newkirk
40f055cb57
- Add promo discount system for deepseek-v4-pro (75% off until 2026-05-31) - Rewrite StreamGemini to handle both SSE and JSON array response formats, fixing 0-token logging for gemini-3-flash and gemini-3-flash-preview - Fall back to model group name for cost lookup when concrete model isnt in the registry (fixes $0 cost on deepseek-auto entries) - Move registry lock before FindModel call to fix data race
102 lines
2.8 KiB
Go
102 lines
2.8 KiB
Go
package utils
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"log"
|
|
"time"
|
|
|
|
"github.com/go-resty/resty/v2"
|
|
"gophergate/internal/models"
|
|
)
|
|
|
|
const ModelsDevURL = "https://models.dev/api.json"
|
|
|
|
func FetchRegistry() (*models.ModelRegistry, error) {
|
|
client := resty.New().SetTimeout(10 * time.Second)
|
|
|
|
var lastErr error
|
|
for attempt := 0; attempt < 3; attempt++ {
|
|
if attempt > 0 {
|
|
backoff := time.Duration(1<<attempt) * time.Second
|
|
time.Sleep(backoff)
|
|
}
|
|
|
|
resp, err := client.R().Get(ModelsDevURL)
|
|
if err != nil {
|
|
lastErr = fmt.Errorf("attempt %d: %w", attempt+1, err)
|
|
continue
|
|
}
|
|
if !resp.IsSuccess() {
|
|
lastErr = fmt.Errorf("attempt %d: HTTP %d", attempt+1, resp.StatusCode())
|
|
continue
|
|
}
|
|
|
|
var providers map[string]models.ProviderInfo
|
|
if err := json.Unmarshal(resp.Body(), &providers); err != nil {
|
|
lastErr = fmt.Errorf("attempt %d: unmarshal: %w", attempt+1, err)
|
|
continue
|
|
}
|
|
|
|
log.Println("Successfully loaded model registry")
|
|
return &models.ModelRegistry{Providers: providers}, nil
|
|
}
|
|
|
|
return nil, fmt.Errorf("failed to fetch registry after 3 attempts: %w", lastErr)
|
|
}
|
|
|
|
// promoDiscount describes a temporary pricing discount applied on top of
|
|
// the standard (list) price from the model registry.
|
|
type promoDiscount struct {
|
|
Factor float64 // multiplier applied after standard calculation (0.25 = 75% off)
|
|
ExpiresAt time.Time // discount ends at this time (UTC)
|
|
}
|
|
|
|
// promoDiscounts maps model IDs to active promotional discounts.
|
|
// Sources:
|
|
// - DeepSeek v4 Pro: 75% off list pricing until 2026-05-31
|
|
// https://api-docs.deepseek.com/quick_start/pricing
|
|
var promoDiscounts = map[string]promoDiscount{
|
|
"deepseek-v4-pro": {
|
|
Factor: 0.25,
|
|
ExpiresAt: time.Date(2026, 5, 31, 23, 59, 59, 0, time.UTC),
|
|
},
|
|
}
|
|
|
|
func CalculateCost(registry *models.ModelRegistry, modelID string, promptTokens, completionTokens, reasoningTokens, cacheRead, cacheWrite uint32) float64 {
|
|
meta := registry.FindModel(modelID)
|
|
if meta == nil || meta.Cost == nil {
|
|
return 0.0
|
|
}
|
|
|
|
// promptTokens is usually the TOTAL prompt size.
|
|
// We subtract cacheRead from it to get the uncached part.
|
|
uncachedTokens := promptTokens
|
|
if cacheRead > 0 {
|
|
if cacheRead > promptTokens {
|
|
uncachedTokens = 0
|
|
} else {
|
|
uncachedTokens = promptTokens - cacheRead
|
|
}
|
|
}
|
|
|
|
cost := (float64(uncachedTokens) * meta.Cost.Input / 1000000.0) +
|
|
(float64(completionTokens) * meta.Cost.Output / 1000000.0)
|
|
|
|
if meta.Cost.CacheRead != nil {
|
|
cost += float64(cacheRead) * (*meta.Cost.CacheRead) / 1000000.0
|
|
}
|
|
if meta.Cost.CacheWrite != nil {
|
|
cost += float64(cacheWrite) * (*meta.Cost.CacheWrite) / 1000000.0
|
|
}
|
|
|
|
// Apply promotional discounts (e.g. DeepSeek 75% off until 2026-05-31).
|
|
if discount, ok := promoDiscounts[modelID]; ok {
|
|
if time.Now().UTC().Before(discount.ExpiresAt) {
|
|
cost *= discount.Factor
|
|
}
|
|
}
|
|
|
|
return cost
|
|
}
|