Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-16 16:30:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🤖 feat: Tool Calling Support for DeepSeek V3.2 + OpenRouter Reasoning (#10752)
Some checks are pending
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Details
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Details
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Details
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
Details

Browse source 
* 🔧 chore: Update @librechat/agents to version 3.0.35

* ✨ feat: Add DeepSeek Model Pricing and Token Handling

- Introduced pricing and token limits for 'deepseek-chat' and 'deepseek-reasoner' models, including prompt and completion rates.
- Enhanced tests to validate pricing and token limits for DeepSeek models, ensuring correct handling of model variations and provider prefixes.
- Updated cache multipliers for DeepSeek models to reflect new pricing structure.
- Improved max output token handling for DeepSeek models, ensuring consistency across different endpoints.
This commit is contained in:
Danny Avila 2025-12-01 14:27:08 -05:00 • committed by GitHub
parent 026890cd27
commit 4202db1c99
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 144 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
packages/api/package.json
View file

@ -84,7 +84,7 @@
"@azure/storage-blob": "^12.27.0",
"@keyv/redis": "^4.3.3",
"@langchain/core": "^0.3.79",
"@librechat/agents": "^3.0.34",
"@librechat/agents": "^3.0.35",
"@librechat/data-schemas": "*",
"@modelcontextprotocol/sdk": "^1.21.0",
"axios": "^1.12.1",

15
packages/api/src/utils/tokens.ts
View file

@ -140,6 +140,7 @@ const anthropicModels = {
const deepseekModels = {
deepseek: 128000,
'deepseek-chat': 128000,
'deepseek-reasoner': 128000,
'deepseek-r1': 128000,
'deepseek-v3': 128000,
@ -347,11 +348,21 @@ const anthropicMaxOutputs = {
'claude-3-7-sonnet': 128000,
};
/** Outputs from https://api-docs.deepseek.com/quick_start/pricing */
const deepseekMaxOutputs = {
deepseek: 8000, // deepseek-chat default: 4K, max: 8K
'deepseek-chat': 8000,
'deepseek-reasoner': 64000, // default: 32K, max: 64K
'deepseek-r1': 64000,
'deepseek-v3': 8000,
'deepseek.r1': 64000,
};
export const maxOutputTokensMap = {
[EModelEndpoint.anthropic]: anthropicMaxOutputs,
[EModelEndpoint.azureOpenAI]: modelMaxOutputs,
[EModelEndpoint.openAI]: modelMaxOutputs,
[EModelEndpoint.custom]: modelMaxOutputs,
[EModelEndpoint.openAI]: { ...modelMaxOutputs, ...deepseekMaxOutputs },
[EModelEndpoint.custom]: { ...modelMaxOutputs, ...deepseekMaxOutputs },
};
/**