Blue Book ledger
The estimate is only as credible as its rate basis.
Class1 keeps a frozen, effective-dated, provenance-aware data layer so every PR estimate can be reproduced and audited.
Why the ledger matters
The hard part is not displaying a price. The hard part is knowing which price was used, when, and why.
LLM vendors change prices, aggregators rename models, context tiers appear, cache discounts differ by provider, and frontier model releases can reset capability assumptions overnight. A PR estimate that uses a live feed without freezing the basis is difficult to reproduce later.
Class1 treats the pricing basis like an estimator treats a cost book. Raw artifacts are preserved with provenance, normalized into silver rows, and curated into a gold snapshot. The estimate can say which basis it used, how old that basis is, and which items were measured, inferred, assumed, excluded, or unpriced.
That makes the Blue Book commercially important. A public basis proves the open-core product. A private basis becomes the paid pilot: customer-specific rates, private actuals, internal model allowances, team allocation rules, and variance reports that cannot be copied from a public dashboard.
Medallion discipline
Bronze raw source. Silver normalizer. Gold estimate basis.
Prices, specs, capability, cloud cost, actuals, carbon, water, and materials all live as frozen snapshots.
The product can refresh the basis, but an estimate never silently depends on a live feed. Staleness is modeled as estimate decay.
What a buyer gets from the Blue Book
A credible estimate needs more than a token price table.
Capability sample
Real coding grades join the price basis.
| Model | Provider | SWE-Bench score | Date |
|---|---|---|---|
| claude-opus-4-5 | anthropic | 79.2% | 2025-12-05 |
| claude-opus-4-5-20251101 | anthropic | 79.2% | 2025-12-15 |
| Doubao-Seed-Code | unknown | 78.8% | 2025-09-28 |
| gemini-3-pro-preview | 77.4% | 2025-11-20 | |
| claude-sonnet-4-20250514 | anthropic | 76.8% | 2025-08-04 |
| claude-4-sonnet | anthropic | 76.4% | 2025-08-19 |
| gpt-5 | openai | 75.6% | 2025-09-01 |
| claude-4-sonnet-20250522 | anthropic | 75.2% | 2025-06-12 |
| claude-sonnet-4-5 | anthropic | 74.8% | 2025-11-03 |
| claude-4-sonnet-20250514 | anthropic | 74.6% | 2025-07-20 |
| claude-sonnet-4.5 | anthropic | 73.8% | 2025-11-03 |
| claude-4-opus-20250514 | anthropic | 73.2% | 2025-05-22 |