xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2025-11-16 21:23:44 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge 012d6018f4 into 8df4a2670b

Browse Source
This commit is contained in:
longkeyy
2025-03-04 09:20:53 +00:00
committed by GitHub
parent 8df4a2670b 012d6018f4
commit 0233cfd11e
3 changed files with 174 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
relay/adaptor/openai/constants.go
View File

@@ -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",
}

209
relay/adaptor/openrouter/constants.go
View File

@@ -1,20 +1,35 @@
package openrouter
var ModelList = []string{
"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",
"chatgpt-4o-latest",
"gpt-3.5-turbo",
"gpt-3.5-turbo-0125",
"gpt-3.5-turbo-0613",
"gpt-3.5-turbo-1106",
"gpt-3.5-turbo-16k",
"gpt-3.5-turbo-instruct",
"gpt-4",
"gpt-4-0314",
"gpt-4-1106-preview",
"gpt-4-32k",
"gpt-4-32k-0314",
"gpt-4-turbo",
"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",
"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",
"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",
"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",
}

128
relay/billing/ratio/model.go
View File

@@ -26,67 +26,69 @@ var modelRatioLock sync.RWMutex
// 1 === ￥0.014 / 1k tokens
var ModelRatio = map[string]float64{
// https://openai.com/pricing
"gpt-4": 15,
"gpt-4-0314": 15,
"gpt-4-0613": 15,
"gpt-4-32k": 30,
"gpt-4-32k-0314": 30,
"gpt-4-32k-0613": 30,
"gpt-4-1106-preview": 5, // $0.01 / 1K tokens
"gpt-4-0125-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo": 5, // $0.01 / 1K tokens
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"gpt-4o": 2.5, // $0.005 / 1K tokens
"chatgpt-4o-latest": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-08-06": 1.25, // $0.0025 / 1K tokens
"gpt-4o-2024-11-20": 1.25, // $0.0025 / 1K tokens
"gpt-4o-mini": 0.075, // $0.00015 / 1K tokens
"gpt-4o-mini-2024-07-18": 0.075, // $0.00015 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens
"gpt-3.5-turbo-0301": 0.75,
"gpt-3.5-turbo-0613": 0.75,
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
"gpt-3.5-turbo-16k-0613": 1.5,
"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
"gpt-3.5-turbo-0125": 0.25, // $0.0005 / 1K tokens
"o1": 7.5, // $15.00 / 1M input tokens
"o1-2024-12-17": 7.5,
"o1-preview": 7.5, // $15.00 / 1M input tokens
"o1-preview-2024-09-12": 7.5,
"o1-mini": 1.5, // $3.00 / 1M input tokens
"o1-mini-2024-09-12": 1.5,
"o3-mini": 1.5, // $3.00 / 1M input tokens
"o3-mini-2025-01-31": 1.5,
"davinci-002": 1, // $0.002 / 1K tokens
"babbage-002": 0.2, // $0.0004 / 1K tokens
"text-ada-001": 0.2,
"text-babbage-001": 0.25,
"text-curie-001": 1,
"text-davinci-002": 10,
"text-davinci-003": 10,
"text-davinci-edit-001": 10,
"code-davinci-edit-001": 10,
"whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
"tts-1": 7.5, // $0.015 / 1K characters
"tts-1-1106": 7.5,
"tts-1-hd": 15, // $0.030 / 1K characters
"tts-1-hd-1106": 15,
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-embedding-3-small": 0.01,
"text-embedding-3-large": 0.065,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e-2": 0.02 * USD, // $0.016 - $0.020 / image
"dall-e-3": 0.04 * USD, // $0.040 - $0.120 / image
"gpt-4": 15,
"gpt-4-0314": 15,
"gpt-4-0613": 15,
"gpt-4-32k": 30,
"gpt-4-32k-0314": 30,
"gpt-4-32k-0613": 30,
"gpt-4-1106-preview": 5, // $0.01 / 1K tokens
"gpt-4-0125-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo": 5, // $0.01 / 1K tokens
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"gpt-4o": 2.5, // $0.005 / 1K tokens
"chatgpt-4o-latest": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-08-06": 1.25, // $0.0025 / 1K tokens
"gpt-4o-2024-11-20": 1.25, // $0.0025 / 1K tokens
"gpt-4o-mini": 0.075, // $0.00015 / 1K tokens
"gpt-4o-mini-2024-07-18": 0.075, // $0.00015 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens
"gpt-3.5-turbo-0301": 0.75,
"gpt-3.5-turbo-0613": 0.75,
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
"gpt-3.5-turbo-16k-0613": 1.5,
"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
"gpt-3.5-turbo-0125": 0.25, // $0.0005 / 1K tokens
"o1": 7.5, // $15.00 / 1M input tokens
"o1-2024-12-17": 7.5,
"o1-preview": 7.5, // $15.00 / 1M input tokens
"o1-preview-2024-09-12": 7.5,
"o1-mini": 1.5, // $3.00 / 1M input tokens
"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,
"text-babbage-001": 0.25,
"text-curie-001": 1,
"text-davinci-002": 10,
"text-davinci-003": 10,
"text-davinci-edit-001": 10,
"code-davinci-edit-001": 10,
"whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
"tts-1": 7.5, // $0.015 / 1K characters
"tts-1-1106": 7.5,
"tts-1-hd": 15, // $0.030 / 1K characters
"tts-1-hd-1106": 15,
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-embedding-3-small": 0.01,
"text-embedding-3-large": 0.065,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e-2": 0.02 * USD, // $0.016 - $0.020 / image
"dall-e-3": 0.04 * USD, // $0.040 - $0.120 / image
// https://docs.anthropic.com/en/docs/about-claude/models
"claude-instant-1.2": 0.8 / 1000 * USD,
"claude-2.0": 8.0 / 1000 * USD,
@@ -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