sessions?limit=200` | Session list — model, cwd, started_at, ended_at, inline `cost`, metadata (JSON: thinking_blocks, turn_count, total_turn_duration_ms, usage_extras) |
19 
20### How families and rates work
21 
22Map each `model` in the cost breakdown to a family from its `matched_rule` / `display_name`:
23 
24| Family | Input $/Mtok | Output $/Mtok | Cache Read $/Mtok | Cache Write $/Mtok |
25|--------|-------------|--------------|-------------------|-------------------|
26| Opus 4.5/4.6 | $5 | $25 | $0.50 | $6.25 |
27…