compass.utilities.LLM_COST_REGISTRY

LLM_COST_REGISTRY = {'gpt-4.1': {'prompt': 2, 'response': 8}, 'gpt-4.1-mini': {'prompt': 0.4, 'response': 1.6}, 'gpt-4.1-nano': {'prompt': 0.1, 'response': 0.4}, 'gpt-4.5': {'prompt': 75, 'response': 150}, 'gpt-4o': {'prompt': 2.5, 'response': 10}, 'gpt-4o-mini': {'prompt': 0.15, 'response': 0.6}, 'gpt-5': {'prompt': 1.25, 'response': 10}, 'gpt-5-chat-latest': {'prompt': 1.25, 'response': 10}, 'gpt-5-mini': {'prompt': 0.25, 'response': 2}, 'gpt-5-nano': {'prompt': 0.05, 'response': 0.4}, 'o1': {'prompt': 15, 'response': 60}, 'o3-mini': {'prompt': 1.1, 'response': 4.4}, 'wetosa-gpt-4.1': {'prompt': 2, 'response': 8}, 'wetosa-gpt-4.1-mini': {'prompt': 0.4, 'response': 1.6}, 'wetosa-gpt-4.1-nano': {'prompt': 0.1, 'response': 0.4}, 'wetosa-gpt-4o': {'prompt': 2.5, 'response': 10}, 'wetosa-gpt-4o-mini': {'prompt': 0.15, 'response': 0.6}, 'wetosa-gpt-5': {'prompt': 1.25, 'response': 10}, 'wetosa-gpt-5-chat-latest': {'prompt': 1.25, 'response': 10}, 'wetosa-gpt-5-mini': {'prompt': 0.25, 'response': 2}, 'wetosa-gpt-5-nano': {'prompt': 0.05, 'response': 0.4}}

LLM Costs registry

The registry maps model names to a dictionary that contains the cost (in $/million tokens) for both prompt and response tokens.