tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-11 16:26:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5571 from jalammar/cohere-updated-models

Browse Source 
Add Cohere refresh models and update pricing
This commit is contained in:
Ishaan Jaff
2024-09-10 17:22:51 -07:00
committed by GitHub
parent aed48e3bad 795b29dfc4
commit 899eaa9566
3 changed files with 71 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/providers/cohere.md
+3 -4
View File
@@ -49,12 +49,11 @@ for chunk in response:
## Supported Models
| Model Name | Function Call |
|------------|----------------|
| command-r-plus-08-2024 | `completion('command-r-plus-08-2024', messages)` |
| command-r-08-2024 | `completion('command-r-08-2024', messages)` |
| command-r-plus | `completion('command-r-plus', messages)` |
| command-r | `completion('command-r', messages)` |
| command-light | `completion('command-light', messages)` |
| command-r-plus | `completion('command-r-plus', messages)` |
| command-medium | `completion('command-medium', messages)` |
| command-medium-beta | `completion('command-medium-beta', messages)` |
| command-xlarge-nightly | `completion('command-xlarge-nightly', messages)` |
| command-nightly | `completion('command-nightly', messages)` |
litellm/model_prices_and_context_window_backup.json
+34 -32
View File
@@ -2662,30 +2662,50 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"command-r": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000050,
"output_cost_per_token": 0.0000015,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-r-08-2024": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-light": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.0000003,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat"
},
"command-r-plus": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-r-plus-08-2024": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
@@ -2694,8 +2714,8 @@
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000002,
"litellm_provider": "cohere",
"mode": "completion"
},
@@ -2703,26 +2723,8 @@
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"litellm_provider": "cohere",
"mode": "completion"
},
"command-medium-beta": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"litellm_provider": "cohere",
"mode": "completion"
},
"command-xlarge-beta": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000002,
"litellm_provider": "cohere",
"mode": "completion"
},
@@ -5545,4 +5547,4 @@
"mode": "embedding",
"source": "https://www.databricks.com/product/pricing/foundation-model-serving"
}
}
}
model_prices_and_context_window.json
+34 -32
View File
@@ -2662,30 +2662,50 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"command-r": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000050,
"output_cost_per_token": 0.0000015,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-r-08-2024": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-light": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.0000003,
"output_cost_per_token": 0.0000006,
"litellm_provider": "cohere_chat",
"mode": "chat"
},
"command-r-plus": {
"max_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
},
"command-r-plus-08-2024": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"litellm_provider": "cohere_chat",
"mode": "chat",
"supports_function_calling": true
@@ -2694,8 +2714,8 @@
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000002,
"litellm_provider": "cohere",
"mode": "completion"
},
@@ -2703,26 +2723,8 @@
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"litellm_provider": "cohere",
"mode": "completion"
},
"command-medium-beta": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"litellm_provider": "cohere",
"mode": "completion"
},
"command-xlarge-beta": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000002,
"litellm_provider": "cohere",
"mode": "completion"
},
@@ -5545,4 +5547,4 @@
"mode": "embedding",
"source": "https://www.databricks.com/product/pricing/foundation-model-serving"
}
}
}