tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-09 02:24:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

add chat-bison-32k@002

Browse Source
This commit is contained in:
Ishaan Jaff
2024-06-26 11:26:14 -07:00
parent 08412f736b
commit 553f258758
2 changed files with 60 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+30
View File
@@ -1107,6 +1107,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1117,6 +1119,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1127,6 +1131,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1137,6 +1143,20 @@
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"chat-bison-32k@002": {
"max_tokens": 8192,
"max_input_tokens": 32000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1147,6 +1167,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1157,6 +1179,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1197,6 +1221,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1207,6 +1233,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1217,6 +1245,8 @@
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
model_prices_and_context_window.json
+30
View File
@@ -1107,6 +1107,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1117,6 +1119,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1127,6 +1131,8 @@
"max_output_tokens": 4096,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1137,6 +1143,20 @@
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"chat-bison-32k@002": {
"max_tokens": 8192,
"max_input_tokens": 32000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1147,6 +1167,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1157,6 +1179,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1197,6 +1221,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1207,6 +1233,8 @@
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@@ -1217,6 +1245,8 @@
"max_output_tokens": 8192,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"