github/sub2api
4
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-19 16:17:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(gemini): 3.6 Flash 兜底价改为官方优惠价

Browse Source 
- 内置兜底价与本地价格表快照的 gemini-3.6-flash 改为 $0.75 输入 / $3.75 输出 /
  $0.075 缓存读取（Priority 档 $1.35 / $6.75 / $0.135），有效期至 2026-12-31，
  2027-01-01 起恢复 $1.50 / $7.50 / $0.15，与 3.7 / 3.8 Flash 及远程价格目录一致
This commit is contained in:
feeeei
2026-10-11 11:22:48 +08:00
parent f0ee427f0a
commit 4426593e9d
4 changed files with 22 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/internal/service/account_stats_pricing_test.go
+1 -1
View File
@@ -933,7 +933,7 @@ func TestResolveAccountStatsCost_Gemini36FlashTierUsesFallbackPricing(t *testing
UsageTokens{InputTokens: 1_000_000, OutputTokens: 1_000_000, CacheReadTokens: 1_000_000}, 1, 0, "", time.Time{}, true,
)
require.NotNil(t, result)
require.InDelta(t, 9.15, *result, 1e-12)
require.InDelta(t, 4.575, *result, 1e-12)
}
func TestResolveAccountStatsCost_AllMiss_ReturnsNil(t *testing.T) {
backend/internal/service/billing_service.go
+8 -7
View File
@@ -474,14 +474,15 @@ func (s *BillingService) initFallbackPricing() {
SupportsCacheBreakdown: false,
}
// Gemini 3.6 Flash (Google AI pricing: $1.50 input / $7.50 output /
// $0.15 cached input per MTok). Antigravity's -high/-low/-medium/-tiered
// aliases are matched below so unavailable remote pricing never records
// token-bearing requests at $0.
// Gemini 3.6 Flash (Google AI pricing: $0.75 input / $3.75 output /
// $0.075 cached input per MTok, promotional through 2026-12-31; official
// rates double to $1.50/$7.50/$0.15 from 2027-01-01). Antigravity's
// -high/-low/-medium/-tiered aliases are matched below so unavailable
// remote pricing never records token-bearing requests at $0.
s.fallbackPrices["gemini-3.6-flash"] = &ModelPricing{
InputPricePerToken: 1.5e-6,
OutputPricePerToken: 7.5e-6,
CacheReadPricePerToken: 0.15e-6,
InputPricePerToken: 0.75e-6,
OutputPricePerToken: 3.75e-6,
CacheReadPricePerToken: 0.075e-6,
SupportsCacheBreakdown: false,
}
backend/internal/service/pricing_service_test.go
+7 -7
View File
@@ -613,10 +613,10 @@ func TestBillingService_Gemini36FlashThinkingTierFallbacksAreBillable(t *testing
t.Run(model, func(t *testing.T) {
cost, err := svc.CalculateCost(model, tokens, 1)
require.NoError(t, err)
require.InDelta(t, 1.5, cost.InputCost, 1e-12)
require.InDelta(t, 7.5, cost.OutputCost, 1e-12)
require.InDelta(t, 0.15, cost.CacheReadCost, 1e-12)
require.InDelta(t, 9.15, cost.TotalCost, 1e-12)
require.InDelta(t, 0.75, cost.InputCost, 1e-12)
require.InDelta(t, 3.75, cost.OutputCost, 1e-12)
require.InDelta(t, 0.075, cost.CacheReadCost, 1e-12)
require.InDelta(t, 4.575, cost.TotalCost, 1e-12)
})
}
}
@@ -725,9 +725,9 @@ func TestDefaultPricingIncludesGemini36FlashRates(t *testing.T) {
t.Run(model, func(t *testing.T) {
pricing, err := billingSvc.GetModelPricing(model)
require.NoError(t, err)
require.InDelta(t, 1.5e-6, pricing.InputPricePerToken, 1e-12)
require.InDelta(t, 7.5e-6, pricing.OutputPricePerToken, 1e-12)
require.InDelta(t, 0.15e-6, pricing.CacheReadPricePerToken, 1e-12)
require.InDelta(t, 0.75e-6, pricing.InputPricePerToken, 1e-12)
require.InDelta(t, 3.75e-6, pricing.OutputPricePerToken, 1e-12)
require.InDelta(t, 0.075e-6, pricing.CacheReadPricePerToken, 1e-12)
})
}
}
backend/resources/model-pricing/model_prices_and_context_window.json
+6 -6
View File
@@ -2616,17 +2616,17 @@
"web_search_billing_unit": "per_query"
},
"gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_priority": 2.7e-07,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_priority": 2.7e-06,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_priority": 1.35e-07,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_priority": 1.35e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 7.5e-06,
"output_cost_per_token_priority": 1.35e-05,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_priority": 6.75e-06,
"source": "https://ai.google.dev/gemini-api/docs/latest-model",
"supports_prompt_caching": true,
"supports_reasoning": true,