# Embedded default pricing for llm_observability. Compiled into the proxy
# binary via go:embed in pricing.go; cost annotation works out of the box
# without any operator action.
#
# Operators override entries by dropping a pricing.yaml into --plugin-data-dir
# (or whichever basename is given via params.pricing_path). The override file
# only needs entries the operator wants to change; missing entries fall
# through to these defaults.
#
# Values are USD per 1_000 tokens. Public list prices drift; ship a fresh
# binary or override individual entries via the override file as needed.
#
# Optional cache fields:
#   cached_input_per_1k    OpenAI: rate for prompt_tokens_details.cached_tokens
#                          (a SUBSET of prompt_tokens). Typically 0.5x input.
#                          Absent → cached portion bills at input_per_1k.
#   cache_read_per_1k      Anthropic: rate for cache_read_input_tokens
#                          (ADDITIVE to input_tokens). Typically 0.1x input.
#                          Absent → cache reads bill at input_per_1k.
#   cache_creation_per_1k  Anthropic: rate for cache_creation_input_tokens
#                          (ADDITIVE to input_tokens). Typically 1.25x input.
#                          Absent → cache writes bill at input_per_1k.

openai:
  # OpenAI + OpenAI-compatible providers (openai_api, azure_openai_api,
  # mistral_api, and the openai-parser gateways) all emit llm.provider="openai",
  # so their models are priced here. Kept in sync with the management catalog;
  # rates cross-checked against LiteLLM model_prices_and_context_window.json.

  # GPT-5.x family — cache reads 10% of input (0.1x).
  gpt-5.5:
    input_per_1k: 0.005
    output_per_1k: 0.03
    cached_input_per_1k: 0.0005
  gpt-5.5-pro:
    input_per_1k: 0.03
    output_per_1k: 0.18
    cached_input_per_1k: 0.003
  gpt-5.4:
    input_per_1k: 0.0025
    output_per_1k: 0.015
    cached_input_per_1k: 0.00025
  gpt-5.4-pro:
    input_per_1k: 0.03
    output_per_1k: 0.18
    cached_input_per_1k: 0.003
  gpt-5.4-mini:
    input_per_1k: 0.00075
    output_per_1k: 0.0045
    cached_input_per_1k: 0.000075
  gpt-5.4-nano:
    input_per_1k: 0.0002
    output_per_1k: 0.00125
    cached_input_per_1k: 0.00002
  gpt-5.3-codex:
    input_per_1k: 0.00175
    output_per_1k: 0.014
    cached_input_per_1k: 0.000175
  gpt-5.3-chat-latest:
    input_per_1k: 0.00175
    output_per_1k: 0.014
    cached_input_per_1k: 0.000175
  # GPT-5 (2025) family — kept for gateway requests using the unsuffixed ids.
  gpt-5:
    input_per_1k: 0.00125
    output_per_1k: 0.01
    cached_input_per_1k: 0.000125
  gpt-5-mini:
    input_per_1k: 0.00025
    output_per_1k: 0.002
    cached_input_per_1k: 0.000025
  gpt-5-nano:
    input_per_1k: 0.00005
    output_per_1k: 0.0004
    cached_input_per_1k: 0.000005
  o4-mini:
    input_per_1k: 0.0011
    output_per_1k: 0.0044
    cached_input_per_1k: 0.000275
  # GPT-4.1 family — cache reads 25% of input.
  gpt-4.1:
    input_per_1k: 0.002
    output_per_1k: 0.008
    cached_input_per_1k: 0.0005
  gpt-4.1-mini:
    input_per_1k: 0.0004
    output_per_1k: 0.0016
    cached_input_per_1k: 0.0001
  gpt-4.1-nano:
    input_per_1k: 0.0001
    output_per_1k: 0.0004
    cached_input_per_1k: 0.000025
  # GPT-4o family — cache reads 50% of input (0.5x).
  gpt-4o:
    input_per_1k: 0.0025
    output_per_1k: 0.01
    cached_input_per_1k: 0.00125
  gpt-4o-mini:
    input_per_1k: 0.00015
    output_per_1k: 0.0006
    cached_input_per_1k: 0.000075
  # Older GPT — no prompt caching.
  gpt-4-turbo:
    input_per_1k: 0.01
    output_per_1k: 0.03
  gpt-3.5-turbo:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  gpt-35-turbo: # Azure deployment alias of gpt-3.5-turbo
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  # Embeddings — no caching, no output tokens.
  text-embedding-3-large:
    input_per_1k: 0.00013
    output_per_1k: 0
  text-embedding-3-small:
    input_per_1k: 0.00002
    output_per_1k: 0

  # Mistral (mistral_api) — routed via the openai parser; no prompt caching.
  mistral-large-latest:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  mistral-medium-latest:
    input_per_1k: 0.0004
    output_per_1k: 0.002
  mistral-medium-3-5:
    input_per_1k: 0.0015
    output_per_1k: 0.0075
  mistral-small-latest:
    input_per_1k: 0.00006
    output_per_1k: 0.00018
  magistral-medium-latest:
    input_per_1k: 0.002
    output_per_1k: 0.005
  magistral-small-latest:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  devstral-medium-latest:
    input_per_1k: 0.0004
    output_per_1k: 0.002
  devstral-small-latest:
    input_per_1k: 0.0001
    output_per_1k: 0.0003
  codestral-2508:
    input_per_1k: 0.0003
    output_per_1k: 0.0009
  codestral-latest:
    input_per_1k: 0.001
    output_per_1k: 0.003
  ministral-3-14b-2512:
    input_per_1k: 0.0002
    output_per_1k: 0.0002
  ministral-8b-latest:
    input_per_1k: 0.00015
    output_per_1k: 0.00015
  ministral-3-3b-2512:
    input_per_1k: 0.0001
    output_per_1k: 0.0001
  mistral-embed:
    input_per_1k: 0.0001
    output_per_1k: 0

anthropic:
  # Claude 4.x family — cache reads ≈10% of input, cache writes ≈125% of input.
  # Pricing source: Anthropic's current published rates per million tokens,
  # divided by 1000 for the per-1k figures stored here.
  claude-fable-5:
    input_per_1k: 0.010
    output_per_1k: 0.050
    cache_read_per_1k: 0.001
    cache_creation_per_1k: 0.0125
  claude-opus-4-8:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  claude-opus-4-7:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  claude-opus-4-6:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  claude-opus-4-1:
    input_per_1k: 0.015
    output_per_1k: 0.075
    cache_read_per_1k: 0.0015
    cache_creation_per_1k: 0.01875
  claude-sonnet-4-6:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cache_read_per_1k: 0.0003
    cache_creation_per_1k: 0.00375
  claude-sonnet-4-5:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cache_read_per_1k: 0.0003
    cache_creation_per_1k: 0.00375
  claude-haiku-4-5:
    input_per_1k: 0.001
    output_per_1k: 0.005
    cache_read_per_1k: 0.0001
    cache_creation_per_1k: 0.00125

bedrock:
  # AWS Bedrock model ids, normalised by the request parser (cross-region
  # inference-profile prefix + version/throughput suffix stripped), e.g.
  # eu.anthropic.claude-sonnet-4-5-20250929-v1:0 -> anthropic.claude-sonnet-4-5.
  # Anthropic-on-Bedrock keeps the additive cache buckets (read ≈0.1x input,
  # write ≈1.25x input); Nova / Llama report no cache, so cost is input+output.
  anthropic.claude-opus-4-8:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  anthropic.claude-opus-4-7:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  anthropic.claude-opus-4-6:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  anthropic.claude-opus-4-1:
    input_per_1k: 0.015
    output_per_1k: 0.075
    cache_read_per_1k: 0.0015
    cache_creation_per_1k: 0.01875
  anthropic.claude-sonnet-4-6:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cache_read_per_1k: 0.0003
    cache_creation_per_1k: 0.00375
  anthropic.claude-sonnet-4-5:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cache_read_per_1k: 0.0003
    cache_creation_per_1k: 0.00375
  anthropic.claude-haiku-4-5:
    input_per_1k: 0.001
    output_per_1k: 0.005
    cache_read_per_1k: 0.0001
    cache_creation_per_1k: 0.00125
  meta.llama3-3-70b-instruct:
    input_per_1k: 0.00072
    output_per_1k: 0.00072
  amazon.nova-2-lite:
    input_per_1k: 0.0003
    output_per_1k: 0.0025
  amazon.nova-pro:
    input_per_1k: 0.0008
    output_per_1k: 0.0032
  amazon.nova-lite:
    input_per_1k: 0.00006
    output_per_1k: 0.00024
  amazon.nova-micro:
    input_per_1k: 0.000035
    output_per_1k: 0.00014