xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2025-11-12 11:23:42 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: support gemini-2.0-flash

Browse Source 
- Enhance model support by adding new entries and refining checks for system instruction compatibility.
- Update logging display behavior and adjust default quotas for better user experience.
- Revamp pricing structures in the billing system to reflect current model values and deprecate outdated entries.
- Streamline code by replacing hardcoded values with configurations for maintainability.
This commit is contained in:
Laisky.Cai
2025-02-06 03:08:41 +00:00
parent d2903b673d
commit f1f8aa92c5
6 changed files with 70 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
relay/billing/ratio/model.go
View File

@@ -88,11 +88,11 @@ var ModelRatio = map[string]float64{
"claude-2.1": 8.0 / 1000 * USD,
"claude-3-haiku-20240307": 0.25 / 1000 * USD,
"claude-3-5-haiku-20241022": 1.0 / 1000 * USD,
"claude-3-5-haiku-latest": 1.0 / 1000 * USD,
"claude-3-5-haiku-latest": 1.0 / 1000 * USD,
"claude-3-sonnet-20240229": 3.0 / 1000 * USD,
"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
"claude-3-5-sonnet-20241022": 3.0 / 1000 * USD,
"claude-3-5-sonnet-latest" : 3.0 / 1000 * USD,
"claude-3-5-sonnet-latest": 3.0 / 1000 * USD,
"claude-3-opus-20240229": 15.0 / 1000 * USD,
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
"ERNIE-4.0-8K": 0.120 * RMB,
@@ -112,15 +112,23 @@ var ModelRatio = map[string]float64{
"bge-large-en": 0.002 * RMB,
"tao-8k": 0.002 * RMB,
// https://ai.google.dev/pricing
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
"gemini-1.0-pro": 1,
"gemini-1.5-pro": 1,
"gemini-1.5-pro-001": 1,
"gemini-1.5-flash": 1,
"gemini-1.5-flash-001": 1,
"gemini-2.0-flash-exp": 1,
"gemini-2.0-flash-thinking-exp": 1,
"gemini-2.0-flash-thinking-exp-01-21": 1,
// https://cloud.google.com/vertex-ai/generative-ai/pricing
// "gemma-2-2b-it": 0,
// "gemma-2-9b-it": 0,
// "gemma-2-27b-it": 0,
"gemini-pro": 0.25 * MILLI_USD, // $0.00025 / 1k characters -> $0.001 / 1k tokens
"gemini-1.0-pro": 0.125 * MILLI_USD,
"gemini-1.5-pro": 1.25 * MILLI_USD,
"gemini-1.5-pro-001": 1.25 * MILLI_USD,
"gemini-1.5-pro-experimental": 1.25 * MILLI_USD,
"gemini-1.5-flash": 0.075 * MILLI_USD,
"gemini-1.5-flash-001": 0.075 * MILLI_USD,
"gemini-1.5-flash-8b": 0.0375 * MILLI_USD,
"gemini-2.0-flash-exp": 0.075 * MILLI_USD,
"gemini-2.0-flash": 0.15 * MILLI_USD,
"gemini-2.0-flash-lite-preview-02-05": 0.075 * MILLI_USD,
"gemini-2.0-flash-thinking-exp-01-21": 0.075 * MILLI_USD,
"gemini-2.0-pro-exp-02-05": 1.25 * MILLI_USD,
"aqa": 1,
// https://open.bigmodel.cn/pricing
"glm-zero-preview": 0.01 * RMB,