Merge 012d6018f4 into 8df4a2670b

relay/adaptor/openai/constants.go

@@ -24,4 +24,6 @@ var ModelList = []string{
 	"o1", "o1-2024-12-17",
 	"o1-preview", "o1-preview-2024-09-12",
 	"o1-mini", "o1-mini-2024-09-12",
+	"o3-mini", "o3-mini-2025-01-31",
+	"gpt-4.5-preview", "gpt-4.5-preview-2025-02-27",
 }

relay/adaptor/openrouter/constants.go

@@ -1,20 +1,35 @@
 package openrouter
 
 var ModelList = []string{
-	"01-ai/yi-large",
+	"chatgpt-4o-latest",
-	"aetherwiing/mn-starcannon-12b",
+	"gpt-3.5-turbo",
-	"ai21/jamba-1-5-large",
+	"gpt-3.5-turbo-0125",
-	"ai21/jamba-1-5-mini",
+	"gpt-3.5-turbo-0613",
-	"ai21/jamba-instruct",
+	"gpt-3.5-turbo-1106",
-	"aion-labs/aion-1.0",
+	"gpt-3.5-turbo-16k",
-	"aion-labs/aion-1.0-mini",
+	"gpt-3.5-turbo-instruct",
-	"aion-labs/aion-rp-llama-3.1-8b",
+	"gpt-4",
-	"allenai/llama-3.1-tulu-3-405b",
+	"gpt-4-0314",
-	"alpindale/goliath-120b",
+	"gpt-4-1106-preview",
-	"alpindale/magnum-72b",
+	"gpt-4-32k",
-	"amazon/nova-lite-v1",
+	"gpt-4-32k-0314",
-	"amazon/nova-micro-v1",
+	"gpt-4-turbo",
-	"amazon/nova-pro-v1",
+	"gpt-4-turbo-preview",
+	"gpt-4o",
+	"gpt-4o-2024-05-13",
+	"gpt-4o-2024-08-06",
+	"gpt-4o-2024-11-20",
+	"gpt-4o-mini",
+	"gpt-4o-mini-2024-07-18",
+	"gpt-4o:extended",
+	"o1",
+	"o1-mini",
+	"o1-mini-2024-09-12",
+	"o1-preview",
+	"o1-preview-2024-09-12",
+	"o3-mini",
+	"o3-mini-high",
+	"gpt-4.5-preview",
 	"anthracite-org/magnum-v2-72b",
 	"anthracite-org/magnum-v4-72b",
 	"anthropic/claude-2",
@@ -37,31 +52,6 @@ var ModelList = []string{
 	"anthropic/claude-3.5-sonnet-20240620",
 	"anthropic/claude-3.5-sonnet-20240620:beta",
 	"anthropic/claude-3.5-sonnet:beta",
-	"cognitivecomputations/dolphin-mixtral-8x22b",
-	"cognitivecomputations/dolphin-mixtral-8x7b",
-	"cohere/command",
-	"cohere/command-r",
-	"cohere/command-r-03-2024",
-	"cohere/command-r-08-2024",
-	"cohere/command-r-plus",
-	"cohere/command-r-plus-04-2024",
-	"cohere/command-r-plus-08-2024",
-	"cohere/command-r7b-12-2024",
-	"databricks/dbrx-instruct",
-	"deepseek/deepseek-chat",
-	"deepseek/deepseek-chat-v2.5",
-	"deepseek/deepseek-chat:free",
-	"deepseek/deepseek-r1",
-	"deepseek/deepseek-r1-distill-llama-70b",
-	"deepseek/deepseek-r1-distill-llama-70b:free",
-	"deepseek/deepseek-r1-distill-llama-8b",
-	"deepseek/deepseek-r1-distill-qwen-1.5b",
-	"deepseek/deepseek-r1-distill-qwen-14b",
-	"deepseek/deepseek-r1-distill-qwen-32b",
-	"deepseek/deepseek-r1:free",
-	"eva-unit-01/eva-llama-3.33-70b",
-	"eva-unit-01/eva-qwen-2.5-32b",
-	"eva-unit-01/eva-qwen-2.5-72b",
 	"google/gemini-2.0-flash-001",
 	"google/gemini-2.0-flash-exp:free",
 	"google/gemini-2.0-flash-lite-preview-02-05:free",
@@ -84,17 +74,32 @@ var ModelList = []string{
 	"google/palm-2-chat-bison-32k",
 	"google/palm-2-codechat-bison",
 	"google/palm-2-codechat-bison-32k",
-	"gryphe/mythomax-l2-13b",
+	"deepseek/deepseek-chat",
-	"gryphe/mythomax-l2-13b:free",
+	"deepseek/deepseek-chat-v2.5",
-	"huggingfaceh4/zephyr-7b-beta:free",
+	"deepseek/deepseek-chat:free",
-	"infermatic/mn-inferor-12b",
+	"deepseek/deepseek-r1",
-	"inflection/inflection-3-pi",
+	"deepseek/deepseek-r1-distill-llama-70b",
-	"inflection/inflection-3-productivity",
+	"deepseek/deepseek-r1-distill-llama-70b:free",
-	"jondurbin/airoboros-l2-70b",
+	"deepseek/deepseek-r1-distill-llama-8b",
-	"liquid/lfm-3b",
+	"deepseek/deepseek-r1-distill-qwen-1.5b",
-	"liquid/lfm-40b",
+	"deepseek/deepseek-r1-distill-qwen-14b",
-	"liquid/lfm-7b",
+	"deepseek/deepseek-r1-distill-qwen-32b",
-	"mancer/weaver",
+	"deepseek/deepseek-r1:free",
+	"qwen/qvq-72b-preview",
+	"qwen/qwen-2-72b-instruct",
+	"qwen/qwen-2-7b-instruct",
+	"qwen/qwen-2-7b-instruct:free",
+	"qwen/qwen-2-vl-72b-instruct",
+	"qwen/qwen-2-vl-7b-instruct",
+	"qwen/qwen-2.5-72b-instruct",
+	"qwen/qwen-2.5-7b-instruct",
+	"qwen/qwen-2.5-coder-32b-instruct",
+	"qwen/qwen-max",
+	"qwen/qwen-plus",
+	"qwen/qwen-turbo",
+	"qwen/qwen-vl-plus:free",
+	"qwen/qwen2.5-vl-72b-instruct:free",
+	"qwen/qwq-32b-preview",
 	"meta-llama/llama-2-13b-chat",
 	"meta-llama/llama-2-70b-chat",
 	"meta-llama/llama-3-70b-instruct",
@@ -112,6 +117,10 @@ var ModelList = []string{
 	"meta-llama/llama-3.3-70b-instruct",
 	"meta-llama/llama-3.3-70b-instruct:free",
 	"meta-llama/llama-guard-2-8b",
+	"x-ai/grok-2-1212",
+	"x-ai/grok-2-vision-1212",
+	"x-ai/grok-beta",
+	"x-ai/grok-vision-beta",
 	"microsoft/phi-3-medium-128k-instruct",
 	"microsoft/phi-3-medium-128k-instruct:free",
 	"microsoft/phi-3-mini-128k-instruct",
@@ -144,6 +153,52 @@ var ModelList = []string{
 	"mistralai/mixtral-8x7b-instruct",
 	"mistralai/pixtral-12b",
 	"mistralai/pixtral-large-2411",
+	"perplexity/llama-3.1-sonar-huge-128k-online",
+	"perplexity/llama-3.1-sonar-large-128k-chat",
+	"perplexity/llama-3.1-sonar-large-128k-online",
+	"perplexity/llama-3.1-sonar-small-128k-chat",
+	"perplexity/llama-3.1-sonar-small-128k-online",
+	"perplexity/sonar",
+	"perplexity/sonar-reasoning",
+	"01-ai/yi-large",
+	"aetherwiing/mn-starcannon-12b",
+	"ai21/jamba-1-5-large",
+	"ai21/jamba-1-5-mini",
+	"ai21/jamba-instruct",
+	"aion-labs/aion-1.0",
+	"aion-labs/aion-1.0-mini",
+	"aion-labs/aion-rp-llama-3.1-8b",
+	"allenai/llama-3.1-tulu-3-405b",
+	"alpindale/goliath-120b",
+	"alpindale/magnum-72b",
+	"amazon/nova-lite-v1",
+	"amazon/nova-micro-v1",
+	"amazon/nova-pro-v1",
+	"cognitivecomputations/dolphin-mixtral-8x22b",
+	"cognitivecomputations/dolphin-mixtral-8x7b",
+	"cohere/command",
+	"cohere/command-r",
+	"cohere/command-r-03-2024",
+	"cohere/command-r-08-2024",
+	"cohere/command-r-plus",
+	"cohere/command-r-plus-04-2024",
+	"cohere/command-r-plus-08-2024",
+	"cohere/command-r7b-12-2024",
+	"databricks/dbrx-instruct",
+	"eva-unit-01/eva-llama-3.33-70b",
+	"eva-unit-01/eva-qwen-2.5-32b",
+	"eva-unit-01/eva-qwen-2.5-72b",
+	"gryphe/mythomax-l2-13b",
+	"gryphe/mythomax-l2-13b:free",
+	"huggingfaceh4/zephyr-7b-beta:free",
+	"infermatic/mn-inferor-12b",
+	"inflection/inflection-3-pi",
+	"inflection/inflection-3-productivity",
+	"jondurbin/airoboros-l2-70b",
+	"liquid/lfm-3b",
+	"liquid/lfm-40b",
+	"liquid/lfm-7b",
+	"mancer/weaver",
 	"neversleep/llama-3-lumimaid-70b",
 	"neversleep/llama-3-lumimaid-8b",
 	"neversleep/llama-3-lumimaid-8b:extended",
@@ -158,60 +213,10 @@ var ModelList = []string{
 	"nousresearch/nous-hermes-llama2-13b",
 	"nvidia/llama-3.1-nemotron-70b-instruct",
 	"nvidia/llama-3.1-nemotron-70b-instruct:free",
-	"openai/chatgpt-4o-latest",
-	"openai/gpt-3.5-turbo",
-	"openai/gpt-3.5-turbo-0125",
-	"openai/gpt-3.5-turbo-0613",
-	"openai/gpt-3.5-turbo-1106",
-	"openai/gpt-3.5-turbo-16k",
-	"openai/gpt-3.5-turbo-instruct",
-	"openai/gpt-4",
-	"openai/gpt-4-0314",
-	"openai/gpt-4-1106-preview",
-	"openai/gpt-4-32k",
-	"openai/gpt-4-32k-0314",
-	"openai/gpt-4-turbo",
-	"openai/gpt-4-turbo-preview",
-	"openai/gpt-4o",
-	"openai/gpt-4o-2024-05-13",
-	"openai/gpt-4o-2024-08-06",
-	"openai/gpt-4o-2024-11-20",
-	"openai/gpt-4o-mini",
-	"openai/gpt-4o-mini-2024-07-18",
-	"openai/gpt-4o:extended",
-	"openai/o1",
-	"openai/o1-mini",
-	"openai/o1-mini-2024-09-12",
-	"openai/o1-preview",
-	"openai/o1-preview-2024-09-12",
-	"openai/o3-mini",
-	"openai/o3-mini-high",
 	"openchat/openchat-7b",
 	"openchat/openchat-7b:free",
 	"openrouter/auto",
-	"perplexity/llama-3.1-sonar-huge-128k-online",
-	"perplexity/llama-3.1-sonar-large-128k-chat",
-	"perplexity/llama-3.1-sonar-large-128k-online",
-	"perplexity/llama-3.1-sonar-small-128k-chat",
-	"perplexity/llama-3.1-sonar-small-128k-online",
-	"perplexity/sonar",
-	"perplexity/sonar-reasoning",
 	"pygmalionai/mythalion-13b",
-	"qwen/qvq-72b-preview",
-	"qwen/qwen-2-72b-instruct",
-	"qwen/qwen-2-7b-instruct",
-	"qwen/qwen-2-7b-instruct:free",
-	"qwen/qwen-2-vl-72b-instruct",
-	"qwen/qwen-2-vl-7b-instruct",
-	"qwen/qwen-2.5-72b-instruct",
-	"qwen/qwen-2.5-7b-instruct",
-	"qwen/qwen-2.5-coder-32b-instruct",
-	"qwen/qwen-max",
-	"qwen/qwen-plus",
-	"qwen/qwen-turbo",
-	"qwen/qwen-vl-plus:free",
-	"qwen/qwen2.5-vl-72b-instruct:free",
-	"qwen/qwq-32b-preview",
 	"raifle/sorcererlm-8x22b",
 	"sao10k/fimbulvetr-11b-v2",
 	"sao10k/l3-euryale-70b",
@@ -227,9 +232,5 @@ var ModelList = []string{
 	"undi95/remm-slerp-l2-13b",
 	"undi95/toppy-m-7b",
 	"undi95/toppy-m-7b:free",
-	"x-ai/grok-2-1212",
-	"x-ai/grok-2-vision-1212",
-	"x-ai/grok-beta",
-	"x-ai/grok-vision-beta",
 	"xwin-lm/xwin-lm-70b",
 }

relay/billing/ratio/model.go

@@ -61,6 +61,8 @@ var ModelRatio = map[string]float64{
 	"o1-mini-2024-09-12":         1.5,
 	"o3-mini":                    1.5, // $3.00 / 1M input tokens
 	"o3-mini-2025-01-31":         1.5,
+	"gpt-4.5-preview":            37.5,
+	"gpt-4.5-preview-2025-02-27": 37.5,
 	"davinci-002":                1,   // $0.002 / 1K tokens
 	"babbage-002":                0.2, // $0.0004 / 1K tokens
 	"text-ada-001":               0.2,
@@ -750,7 +752,11 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		}
 		return 4.0 / 3.0
 	}
+	// including gpt-4, gpt-4.5
 	if strings.HasPrefix(name, "gpt-4") {
+		if strings.HasPrefix(name, "gpt-4.5") {
+			return 2
+		}
 		if strings.HasPrefix(name, "gpt-4o") {
 			if name == "gpt-4o-2024-05-13" {
 				return 3