diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 25124a13e7..30a192331e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -761,6 +761,20 @@ "litellm_provider": "perplexity", "mode": "chat" }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "max_tokens": 16384, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.00000015, + "litellm_provider": "anyscale", + "mode": "chat" + }, + "anyscale/Zephyr-7b-beta": { + "max_tokens": 16384, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.00000015, + "litellm_provider": "anyscale", + "mode": "chat" + }, "anyscale/meta-llama/Llama-2-7b-chat-hf": { "max_tokens": 4096, "input_cost_per_token": 0.00000015, @@ -768,13 +782,6 @@ "litellm_provider": "anyscale", "mode": "chat" }, - "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { - "max_tokens": 4096, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000015, - "litellm_provider": "anyscale", - "mode": "chat" - }, "anyscale/meta-llama/Llama-2-13b-chat-hf": { "max_tokens": 4096, "input_cost_per_token": 0.00000025, @@ -790,7 +797,7 @@ "mode": "chat" }, "anyscale/codellama/CodeLlama-34b-Instruct-hf": { - "max_tokens": 4096, + "max_tokens": 16384, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "litellm_provider": "anyscale",