phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Merge pull request #1290 from fcakyon/patch-1

Browse source 
fix typos & add missing names for azure models
This commit is contained in:
Ishaan Jaff 2024-01-01 17:58:17 +05:30 • committed by GitHub
commit 9cb5a2bec0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 35 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/__init__.py
View file

@ -335,9 +335,9 @@ baseten_models: List = [
# used for token counting # used for token counting
# Azure returns gpt-35-turbo in their responses, we need to map this to azure/gpt-3.5-turbo for token counting # Azure returns gpt-35-turbo in their responses, we need to map this to azure/gpt-3.5-turbo for token counting
azure_llms = { azure_llms = {
"gpt-35-turbo": "azure/gpt-3.5-turbo", "gpt-35-turbo": "azure/gpt-35-turbo",
"gpt-35-turbo-16k": "azure/gpt-3.5-turbo-16k", "gpt-35-turbo-16k": "azure/gpt-35-turbo-16k",
"gpt-35-turbo-instruct": "azure/gpt-3.5-turbo-instruct", "gpt-35-turbo-instruct": "azure/gpt-35-turbo-instruct",
} }
petals_models = [ petals_models = [

36
model_prices_and_context_window.json
View file

@ -118,28 +118,56 @@
"litellm_provider": "azure", "litellm_provider": "azure",
"mode": "chat" "mode": "chat"
}, },
"azure/gpt-4-32k": { "azure/gpt-4-0613": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006,
"litellm_provider": "azure",
"mode": "chat"
},
"azure/gpt-4-32k-0613": {
"max_tokens": 32768,
"input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012,
"litellm_provider": "azure",
"mode": "chat"
},
"azure/gpt-4-32k": {
"max_tokens": 32768,
"input_cost_per_token": 0.00006, "input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012, "output_cost_per_token": 0.00012,
"litellm_provider": "azure", "litellm_provider": "azure",
"mode": "chat" "mode": "chat"
}, },
"azure/gpt-4": { "azure/gpt-4": {
"max_tokens": 16385, "max_tokens": 8192,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006, "output_cost_per_token": 0.00006,
"litellm_provider": "azure", "litellm_provider": "azure",
"mode": "chat" "mode": "chat"
}, },
"azure/gpt-3.5-turbo-16k": { "azure/gpt-35-turbo-16k-0613": {
"max_tokens": 16385, "max_tokens": 16385,
"input_cost_per_token": 0.000003, "input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004, "output_cost_per_token": 0.000004,
"litellm_provider": "azure", "litellm_provider": "azure",
"mode": "chat" "mode": "chat"
}, },
"azure/gpt-3.5-turbo": { "azure/gpt-35-turbo-1106": {
"max_tokens": 16384,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002,
"litellm_provider": "azure",
"mode": "chat"
},
"azure/gpt-35-turbo-16k": {
"max_tokens": 16385,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004,
"litellm_provider": "azure",
"mode": "chat"
},
"azure/gpt-35-turbo": {
"max_tokens": 4097, "max_tokens": 4097,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,