phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

build(model_prices_and_context_window.json): add bedrock mistral small

Browse source
This commit is contained in:
Krrish Dholakia 2024-08-28 10:12:11 -07:00
parent 1f3dd43c27
commit 76c38c6d4b
3 changed files with 28 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/model_prices_and_context_window_backup.json
View file

@ -3297,6 +3297,16 @@
"mode": "chat",
"supports_function_calling": true
},
"mistral.mistral-small-2402-v1:0": {
"max_tokens": 8191,
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000003,
"litellm_provider": "bedrock",
"mode": "chat",
"supports_function_calling": true
},
"bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": {
"max_tokens": 8191,
"max_input_tokens": 32000,

12
litellm/proxy/_new_secret_config.yaml
View file

@ -1,12 +1,16 @@
model_list:
- model_name: fake-openai-endpoint
litellm_params:
model: sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614
model: gpt-3.5-turbo
# model: sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614
# sagemaker_base_url: https://exampleopenaiendpoint-production.up.railway.app/invocations/
# api_base: https://exampleopenaiendpoint-production.up.railway.app
input_cost_per_token: 10
output_cost_per_token: 10
litellm_settings:
max_internal_user_budget: 0.00001
internal_user_budget_duration: "3s" # reset every 3seconds

10
model_prices_and_context_window.json
View file

@ -3297,6 +3297,16 @@
"mode": "chat",
"supports_function_calling": true
},
"mistral.mistral-small-2402-v1:0": {
"max_tokens": 8191,
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000003,
"litellm_provider": "bedrock",
"mode": "chat",
"supports_function_calling": true
},
"bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": {
"max_tokens": 8191,
"max_input_tokens": 32000,