Ecosystem/ai-gateway
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: update gemini model and price (#1705)

Browse Source
This commit is contained in:
longkeyy 2024-08-06 23:43:33 +08:00 committed by GitHub
parent e7e99e558a
commit b4bfa418a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 23 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
relay/adaptor/gemini/constants.go
View File

@ -3,6 +3,5 @@ package gemini
// https://ai.google.dev/models/gemini // https://ai.google.dev/models/gemini
var ModelList = []string{ var ModelList = []string{
"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro", "gemini-pro", "gemini-1.0-pro", "gemini-1.5-flash", "gemini-1.5-pro", "text-embedding-004", "aqa",
"gemini-pro-vision", "gemini-1.0-pro-vision-001", "embedding-001", "text-embedding-004",
} }

9
relay/adaptor/groq/constants.go
View File

@ -4,9 +4,14 @@ package groq
var ModelList = []string{ var ModelList = []string{
"gemma-7b-it", "gemma-7b-it",
"llama2-7b-2048",
"llama2-70b-4096",
"mixtral-8x7b-32768", "mixtral-8x7b-32768",
"llama3-8b-8192", "llama3-8b-8192",
"llama3-70b-8192", "llama3-70b-8192",
"gemma2-9b-it",
"llama-3.1-405b-reasoning",
"llama-3.1-70b-versatile",
"llama-3.1-8b-instant",
"llama3-groq-70b-8192-tool-use-preview",
"llama3-groq-8b-8192-tool-use-preview",
"whisper-large-v3",
} }

27
relay/billing/ratio/model.go
View File

@ -98,12 +98,11 @@ var ModelRatio = map[string]float64{
"bge-large-en": 0.002 * RMB, "bge-large-en": 0.002 * RMB,
"tao-8k": 0.002 * RMB, "tao-8k": 0.002 * RMB,
// https://ai.google.dev/pricing // https://ai.google.dev/pricing
"PaLM-2": 1, "gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens "gemini-1.0-pro": 1,
"gemini-pro-vision": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens "gemini-1.5-flash": 1,
"gemini-1.0-pro-vision-001": 1, "gemini-1.5-pro": 1,
"gemini-1.0-pro-001": 1, "aqa": 1,
"gemini-1.5-pro": 1,
// https://open.bigmodel.cn/pricing // https://open.bigmodel.cn/pricing
"glm-4": 0.1 * RMB, "glm-4": 0.1 * RMB,
"glm-4v": 0.1 * RMB, "glm-4v": 0.1 * RMB,
@ -158,12 +157,16 @@ var ModelRatio = map[string]float64{
"mistral-large-latest": 8.0 / 1000 * USD, "mistral-large-latest": 8.0 / 1000 * USD,
"mistral-embed": 0.1 / 1000 * USD, "mistral-embed": 0.1 / 1000 * USD,
// https://wow.groq.com/#:~:text=inquiries%C2%A0here.-,Model,-Current%20Speed // https://wow.groq.com/#:~:text=inquiries%C2%A0here.-,Model,-Current%20Speed
"llama3-70b-8192": 0.59 / 1000 * USD, "gemma-7b-it": 0.07 / 1000000 * USD,
"mixtral-8x7b-32768": 0.27 / 1000 * USD, "mixtral-8x7b-32768": 0.24 / 1000000 * USD,
"llama3-8b-8192": 0.05 / 1000 * USD, "llama3-8b-8192": 0.05 / 1000000 * USD,
"gemma-7b-it": 0.1 / 1000 * USD, "llama3-70b-8192": 0.59 / 1000000 * USD,
"llama2-70b-4096": 0.64 / 1000 * USD, "gemma2-9b-it": 0.20 / 1000000 * USD,
"llama2-7b-2048": 0.1 / 1000 * USD, "llama-3.1-405b-reasoning": 0.89 / 1000000 * USD,
"llama-3.1-70b-versatile": 0.59 / 1000000 * USD,
"llama-3.1-8b-instant": 0.05 / 1000000 * USD,
"llama3-groq-70b-8192-tool-use-preview": 0.89 / 1000000 * USD,
"llama3-groq-8b-8192-tool-use-preview": 0.19 / 1000000 * USD,
// https://platform.lingyiwanwu.com/docs#-计费单元 // https://platform.lingyiwanwu.com/docs#-计费单元
"yi-34b-chat-0205": 2.5 / 1000 * RMB, "yi-34b-chat-0205": 2.5 / 1000 * RMB,
"yi-34b-chat-200k": 12.0 / 1000 * RMB, "yi-34b-chat-200k": 12.0 / 1000 * RMB,