diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index fa9c7ffbd5..df10efaa92 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8634,6 +8634,26 @@ "mode": "chat", "supports_tool_choice": true }, + "ollama/qwen-coder-14b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat", + "supports_function_calling": true + }, + "ollama/qwen-coder-32b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat", + "supports_function_calling": true + }, "ollama/codegemma": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -9179,24 +9199,6 @@ "litellm_provider": "perplexity", "mode": "chat" }, - "perplexity/sonar": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000001, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-pro": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 8096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "perplexity", - "mode": "chat" - }, "perplexity/pplx-7b-chat": { "max_tokens": 8192, "max_input_tokens": 8192,