phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Correct Vertex Embedding Model Data/Prices (#7069)

Browse source 
* Correct embedding model prices
* Corrected max_tokens 
* Added text-embedding-005
This commit is contained in:
Emerson Gomes 2024-12-06 18:47:11 -06:00 • committed by GitHub
parent c3d1a3f903
commit 04d558e75f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 27 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

36
model_prices_and_context_window.json
View file

@ -3215,10 +3215,22 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
}, },
"text-embedding-004": { "text-embedding-004": {
"max_tokens": 3072, "max_tokens": 2048,
"max_input_tokens": 3072, "max_input_tokens": 2048,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
},
"text-embedding-005": {
"max_tokens": 2048,
"max_input_tokens": 2048,
"output_vector_size": 768,
"input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3228,7 +3240,8 @@
"max_tokens": 2048, "max_tokens": 2048,
"max_input_tokens": 2048, "max_input_tokens": 2048,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3238,7 +3251,8 @@
"max_tokens": 3072, "max_tokens": 3072,
"max_input_tokens": 3072, "max_input_tokens": 3072,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3248,7 +3262,8 @@
"max_tokens": 3072, "max_tokens": 3072,
"max_input_tokens": 3072, "max_input_tokens": 3072,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3258,7 +3273,8 @@
"max_tokens": 3072, "max_tokens": 3072,
"max_input_tokens": 3072, "max_input_tokens": 3072,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3268,7 +3284,8 @@
"max_tokens": 3072, "max_tokens": 3072,
"max_input_tokens": 3072, "max_input_tokens": 3072,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",
@ -3278,7 +3295,8 @@
"max_tokens": 3072, "max_tokens": 3072,
"max_input_tokens": 3072, "max_input_tokens": 3072,
"output_vector_size": 768, "output_vector_size": 768,
"input_cost_per_token": 0.00000000625, "input_cost_per_character": 0.000000025,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0, "output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models", "litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding", "mode": "embedding",