phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 10:14:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(router.py): add server cooldown logic

Browse source
This commit is contained in:
Krrish Dholakia 2023-11-22 15:59:41 -08:00
parent 4ece219ec5
commit 3e76d4b422
5 changed files with 67 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

12
model_prices_and_context_window.json
View file

@ -157,24 +157,24 @@
"claude-instant-1.2": {
"max_tokens": 100000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551,
"input_cost_per_token": 0.000000163,
"output_cost_per_token": 0.000000551,
"litellm_provider": "anthropic",
"mode": "chat"
},
"claude-2": {
"max_tokens": 100000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.00001102,
"output_cost_per_token": 0.00003268,
"input_cost_per_token": 0.000008,
"output_cost_per_token": 0.000024,
"litellm_provider": "anthropic",
"mode": "chat"
},
"claude-2.1": {
"max_tokens": 200000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.00001102,
"output_cost_per_token": 0.00003268,
"input_cost_per_token": 0.000008,
"output_cost_per_token": 0.000024,
"litellm_provider": "anthropic",
"mode": "chat"
},