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

Merge pull request #4421 from BerriAI/litellm_add_vertex_models

Browse source 
[Feat] Add all Vertex AI Models
This commit is contained in:
Ishaan Jaff 2024-06-26 18:10:09 -07:00 • committed by GitHub
commit 3dc578555c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 373 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

184
litellm/model_prices_and_context_window_backup.json
View file

@ -1068,21 +1068,55 @@
"tool_use_system_prompt_tokens": 159
},
"text-bison": {
"max_tokens": 1024,
"max_tokens": 2048,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"max_output_tokens": 2048,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison@001": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison32k": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"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-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison32k@002": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"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-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@ -1113,6 +1147,8 @@
"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"
@ -1123,6 +1159,8 @@
"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"
@ -1133,6 +1171,8 @@
"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"
@ -1143,6 +1183,20 @@
"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"
@ -1153,6 +1207,8 @@
"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"
@ -1163,6 +1219,44 @@
"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"
},
"code-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"code-bison32k": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"code-bison-32k@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1197,12 +1291,36 @@
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"code-gecko-latest": {
"max_tokens": 64,
"max_input_tokens": 2048,
"max_output_tokens": 64,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"codechat-bison@latest": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"codechat-bison": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1213,6 +1331,20 @@
"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"
},
"codechat-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1223,6 +1355,20 @@
"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-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"codechat-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-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@ -1272,6 +1418,36 @@
"supports_function_calling": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-ultra": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"input_cost_per_image": 0.0025,
"input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-ultra-001": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"input_cost_per_image": 0.0025,
"input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-pro-002": {
"max_tokens": 8192,
"max_input_tokens": 32760,

18
litellm/tests/test_amazing_vertex_completion.py
View file

@ -329,11 +329,14 @@ def test_vertex_ai():
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"codechat-bison@latest",
"code-bison@001",
"text-bison@001",
"gemini-1.5-pro",
"gemini-1.5-pro-preview-0215",
]:
] or (
"gecko" in model or "32k" in model or "ultra" in model or "002" in model
):
# our account does not have access to this model
continue
print("making request", model)
@ -381,12 +384,15 @@ def test_vertex_ai_stream():
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"codechat-bison@latest",
"code-bison@001",
"text-bison@001",
"gemini-1.5-pro",
"gemini-1.5-pro-preview-0215",
]:
# ouraccount does not have access to this model
] or (
"gecko" in model or "32k" in model or "ultra" in model or "002" in model
):
# our account does not have access to this model
continue
print("making request", model)
response = completion(
@ -433,11 +439,12 @@ async def test_async_vertexai_response():
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"codechat-bison@latest",
"code-bison@001",
"text-bison@001",
"gemini-1.5-pro",
"gemini-1.5-pro-preview-0215",
]:
] or ("gecko" in model or "32k" in model or "ultra" in model or "002" in model):
# our account does not have access to this model
continue
try:
@ -479,11 +486,12 @@ async def test_async_vertexai_streaming_response():
"code-gecko@001",
"code-gecko@002",
"code-gecko@latest",
"codechat-bison@latest",
"code-bison@001",
"text-bison@001",
"gemini-1.5-pro",
"gemini-1.5-pro-preview-0215",
]:
] or ("gecko" in model or "32k" in model or "ultra" in model or "002" in model):
# our account does not have access to this model
continue
try:

184
model_prices_and_context_window.json
View file

@ -1068,21 +1068,55 @@
"tool_use_system_prompt_tokens": 159
},
"text-bison": {
"max_tokens": 1024,
"max_tokens": 2048,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"max_output_tokens": 2048,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison@001": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"max_output_tokens": 1024,
"input_cost_per_character": 0.00000025,
"output_cost_per_character": 0.0000005,
"litellm_provider": "vertex_ai-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison32k": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"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-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-bison32k@002": {
"max_tokens": 1024,
"max_input_tokens": 8192,
"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-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@ -1113,6 +1147,8 @@
"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"
@ -1123,6 +1159,8 @@
"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"
@ -1133,6 +1171,8 @@
"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"
@ -1143,6 +1183,20 @@
"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"
@ -1153,6 +1207,8 @@
"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"
@ -1163,6 +1219,44 @@
"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"
},
"code-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"code-bison32k": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"code-bison-32k@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1197,12 +1291,36 @@
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"code-gecko-latest": {
"max_tokens": 64,
"max_input_tokens": 2048,
"max_output_tokens": 64,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-text-models",
"mode": "completion",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"codechat-bison@latest": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
},
"codechat-bison": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1213,6 +1331,20 @@
"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"
},
"codechat-bison@002": {
"max_tokens": 1024,
"max_input_tokens": 6144,
"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"
@ -1223,6 +1355,20 @@
"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-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"codechat-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-code-chat-models",
"mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
@ -1272,6 +1418,36 @@
"supports_function_calling": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-ultra": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"input_cost_per_image": 0.0025,
"input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-ultra-001": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"input_cost_per_image": 0.0025,
"input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-pro-002": {
"max_tokens": 8192,
"max_input_tokens": 32760,