# Demonstrates the `cost` override that declares a model's token pricing

# explicitly, in USD per one million tokens. It takes precedence over the

# models.dev catalogue and — more importantly — prices models the catalogue

# does not know at all: custom OpenAI-compatible providers, local models, and

# private deployments otherwise bill $0 despite consuming tokens.

#

# A declared cost feeds per-turn cost computation, session cost tracking, the

# /model picker, and the after_llm_call hook's `cost` field. Prices must not

# be negative; an all-zero table means "priced, free" (distinct from unpriced).

providers:

# A self-hosted OpenAI-compatible gateway with negotiated pricing.

# models.dev knows nothing about the models it serves.

internal-llm:

api_type: openai_chatcompletions

base_url: https://llm.internal.example.com/v1

token_key: INTERNAL_LLM_API_KEY

models:

# Custom endpoint: without `cost` every call would be recorded at $0.

internal-gpt:

provider: internal-llm

model: gpt-4o

cost:

input: 1.25 # USD per 1M input tokens

output: 5.00 # USD per 1M output tokens

cache_read: 0.125 # USD per 1M cached input tokens

cache_write: 1.5625 # USD per 1M cache-write tokens

# Catalogued model with a discounted enterprise contract: the override

# replaces the models.dev list price so recorded spend matches the invoice.

discounted-sonnet:

provider: anthropic

model: claude-sonnet-4-5

cost:

input: 2.4

output: 12.0

agents:

root:

model: internal-gpt

description: Assistant on a custom endpoint with accurate cost tracking

instruction: You are a helpful assistant.