tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-12 20:22:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

groq add groq/llama-3.3 (#7076)

Browse Source
This commit is contained in:
Ishaan Jaff
2024-12-06 21:24:11 -08:00
committed by GitHub
parent 87ca62943b
commit 4d90e8ad62
2 changed files with 90 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+72 -9
View File
@@ -1740,6 +1740,24 @@
"supports_tool_choice": true,
"supports_prompt_caching": true
},
"groq/llama-3.3-70b-versatile": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/llama-3.3-70b-specdec": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000099,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/llama2-70b-4096": {
"max_tokens": 4096,
"max_input_tokens": 4096,
@@ -3215,10 +3233,22 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"text-embedding-004": {
"max_tokens": 3072,
"max_input_tokens": 3072,
"max_tokens": 2048,
"max_input_tokens": 2048,
"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,
"litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding",
@@ -3228,7 +3258,8 @@
"max_tokens": 2048,
"max_input_tokens": 2048,
"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",
@@ -3238,7 +3269,8 @@
"max_tokens": 3072,
"max_input_tokens": 3072,
"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",
@@ -3248,7 +3280,8 @@
"max_tokens": 3072,
"max_input_tokens": 3072,
"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",
@@ -3258,7 +3291,8 @@
"max_tokens": 3072,
"max_input_tokens": 3072,
"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",
@@ -3268,7 +3302,8 @@
"max_tokens": 3072,
"max_input_tokens": 3072,
"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",
@@ -3278,7 +3313,8 @@
"max_tokens": 3072,
"max_input_tokens": 3072,
"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",
@@ -3538,6 +3574,33 @@
"notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro."
}
},
"gemini/gemini-exp-1206": {
"max_tokens": 8192,
"max_input_tokens": 2097152,
"max_output_tokens": 8192,
"max_images_per_prompt": 3000,
"max_videos_per_prompt": 10,
"max_video_length": 1,
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_pdf_size_mb": 30,
"input_cost_per_token": 0,
"input_cost_per_token_above_128k_tokens": 0,
"output_cost_per_token": 0,
"output_cost_per_token_above_128k_tokens": 0,
"litellm_provider": "gemini",
"mode": "chat",
"supports_system_messages": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_response_schema": true,
"tpm": 4000000,
"rpm": 1000,
"source": "https://ai.google.dev/pricing",
"metadata": {
"notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro."
}
},
"gemini/gemini-1.5-flash-exp-0827": {
"max_tokens": 8192,
"max_input_tokens": 1048576,
model_prices_and_context_window.json
+18
View File
@@ -1740,6 +1740,24 @@
"supports_tool_choice": true,
"supports_prompt_caching": true
},
"groq/llama-3.3-70b-versatile": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/llama-3.3-70b-specdec": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000099,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/llama2-70b-4096": {
"max_tokens": 4096,
"max_input_tokens": 4096,