# Default LLM pricing used by NetBird's Agent Network cost metering.
# GENERATED from the management catalog — do not edit this file in the
# repository; regenerate with:
#
#   go generate ./management/internals/modules/agentnetwork/pricing
#
# Operators: copy this file to <datadir>/defaults_llm_pricing.yaml (or
# any path configured via management.json:
#
#   { "AgentNetwork": { "PricingDefaultsFile": "/path/defaults_llm_pricing.yaml" } }
#
# ) and adjust the entries you want to change. Management re-reads the
# file periodically (mtime poll, every minute): the live table feeds the
# proxies' cost metering and the dashboard's model-price prefill, so
# edits apply without a restart. Your file only needs the entries you
# want to change — but each entry REPLACES the built-in entry for that
# surface+model whole, so repeat the cache rates you want to keep.
# Unknown fields and negative or non-finite rates are rejected: at
# startup that fails boot (for an explicitly configured path); at
# runtime the previous table is kept and a warning is logged. Deleting
# the file reverts to the built-in defaults below.
#
# Top-level keys are pricing surfaces — the parser shape requests are
# metered under: "openai" (also Azure, Mistral, and OpenAI-compatible
# gateways), "anthropic" (also Anthropic-on-Vertex), "bedrock"
# (normalized ids, e.g. anthropic.claude-sonnet-4-5). Model keys must be
# the normalized id the proxy meters (version/region suffixes stripped).
#
# Values are USD per 1_000 tokens. Optional cache fields:
#   cached_input_per_1k    OpenAI shape: rate for cached prompt tokens
#                          (a SUBSET of input tokens). Absent -> cached
#                          portion bills at input_per_1k.
#   cache_read_per_1k      Anthropic shape: rate for cache_read tokens
#                          (ADDITIVE to input). Absent -> input rate.
#   cache_creation_per_1k  Anthropic shape: rate for cache_creation
#                          tokens (ADDITIVE to input). Absent -> input
#                          rate.

anthropic:
  claude-fable-5:
    input_per_1k: 0.01
    output_per_1k: 0.05
    cache_read_per_1k: 0.001
    cache_creation_per_1k: 0.0125
  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
  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-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-4-7:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  claude-opus-4-8:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  claude-opus-5:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  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-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
  kimi-k3:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cached_input_per_1k: 0.0003
    cache_read_per_1k: 0.0003
  "kimi-k3[1m]":
    input_per_1k: 0.003
    output_per_1k: 0.015
    cache_read_per_1k: 0.0003

bedrock:
  amazon.nova-2-lite:
    input_per_1k: 0.0003
    output_per_1k: 0.0025
  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
  amazon.nova-pro:
    input_per_1k: 0.0008
    output_per_1k: 0.0032
  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
  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-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-4-7:
    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-4-8:
    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-5:
    input_per_1k: 0.005
    output_per_1k: 0.025
    cache_read_per_1k: 0.0005
    cache_creation_per_1k: 0.00625
  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-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
  meta.llama3-3-70b-instruct:
    input_per_1k: 0.00072
    output_per_1k: 0.00072

openai:
  codestral-2508:
    input_per_1k: 0.0003
    output_per_1k: 0.0009
  codestral-latest:
    input_per_1k: 0.001
    output_per_1k: 0.003
  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
  gpt-3.5-turbo:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  gpt-35-turbo:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  gpt-4-turbo:
    input_per_1k: 0.01
    output_per_1k: 0.03
  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:
    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
  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
  gpt-5.3-chat-latest:
    input_per_1k: 0.00175
    output_per_1k: 0.014
    cached_input_per_1k: 0.000175
  gpt-5.3-codex:
    input_per_1k: 0.00175
    output_per_1k: 0.014
    cached_input_per_1k: 0.000175
  gpt-5.4:
    input_per_1k: 0.0025
    output_per_1k: 0.015
    cached_input_per_1k: 0.00025
  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-5.4-pro:
    input_per_1k: 0.03
    output_per_1k: 0.18
    cached_input_per_1k: 0.003
  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
  kimi-k3:
    input_per_1k: 0.003
    output_per_1k: 0.015
    cached_input_per_1k: 0.0003
    cache_read_per_1k: 0.0003
  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
  ministral-3-14b-2512:
    input_per_1k: 0.0002
    output_per_1k: 0.0002
  ministral-3-3b-2512:
    input_per_1k: 0.0001
    output_per_1k: 0.0001
  ministral-8b-latest:
    input_per_1k: 0.00015
    output_per_1k: 0.00015
  mistral-embed:
    input_per_1k: 0.0001
    output_per_1k: 0
  mistral-large-latest:
    input_per_1k: 0.0005
    output_per_1k: 0.0015
  mistral-medium-3-5:
    input_per_1k: 0.0015
    output_per_1k: 0.0075
  mistral-medium-latest:
    input_per_1k: 0.0004
    output_per_1k: 0.002
  mistral-small-latest:
    input_per_1k: 0.00006
    output_per_1k: 0.00018
  o4-mini:
    input_per_1k: 0.0011
    output_per_1k: 0.0044
    cached_input_per_1k: 0.000275
  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