[management, proxy] Management-owned LLM pricing: file-backed defaults + (#6965)

This commit is contained in:
Misha Bragin
2026-07-31 20:52:56 +02:00
committed by GitHub
parent feecb993f4
commit 0780a806f2
47 changed files with 3196 additions and 1540 deletions
@@ -0,0 +1,156 @@
// Package pricing builds the default LLM pricing table the synthesizer
// ships to the proxy's cost_meter middleware. The catalog is the single
// source of default rates: every catalog provider's models are folded
// into the pricing surfaces the provider declares (PricingSurfaces),
// then a small supplemental list adds priced-but-not-operator-selectable
// entries. Management is the sole pricing authority — the proxy carries
// no embedded price list and bills exclusively from the table it is
// sent.
//go:generate go run gen.go
package pricing
import (
"sync"
"sync/atomic"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog"
)
// Entry is a single model's pricing in USD per 1k tokens. This struct IS
// the wire shape: the synthesizer marshals it verbatim into cost_meter's
// ConfigJSON, and the proxy unmarshals the same field names.
//
// A zero rate means "no rate configured" — the proxy bills that cache
// bucket at InputPer1k (identical semantics to the retired proxy-embedded
// table). CachedInputPer1k is the OpenAI shape (cached prompt tokens are
// a subset of input); CacheReadPer1k / CacheCreationPer1k are the
// Anthropic shape (additive buckets).
type Entry struct {
InputPer1k float64 `json:"input_per_1k"`
OutputPer1k float64 `json:"output_per_1k"`
CachedInputPer1k float64 `json:"cached_input_per_1k,omitempty"`
CacheReadPer1k float64 `json:"cache_read_per_1k,omitempty"`
CacheCreationPer1k float64 `json:"cache_creation_per_1k,omitempty"`
}
// supplementalDefaults are (surface, model) entries that are priced but
// deliberately not operator-selectable in the catalog. Each carries a
// reason; when one of these models joins a catalog lineup, delete the
// row here — the collision test fails loudly if the rates ever disagree.
var supplementalDefaults = map[string]map[string]Entry{
"openai": {
// GPT-5 (2025) family — kept for gateway requests using the
// unsuffixed ids; the dashboard offers only the 5.x lineup.
"gpt-5": {InputPer1k: 0.00125, OutputPer1k: 0.01, CachedInputPer1k: 0.000125},
"gpt-5-mini": {InputPer1k: 0.00025, OutputPer1k: 0.002, CachedInputPer1k: 0.000025},
"gpt-5-nano": {InputPer1k: 0.00005, OutputPer1k: 0.0004, CachedInputPer1k: 0.000005},
},
"anthropic": {
// claude-opus-5 is not yet in the catalog lineup but gateway /
// grandfathered traffic uses it; priced so it isn't skipped.
"claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
// "kimi-k3[1m]" is the 1M-context alias some Claude Code guides
// configure against Moonshot's Anthropic-compatible endpoint;
// priced identically to kimi-k3 so those requests aren't skipped.
"kimi-k3[1m]": {InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003},
},
"bedrock": {
"anthropic.claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
},
}
var (
compiledOnce sync.Once
compiledTable map[string]map[string]Entry
// mergedTable holds the current live table when a pricing defaults
// file is loaded: the file merged entry-whole over the compiled-in
// base. Nil while no file is loaded (or after the file is removed),
// in which case the compiled-in table serves. Swapped atomically by
// the file loader/reloader; readers never block.
mergedTable atomic.Pointer[map[string]map[string]Entry]
)
// DefaultTable returns the current default pricing table keyed
// surface -> model -> Entry: the management-side defaults file (see
// LoadFile / StartReloader) when one is loaded, merged over the
// compiled-in catalog table, which alone serves as the fallback when no
// file exists. The snapshot may change between calls as the file is
// re-read — consumers (the synthesizer on every reconcile, the catalog
// endpoint on every request) pick up fresh rates automatically. Callers
// must not mutate the returned maps.
func DefaultTable() map[string]map[string]Entry {
if t := mergedTable.Load(); t != nil {
return *t
}
return compiledBase()
}
// compiledBase returns the compiled-in table (catalog + supplementals),
// built once.
func compiledBase() map[string]map[string]Entry {
compiledOnce.Do(func() {
compiledTable = buildDefaultTable()
})
return compiledTable
}
func buildDefaultTable() map[string]map[string]Entry {
out := make(map[string]map[string]Entry)
for _, p := range catalog.All() {
for _, surface := range p.PricingSurfaces {
inner, ok := out[surface]
if !ok {
inner = make(map[string]Entry)
out[surface] = inner
}
for _, m := range p.Models {
// First writer wins; providers contributing the same
// (surface, model) must agree on rates — enforced by
// TestDefaultTable_NoConflictingContributions.
if _, dup := inner[m.ID]; dup {
continue
}
inner[m.ID] = entryFromCatalogModel(m)
}
}
}
for surface, models := range supplementalDefaults {
inner, ok := out[surface]
if !ok {
inner = make(map[string]Entry)
out[surface] = inner
}
for id, e := range models {
if _, dup := inner[id]; dup {
continue
}
inner[id] = e
}
}
return out
}
func entryFromCatalogModel(m catalog.Model) Entry {
return Entry{
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
CachedInputPer1k: m.CachedInputPer1k,
CacheReadPer1k: m.CacheReadPer1k,
CacheCreationPer1k: m.CacheCreationPer1k,
}
}
// LookupDefault returns the default entry for model on the first of the
// given surfaces that prices it. Used by the synthesizer to seed a
// per-provider entry with default cache rates before overlaying the
// operator's stored prices.
func LookupDefault(surfaces []string, model string) (Entry, bool) {
table := DefaultTable()
for _, s := range surfaces {
if e, ok := table[s][model]; ok {
return e, true
}
}
return Entry{}, false
}
@@ -0,0 +1,282 @@
# 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
@@ -0,0 +1,148 @@
package pricing
import (
"math"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog"
)
// TestDefaultTable_CoversEveryCatalogModel replaces the proxy's old
// hand-maintained coverage list: because the table is built FROM the
// catalog, drift is impossible by construction — this test guards the
// fold itself (every catalog model of every surfaced provider resolves,
// with exactly the catalog's rates).
func TestDefaultTable_CoversEveryCatalogModel(t *testing.T) {
table := DefaultTable()
for _, p := range catalog.All() {
if len(p.PricingSurfaces) == 0 {
assert.Empty(t, p.Models, "catalog entry %s declares models but no pricing surfaces — those models would never be priced", p.ID)
continue
}
for _, surface := range p.PricingSurfaces {
byModel, ok := table[surface]
require.True(t, ok, "surface %q (provider %s) missing from default table", surface, p.ID)
for _, m := range p.Models {
e, ok := byModel[m.ID]
require.True(t, ok, "%s/%s (provider %s) missing from default table", surface, m.ID, p.ID)
assert.Equal(t, m.InputPer1k, e.InputPer1k, "%s/%s input rate", surface, m.ID)
assert.Equal(t, m.OutputPer1k, e.OutputPer1k, "%s/%s output rate", surface, m.ID)
}
}
}
}
// TestDefaultTable_NoConflictingContributions enforces the collision rule
// documented on catalog.Provider.PricingSurfaces: when two catalog
// providers contribute the same (surface, model) pair — azure/vertex
// mirroring openai/anthropic, kimi on both surfaces — their rates must be
// identical, because the surface-keyed table can only hold one entry.
// If a provider ever diverges (e.g. Azure reprices a model), this fails
// and the divergence must move to per-provider-record pricing.
func TestDefaultTable_NoConflictingContributions(t *testing.T) {
type contribution struct {
providerID string
entry Entry
}
seen := map[string]map[string]contribution{}
for _, p := range catalog.All() {
for _, surface := range p.PricingSurfaces {
if seen[surface] == nil {
seen[surface] = map[string]contribution{}
}
for _, m := range p.Models {
e := entryFromCatalogModel(m)
if prev, dup := seen[surface][m.ID]; dup {
assert.Equal(t, prev.entry, e,
"%s/%s: %s and %s contribute different rates", surface, m.ID, prev.providerID, p.ID)
continue
}
seen[surface][m.ID] = contribution{providerID: p.ID, entry: e}
}
}
}
// Supplemental entries must never shadow a catalog-contributed model —
// they exist precisely because the catalog does NOT list them.
for surface, models := range supplementalDefaults {
for id := range models {
_, fromCatalog := seen[surface][id]
assert.False(t, fromCatalog, "supplemental %s/%s is now in the catalog — delete the supplemental row", surface, id)
}
}
}
// TestDefaultTable_AllRatesFiniteNonNegative mirrors the proxy-side
// NewTable validation so a bad catalog edit is caught here, at unit-test
// time, rather than as a chain-build failure on every proxy.
func TestDefaultTable_AllRatesFiniteNonNegative(t *testing.T) {
for surface, models := range DefaultTable() {
for id, e := range models {
for field, v := range map[string]float64{
"input": e.InputPer1k,
"output": e.OutputPer1k,
"cached_input": e.CachedInputPer1k,
"cache_read": e.CacheReadPer1k,
"cache_creation": e.CacheCreationPer1k,
} {
assert.False(t, v < 0 || math.IsNaN(v) || math.IsInf(v, 0),
"%s/%s: %s rate %v must be finite and non-negative", surface, id, field, v)
}
}
}
}
// TestDefaultTable_PinnedRates pins rates that previously drifted or are
// easy to mis-enter (carried over from the proxy's retired
// defaults_coverage_test), plus the supplemental entries.
func TestDefaultTable_PinnedRates(t *testing.T) {
table := DefaultTable()
gpt54 := table["openai"]["gpt-5.4"]
assert.InDelta(t, 0.0025, gpt54.InputPer1k, 1e-9, "gpt-5.4 input")
assert.InDelta(t, 0.015, gpt54.OutputPer1k, 1e-9, "gpt-5.4 output")
assert.InDelta(t, 0.00025, gpt54.CachedInputPer1k, 1e-9, "gpt-5.4 cached input")
sonnet := table["bedrock"]["anthropic.claude-sonnet-4-5"]
assert.InDelta(t, 0.003, sonnet.InputPer1k, 1e-9, "bedrock sonnet-4-5 input")
assert.InDelta(t, 0.015, sonnet.OutputPer1k, 1e-9, "bedrock sonnet-4-5 output")
assert.InDelta(t, 0.0003, sonnet.CacheReadPer1k, 1e-9, "bedrock sonnet-4-5 cache read")
assert.InDelta(t, 0.00375, sonnet.CacheCreationPer1k, 1e-9, "bedrock sonnet-4-5 cache creation")
// Vertex Claude prices under "anthropic" with the bare id.
fable := table["anthropic"]["claude-fable-5"]
assert.InDelta(t, 0.010, fable.InputPer1k, 1e-9, "claude-fable-5 input")
assert.InDelta(t, 0.0125, fable.CacheCreationPer1k, 1e-9, "claude-fable-5 cache creation")
// Supplementals present on their surfaces.
for surface, ids := range map[string][]string{
"openai": {"gpt-5", "gpt-5-mini", "gpt-5-nano"},
"anthropic": {"claude-opus-5", "kimi-k3[1m]", "kimi-k3"},
"bedrock": {"anthropic.claude-opus-5"},
} {
for _, id := range ids {
_, ok := table[surface][id]
assert.True(t, ok, "%s/%s must be priced", surface, id)
}
}
// Embeddings bill input-only — output stays zero.
emb := table["openai"]["text-embedding-3-large"]
assert.Zero(t, emb.OutputPer1k, "embedding output rate must be zero")
assert.Positive(t, emb.InputPer1k, "embedding input rate must be set")
}
func TestLookupDefault_SurfaceOrder(t *testing.T) {
// kimi-k3 exists on both surfaces; first surface in the slice wins.
e, ok := LookupDefault([]string{"openai", "anthropic"}, "kimi-k3")
require.True(t, ok)
assert.InDelta(t, 0.003, e.InputPer1k, 1e-9)
_, ok = LookupDefault([]string{"bedrock"}, "gpt-4o")
assert.False(t, ok, "gpt-4o is not a bedrock model")
_, ok = LookupDefault(nil, "gpt-4o")
assert.False(t, ok, "no surfaces, no match")
}
@@ -0,0 +1,109 @@
package pricing
import (
"bytes"
"fmt"
"sort"
"strconv"
)
// MarshalDefaultsYAML renders the built-in default pricing table (catalog
// + supplementals, WITHOUT any operator override) as the YAML schema
// LoadOverrideFile consumes. It backs the generated
// defaults_llm_pricing.example.yaml so operators start from a file that
// matches the compiled-in rates exactly; a golden test keeps the two in
// sync. Output is deterministic (sorted surfaces and models).
func MarshalDefaultsYAML() []byte {
var b bytes.Buffer
b.WriteString(exampleHeader)
table := buildDefaultTable()
surfaces := make([]string, 0, len(table))
for s := range table {
surfaces = append(surfaces, s)
}
sort.Strings(surfaces)
for _, surface := range surfaces {
fmt.Fprintf(&b, "\n%s:\n", surface)
models := table[surface]
ids := make([]string, 0, len(models))
for id := range models {
ids = append(ids, id)
}
sort.Strings(ids)
for _, id := range ids {
e := models[id]
fmt.Fprintf(&b, " %s:\n", yamlKey(id))
fmt.Fprintf(&b, " input_per_1k: %s\n", rate(e.InputPer1k))
fmt.Fprintf(&b, " output_per_1k: %s\n", rate(e.OutputPer1k))
if e.CachedInputPer1k > 0 {
fmt.Fprintf(&b, " cached_input_per_1k: %s\n", rate(e.CachedInputPer1k))
}
if e.CacheReadPer1k > 0 {
fmt.Fprintf(&b, " cache_read_per_1k: %s\n", rate(e.CacheReadPer1k))
}
if e.CacheCreationPer1k > 0 {
fmt.Fprintf(&b, " cache_creation_per_1k: %s\n", rate(e.CacheCreationPer1k))
}
}
}
return b.Bytes()
}
// rate renders a USD-per-1k rate without float noise ("0.00015", not
// "0.000150000000...").
func rate(v float64) string {
return strconv.FormatFloat(v, 'f', -1, 64)
}
// yamlKey quotes model ids that YAML would otherwise misparse (e.g.
// "kimi-k3[1m]" starts a flow sequence unquoted).
func yamlKey(id string) string {
for _, r := range id {
switch r {
case '[', ']', '{', '}', ':', '#', ',', '&', '*', '!', '|', '>', '\'', '"', '%', '@', '`':
return strconv.Quote(id)
}
}
return id
}
const exampleHeader = `# 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.
`
@@ -0,0 +1,20 @@
//go:build ignore
// Regenerates defaults_llm_pricing.example.yaml from the compiled-in
// default pricing table. Run via:
//
// go generate ./management/internals/modules/agentnetwork/pricing
package main
import (
"log"
"os"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing"
)
func main() {
if err := os.WriteFile("defaults_llm_pricing.example.yaml", pricing.MarshalDefaultsYAML(), 0o644); err != nil {
log.Fatalf("write defaults_llm_pricing.example.yaml: %v", err)
}
}
@@ -0,0 +1,249 @@
package pricing
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"io/fs"
"math"
"os"
"sync"
"time"
log "github.com/sirupsen/logrus"
"gopkg.in/yaml.v3"
)
// DefaultFileName is the basename probed under management's datadir when
// AgentNetwork.PricingDefaultsFile doesn't configure an explicit path.
const DefaultFileName = "defaults_llm_pricing.yaml"
// ReloadInterval is the cadence at which the pricing file's mtime is
// polled for changes.
const ReloadInterval = time.Minute
// maxFileBytes bounds the pricing file read so a misconfigured path
// (pointed at a huge file) cannot exhaust process memory.
const maxFileBytes = 4 << 20
// pricingFile mirrors the on-disk YAML schema — the same schema the
// proxy's retired embedded defaults_pricing.yaml used, so files written
// for it keep working. Keys are pricing surfaces ("openai", "anthropic",
// "bedrock"); nested keys are normalized model ids.
type pricingFile map[string]map[string]struct {
InputPer1k float64 `yaml:"input_per_1k"`
OutputPer1k float64 `yaml:"output_per_1k"`
CachedInputPer1k float64 `yaml:"cached_input_per_1k"`
CacheReadPer1k float64 `yaml:"cache_read_per_1k"`
CacheCreationPer1k float64 `yaml:"cache_creation_per_1k"`
}
// fileState tracks the watched pricing file across reloads.
var fileState struct {
mu sync.Mutex
path string
mtime int64
}
// LoadFile loads the management-side pricing defaults file and makes it
// the live table (merged entry-whole over the compiled-in fallback; see
// DefaultTable). The path stays registered for the periodic reloader, so
// later edits — or the file (re)appearing after deletion — are picked up
// without a restart.
//
// required governs the missing-file case: true for an explicitly
// configured path (a typo must fail startup rather than silently bill
// with built-ins the operator believes they replaced), false for the
// conventional <datadir>/defaults_llm_pricing.yaml probe (absent file =
// compiled-in defaults, still watched in case it appears). A file that
// exists but is malformed is always an error at load time.
func LoadFile(path string, required bool) error {
if path == "" {
return nil
}
fileState.mu.Lock()
fileState.path = path
fileState.mu.Unlock()
table, mtime, err := readFile(path)
if err != nil {
if errors.Is(err, fs.ErrNotExist) && !required {
log.Infof("agent-network pricing defaults file %s not present; serving built-in defaults", path)
return nil
}
return err
}
storeFileTable(table, mtime)
log.Infof("agent-network pricing defaults loaded from %s", path)
return nil
}
// StartReloader launches the periodic mtime-poll goroutine for the file
// registered by LoadFile. Runtime failures are lenient — a parse error
// keeps the previously loaded table and logs a warning; a deleted file
// reverts to the compiled-in defaults — so a mid-edit save can never
// take pricing down. Returns immediately when no path was registered.
func StartReloader(ctx context.Context, interval time.Duration) {
fileState.mu.Lock()
path := fileState.path
fileState.mu.Unlock()
if path == "" {
return
}
if interval <= 0 {
interval = ReloadInterval
}
go func() {
t := time.NewTicker(interval)
defer t.Stop()
for {
select {
case <-ctx.Done():
return
case <-t.C:
reload()
}
}
}()
}
// reload performs one mtime check + reload cycle.
func reload() {
fileState.mu.Lock()
path, lastMtime := fileState.path, fileState.mtime
fileState.mu.Unlock()
log.Debugf("agent-network pricing defaults reload: checking %s for changes", path)
st, err := os.Stat(path)
if err != nil {
if errors.Is(err, fs.ErrNotExist) {
// File removed (or not yet created): serve compiled-in
// defaults and reset mtime so a future (re)appearance loads.
if mergedTable.Swap(nil) != nil {
log.Warnf("agent-network pricing defaults file %s removed; reverting to built-in defaults", path)
}
setMtime(0)
return
}
log.Warnf("agent-network pricing defaults reload: stat %s: %v", path, err)
return
}
if st.ModTime().UnixNano() == lastMtime {
log.Debugf("agent-network pricing defaults %s unchanged since last check", path)
return
}
table, mtime, err := readFile(path)
if err != nil {
// Keep the previously loaded table — never blank prices because
// an operator saved mid-edit.
log.Warnf("agent-network pricing defaults reload failed for %s (keeping previous table): %v", path, err)
return
}
storeFileTable(table, mtime)
log.Infof("agent-network pricing defaults reloaded from %s", path)
}
func readFile(path string) (map[string]map[string]Entry, int64, error) {
f, err := os.Open(path)
if err != nil {
return nil, 0, fmt.Errorf("open pricing defaults %s: %w", path, err)
}
defer func() { _ = f.Close() }()
st, err := f.Stat()
if err != nil {
return nil, 0, fmt.Errorf("stat pricing defaults %s: %w", path, err)
}
data, err := io.ReadAll(io.LimitReader(f, maxFileBytes+1))
if err != nil {
return nil, 0, fmt.Errorf("read pricing defaults %s: %w", path, err)
}
if len(data) > maxFileBytes {
return nil, 0, fmt.Errorf("pricing defaults %s exceeds %d bytes", path, maxFileBytes)
}
table, err := parsePricingYAML(data)
if err != nil {
return nil, 0, fmt.Errorf("parse pricing defaults %s: %w", path, err)
}
return table, st.ModTime().UnixNano(), nil
}
// storeFileTable merges the parsed file over the compiled-in base and
// publishes the result as the live table. File entries replace the
// built-in entry for the same (surface, model) whole — they are not
// field-merged — and surfaces/models the file doesn't mention keep the
// built-in rates, so a partial file only needs the entries it changes.
func storeFileTable(table map[string]map[string]Entry, mtime int64) {
base := compiledBase()
merged := make(map[string]map[string]Entry, len(base)+len(table))
for surface, models := range base {
inner := make(map[string]Entry, len(models))
for id, e := range models {
inner[id] = e
}
merged[surface] = inner
}
for surface, models := range table {
inner, ok := merged[surface]
if !ok {
inner = make(map[string]Entry, len(models))
merged[surface] = inner
}
for id, e := range models {
inner[id] = e
}
}
mergedTable.Store(&merged)
setMtime(mtime)
}
func setMtime(v int64) {
fileState.mu.Lock()
fileState.mtime = v
fileState.mu.Unlock()
}
// parsePricingYAML decodes and validates the pricing YAML. Unknown
// fields are rejected (typos surface instead of silently pricing at 0)
// and every rate must be a finite, non-negative USD amount — the same
// constraints the HTTP API enforces on operator per-provider prices.
func parsePricingYAML(data []byte) (map[string]map[string]Entry, error) {
dec := yaml.NewDecoder(bytes.NewReader(data))
dec.KnownFields(true)
var raw pricingFile
if err := dec.Decode(&raw); err != nil && !errors.Is(err, io.EOF) {
return nil, fmt.Errorf("decode yaml: %w", err)
}
out := make(map[string]map[string]Entry, len(raw))
for surface, models := range raw {
inner := make(map[string]Entry, len(models))
for model, e := range models {
for field, v := range map[string]float64{
"input_per_1k": e.InputPer1k,
"output_per_1k": e.OutputPer1k,
"cached_input_per_1k": e.CachedInputPer1k,
"cache_read_per_1k": e.CacheReadPer1k,
"cache_creation_per_1k": e.CacheCreationPer1k,
} {
if v < 0 || math.IsNaN(v) || math.IsInf(v, 0) {
return nil, fmt.Errorf("%s/%s: %s must be a finite, non-negative rate, got %v", surface, model, field, v)
}
}
inner[model] = Entry{
InputPer1k: e.InputPer1k,
OutputPer1k: e.OutputPer1k,
CachedInputPer1k: e.CachedInputPer1k,
CacheReadPer1k: e.CacheReadPer1k,
CacheCreationPer1k: e.CacheCreationPer1k,
}
}
out[surface] = inner
}
return out, nil
}
@@ -0,0 +1,173 @@
package pricing
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// resetFileState snapshots and restores the package-level file state so
// tests stay order-independent.
func resetFileState(t *testing.T) {
t.Helper()
prevMerged := mergedTable.Load()
fileState.mu.Lock()
prevPath, prevMtime := fileState.path, fileState.mtime
fileState.mu.Unlock()
t.Cleanup(func() {
mergedTable.Store(prevMerged)
fileState.mu.Lock()
fileState.path, fileState.mtime = prevPath, prevMtime
fileState.mu.Unlock()
})
}
func writePricing(t *testing.T, path, yml string) {
t.Helper()
require.NoError(t, os.WriteFile(path, []byte(yml), 0o600))
}
func TestLoadFile_MergesOverCompiledDefaults(t *testing.T) {
resetFileState(t)
path := filepath.Join(t.TempDir(), DefaultFileName)
writePricing(t, path, `
openai:
# Reprice a built-in model. The entry replaces the built-in WHOLE:
# omitting the cache rate here drops the built-in 0.00125 discount.
gpt-4o:
input_per_1k: 0.9
output_per_1k: 1.8
# A model NetBird doesn't know at all.
my-private-ft:
input_per_1k: 0.01
output_per_1k: 0.02
cached_input_per_1k: 0.005
gemini:
gemini-pro:
input_per_1k: 0.00125
output_per_1k: 0.005
`)
require.NoError(t, LoadFile(path, true))
table := DefaultTable()
gpt4o := table["openai"]["gpt-4o"]
assert.InDelta(t, 0.9, gpt4o.InputPer1k, 1e-9, "file rate replaces the compiled-in rate")
assert.Zero(t, gpt4o.CachedInputPer1k, "entries replace whole — omitted cache rate is dropped, not inherited")
ft := table["openai"]["my-private-ft"]
assert.InDelta(t, 0.005, ft.CachedInputPer1k, 1e-9, "unknown models are added to the surface")
_, ok := table["gemini"]["gemini-pro"]
assert.True(t, ok, "a surface the catalog doesn't declare can be added")
// Untouched entries keep compiled-in rates (catalog, other surface,
// supplemental).
assert.InDelta(t, 0.00015, table["openai"]["gpt-4o-mini"].InputPer1k, 1e-9, "unlisted model keeps compiled rate")
assert.InDelta(t, 0.003, table["anthropic"]["claude-sonnet-4-5"].InputPer1k, 1e-9, "unlisted surface untouched")
assert.InDelta(t, 0.00125, table["openai"]["gpt-5"].InputPer1k, 1e-9, "supplemental entries untouched")
// The synthesizer-facing lookup reads the live table too.
e, ok := LookupDefault([]string{"openai"}, "gpt-4o")
require.True(t, ok)
assert.InDelta(t, 0.9, e.InputPer1k, 1e-9, "LookupDefault serves the file-backed rate")
}
func TestLoadFile_MissingPath(t *testing.T) {
resetFileState(t)
missing := filepath.Join(t.TempDir(), DefaultFileName)
require.Error(t, LoadFile(missing, true),
"explicitly configured path that doesn't exist must fail startup")
require.NoError(t, LoadFile(missing, false),
"conventional datadir probe tolerates an absent file (compiled-in defaults serve)")
assert.Nil(t, mergedTable.Load(), "no file, no merged table")
fileState.mu.Lock()
path := fileState.path
fileState.mu.Unlock()
assert.Equal(t, missing, path, "the path stays registered so the reloader picks the file up when it appears")
}
func TestLoadFile_RejectsInvalid(t *testing.T) {
resetFileState(t)
dir := t.TempDir()
cases := map[string]string{
"unknown field (typo)": "openai:\n gpt-4o:\n input_per1k: 0.1\n",
"negative rate": "openai:\n gpt-4o:\n input_per_1k: -0.1\n",
"non-numeric rate": "openai:\n gpt-4o:\n input_per_1k: cheap\n",
"not a mapping": "- just\n- a\n- list\n",
}
for name, yml := range cases {
path := filepath.Join(dir, DefaultFileName)
writePricing(t, path, yml)
assert.Error(t, LoadFile(path, true), "case %q must be rejected", name)
}
}
// TestReload_LifeCycle drives the reloader's single-shot reload through
// its full lifecycle: file edit picked up on mtime change, a broken save
// keeps the previous table, and file removal reverts to the compiled-in
// defaults (then a re-created file loads again).
func TestReload_LifeCycle(t *testing.T) {
resetFileState(t)
path := filepath.Join(t.TempDir(), DefaultFileName)
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.5\n output_per_1k: 1\n")
require.NoError(t, LoadFile(path, true))
require.InDelta(t, 0.5, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9)
// Edit: new mtime, new rates.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.7\n output_per_1k: 1.4\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.7, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9, "edit must be picked up")
// Broken save: previous table survives.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: -1\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.7, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"a malformed save must keep the previously loaded table, never blank prices")
// Removal: compiled-in defaults serve again.
require.NoError(t, os.Remove(path))
reload()
assert.InDelta(t, 0.0025, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"file removal reverts to the compiled-in rate")
// Re-created file loads without a restart.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.9\n output_per_1k: 1.8\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.9, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"a file appearing after removal (or after a missing-probe boot) must load")
}
// bumpMtime pushes the file's mtime forward past the previously recorded
// value — timestamps can otherwise collide within the test's timescale.
func bumpMtime(t *testing.T, path string) {
t.Helper()
st, err := os.Stat(path)
require.NoError(t, err)
next := st.ModTime().Add(2 * 1e9)
require.NoError(t, os.Chtimes(path, next, next))
}
// TestExampleYAML_InSyncWithBuiltins is the golden guard for
// defaults_llm_pricing.example.yaml: the shipped example must stay
// byte-identical to what the compiled-in table renders (catalog edits
// require `go generate ./management/internals/modules/agentnetwork/pricing`)
// and must round-trip through the same parser operators' files go
// through, reproducing the compiled-in table exactly.
func TestExampleYAML_InSyncWithBuiltins(t *testing.T) {
onDisk, err := os.ReadFile("defaults_llm_pricing.example.yaml")
require.NoError(t, err, "example file must exist next to the package")
require.Equal(t, string(MarshalDefaultsYAML()), string(onDisk),
"defaults_llm_pricing.example.yaml is stale — run: go generate ./management/internals/modules/agentnetwork/pricing")
parsed, err := parsePricingYAML(onDisk)
require.NoError(t, err, "the example must be a valid pricing defaults file")
assert.Equal(t, buildDefaultTable(), parsed,
"parsing the example must reproduce the compiled-in table exactly")
}