feat: support gemini-2.0-flash (#2055)

* feat: support gemini-2.0-flash

- 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- Revamp pricing structures in the billing system to reflect current model values and deprecate outdated entries.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.

* feat: add new Gemini 2.0 flash models to adapter and billing ratio

* fix: update GetRequestURL to support gemini-1.5 model in versioning
This commit is contained in:
Laisky.Cai
2025-02-12 00:34:25 +08:00
committed by GitHub
parent 6916debf66
commit fef7ae048b
7 changed files with 76 additions and 31 deletions

View File

@@ -115,15 +115,24 @@ 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-001": 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,