diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6dff2387fa3..6d85c103de0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -85419,6 +85419,7 @@ }, "gpt-6-astra-law": { "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 922000, @@ -85437,6 +85438,8 @@ "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -104450,6 +104453,306 @@ "supports_video_input": false, "supports_vision": false }, + "gpt-6.2-astra": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_12hr": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 4e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 8e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.00012, + "cache_creation_input_token_cost_above_12hr_batches": 1e-05, + "cache_creation_input_token_cost_above_12hr_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 6e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_creation_input_token_cost_priority": 2e-05, + "cache_creation_input_token_cost_ultrafast": 3e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 2.4e-06, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_ultrafast": 1.2e-06, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 8e-06, + "input_cost_per_token_above_272k_tokens": 1.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 3.2e-05, + "input_cost_per_token_above_272k_tokens_ultrafast": 4.8e-05, + "input_cost_per_token_batches": 4e-06, + "input_cost_per_token_priority": 1.6e-05, + "input_cost_per_token_ultrafast": 2.4e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 0.00012, + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00018, + "output_cost_per_token_batches": 2e-05, + "output_cost_per_token_priority": 8e-05, + "output_cost_per_token_ultrafast": 0.00012, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-astra": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6.2-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 1.5e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_ultrafast": 7.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 6e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_ultrafast": 3e-07, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 1.2e-05, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_ultrafast": 6e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 4.5e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "output_cost_per_token_ultrafast": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-sol": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6.2-astra-law": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_12hr": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 4e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 8e-06, + "input_cost_per_token_above_272k_tokens": 1.6e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_above_272k_tokens": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-astra-law": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-6.2-astra": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_12hr": 2e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6dff2387fa3..6d85c103de0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -85419,6 +85419,7 @@ }, "gpt-6-astra-law": { "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 922000, @@ -85437,6 +85438,8 @@ "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -104450,6 +104453,306 @@ "supports_video_input": false, "supports_vision": false }, + "gpt-6.2-astra": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_12hr": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 4e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 8e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.00012, + "cache_creation_input_token_cost_above_12hr_batches": 1e-05, + "cache_creation_input_token_cost_above_12hr_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 6e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_creation_input_token_cost_priority": 2e-05, + "cache_creation_input_token_cost_ultrafast": 3e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 2.4e-06, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_ultrafast": 1.2e-06, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 8e-06, + "input_cost_per_token_above_272k_tokens": 1.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 3.2e-05, + "input_cost_per_token_above_272k_tokens_ultrafast": 4.8e-05, + "input_cost_per_token_batches": 4e-06, + "input_cost_per_token_priority": 1.6e-05, + "input_cost_per_token_ultrafast": 2.4e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 0.00012, + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00018, + "output_cost_per_token_batches": 2e-05, + "output_cost_per_token_priority": 8e-05, + "output_cost_per_token_ultrafast": 0.00012, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-astra": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6.2-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 1.5e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_ultrafast": 7.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 6e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_ultrafast": 3e-07, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 1.2e-05, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_ultrafast": 6e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 4.5e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "output_cost_per_token_ultrafast": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-sol": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6.2-astra-law": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_12hr": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 4e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "fedramp_uplift_multiplier": 1.1, + "input_cost_per_token": 8e-06, + "input_cost_per_token_above_272k_tokens": 1.6e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_above_272k_tokens": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.2-astra-law": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-6.2-astra": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_12hr": 2e-05,