From b68fee48a670708f02f22628e87f04844f326312 Mon Sep 17 00:00:00 2001 From: Kyrylo Yefimenko Date: Tue, 8 Oct 2024 15:50:58 +0100 Subject: [PATCH] (fix) Fix Groq pricing for llama3.1 (#6114) * Adjust ollama models to chat instead of completions * Fix Groq prices for llama3.1 --- model_prices_and_context_window.json | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7d060dd83..0f1ad77a6 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1491,8 +1491,8 @@ "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000059, - "output_cost_per_token": 0.00000079, + "input_cost_per_token": 0.00000005, + "output_cost_per_token": 0.00000008, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -5303,7 +5303,7 @@ "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", - "mode": "completion" + "mode": "chat" }, "ollama/llama2:7b": { "max_tokens": 4096, @@ -5312,7 +5312,7 @@ "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", - "mode": "completion" + "mode": "chat" }, "ollama/llama2:13b": { "max_tokens": 4096, @@ -5321,7 +5321,7 @@ "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", - "mode": "completion" + "mode": "chat" }, "ollama/llama2:70b": { "max_tokens": 4096, @@ -5330,7 +5330,7 @@ "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", - "mode": "completion" + "mode": "chat" }, "ollama/llama2-uncensored": { "max_tokens": 4096,