Model Pricing Configuration#

Overview#

Langfuse stores model pricing in PostgreSQL via Prisma using three related tables: Model, Price, and PricingTier 1. The system supports two pricing modes:

• Flat pricing — legacy inputPrice/outputPrice/totalPrice decimal fields directly on the Model record.
• Tiered pricing — condition-based PricingTier records linked to granular Price entries per usageType (added in November 2025).

Models with projectId = null are system-wide defaults; models scoped to a project via projectId override them for that project 2. Default models are shipped via Prisma migrations, not a seed file.

Database Schema#

Three Prisma models make up the pricing layer 1. The Model → PricingTier → Price hierarchy means every price is attached to a tier, even flat/legacy prices (which are backfilled into a default tier).

All three tables cascade-delete on parent removal 3.

Usage Types#

The usageType field on Price is a free-form string matched exactly against keys in the ingested usage_details map. Supported values across providers include:

⚠️ Exact-match gotcha: Cost calculation matches usageType by strict string equality against usage_details keys 4. If the provider SDK emits a raw key (e.g., cache_read_input_tokens) that doesn't match the pricing entry key (input_cached_tokens), that bucket is silently priced at zero. This caused a known undercount for GPT-5.6 Sol/Terra/Luna models 5.

Tiered Pricing Mechanism#

Each PricingTier holds a conditions JSONB array. Each condition has the shape 6:

{ usageDetailPattern: string, operator: "gt"|"gte"|"lt"|"lte"|"eq"|"neq", value: number, caseSensitive: boolean }

At cost calculation time, matchPricingTier() 4:

1. Iterates non-default tiers in ascending priority order.
2. For each tier, compiles usageDetailPattern as a regex, sums all matching usage_details keys, and evaluates the operator+threshold (AND logic across conditions).
3. Returns the first matching tier; falls back to the isDefault = true tier if none match.

Each winning tier owns a set of Price records — one per usageType. calculateUsageCosts() then multiplies price × units for each key 4.

User override: if any provided_cost_details key is set on the observation, automatic cost calculation is bypassed entirely 4.

Management APIs and Entry Points#

Public REST API#

• GET /api/public/models — list all models (system + project-scoped) with their pricing tiers.
• POST /api/public/models — create a custom model with flat or tiered pricing.
• GET /DELETE /api/public/models/[modelId] (source) — fetch or delete a specific model.

Internal tRPC Router#

web/src/server/api/routers/models.ts exposes upsert, getById, getAll, delete, and testMatch procedures. upsert deletes existing pricing tiers before writing new ones — i.e., tier updates are full replacements 7.

Default Model Definitions#

System-default models are added exclusively via Prisma migrations in packages/shared/prisma/migrations/. Notable migration milestones:

• 20241024100928_add_prices_table — introduced the prices table.
• 20251127105316_add_pricing_tiers — added pricing_tiers table; backfilled existing prices into default tiers.
• 20250711105322_prices_add_project_id — enabled per-project custom pricing.
• 20240913095558_models_add_openai_o1 — added o1 reasoning models (no tokenizer config because reasoning output cannot be locally tokenized).

Model Matching#

findModel() resolves an incoming model name string against matchPattern regexes. Results are cached in Redis and local memory to minimize DB round-trips during high-throughput ingestion.