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

add pricing for vertex ai 21

Browse source
This commit is contained in:
Ishaan Jaff 2024-08-29 19:03:38 -07:00
parent ef47b2bc87
commit 26c03c9c8b
2 changed files with 90 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

45
litellm/model_prices_and_context_window_backup.json
View file

@ -2169,6 +2169,51 @@
"mode": "chat",
"supports_function_calling": true
},
"vertex_ai/jamba-1.5-mini@001": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-large@001": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-mini": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-large": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/mistral-nemo@2407": {
"max_tokens": 128000,
"max_input_tokens": 128000,

45
model_prices_and_context_window.json
View file

@ -2169,6 +2169,51 @@
"mode": "chat",
"supports_function_calling": true
},
"vertex_ai/jamba-1.5-mini@001": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-large@001": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-mini": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000004,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/jamba-1.5-large": {
"max_tokens": 256000,
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"litellm_provider": "vertex_ai-ai21_models",
"mode": "chat"
},
"vertex_ai/mistral-nemo@2407": {
"max_tokens": 128000,
"max_input_tokens": 128000,