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

feat - add azure_ai llama v3.1 8B 70B and 405B

Browse source
This commit is contained in:
Wanis Elabbar 2024-07-23 23:57:50 +01:00 • committed by GitHub
parent f64a3309d1
commit e14ef3eeda
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 27 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

27
model_prices_and_context_window.json
View file

@ -760,6 +760,33 @@
"litellm_provider": "azure_ai", "litellm_provider": "azure_ai",
"mode": "chat" "mode": "chat"
}, },
"azure_ai/Meta-Llama-31-8B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.0000003,
"output_cost_per_token": 0.00000061,
"litellm_provider": "azure_ai",
"mode": "chat"
},
"azure_ai/Meta-Llama-31-70B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00000268,
"output_cost_per_token": 0.00000354,
"litellm_provider": "azure_ai",
"mode": "chat"
},
"azure_ai/Meta-Llama-31-405B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00000533,
"output_cost_per_token": 0.000016,
"litellm_provider": "azure_ai",
"mode": "chat"
},
"babbage-002": { "babbage-002": {
"max_tokens": 16384, "max_tokens": 16384,
"max_input_tokens": 16384, "max_input_tokens": 16384,