From 795b29dfc4613cd0930834ecd71fb9bb840c7cec Mon Sep 17 00:00:00 2001 From: Jay Alammar Date: Tue, 10 Sep 2024 13:47:05 -0400 Subject: [PATCH] Updating Cohere models, prices, and documentation --- docs/my-website/docs/providers/cohere.md | 7 ++--- ...odel_prices_and_context_window_backup.json | 30 ++++--------------- model_prices_and_context_window.json | 30 ++++--------------- 3 files changed, 15 insertions(+), 52 deletions(-) diff --git a/docs/my-website/docs/providers/cohere.md b/docs/my-website/docs/providers/cohere.md index 1a841cbd5..1154dc3c4 100644 --- a/docs/my-website/docs/providers/cohere.md +++ b/docs/my-website/docs/providers/cohere.md @@ -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)` | diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2af58b3a9..ff2bdfa6b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2685,8 +2685,8 @@ "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": 0.0000003, + "output_cost_per_token": 0.0000006, "litellm_provider": "cohere_chat", "mode": "chat" }, @@ -2714,8 +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" }, @@ -2723,26 +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" }, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2af58b3a9..ff2bdfa6b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2685,8 +2685,8 @@ "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": 0.0000003, + "output_cost_per_token": 0.0000006, "litellm_provider": "cohere_chat", "mode": "chat" }, @@ -2714,8 +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" }, @@ -2723,26 +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" },