From e2072b7aa89c7d8cac366de3540bc9f6ce62f810 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 16:24:12 -0700 Subject: [PATCH] chore(cost-map): add openai gpt-6.1-sol from the pricing page (#43738) Backport of #43738 to stable/1.103.x. Cherry-picked from a3552c451bf2b21aab31e7dd11b2f1757b970d46 (main). Prerequisite for #43935: adds the gpt-6.1-sol entry that fix corrects. Cost-map conflict resolved by appending the new entry. The cost-map schema and its schema test also allow the *_above_272k_tokens_batches keys this row carries, which main already allows. --- ...odel_prices_and_context_window_backup.json | 76 +++++++++++++++++++ model_prices_and_context_window.json | 76 +++++++++++++++++++ model_prices_and_context_window.schema.json | 16 ++++ tests/test_litellm/test_utils.py | 4 + 4 files changed, 172 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f16737981f4..81755749c64 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -75798,5 +75798,81 @@ "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "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_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 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_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "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_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_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_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "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_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f16737981f4..81755749c64 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -75798,5 +75798,81 @@ "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "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_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 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_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "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_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_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_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "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_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true } } diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 1a43df4a83e..18870ced268 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -397,6 +397,22 @@ "minimum": 0, "description": "USD per prompt token via the provider's batch API." }, + "cache_creation_input_token_cost_above_272k_tokens_batches": { + "type": "number", + "minimum": 0 + }, + "cache_read_input_token_cost_above_272k_tokens_batches": { + "type": "number", + "minimum": 0 + }, + "input_cost_per_token_above_272k_tokens_batches": { + "type": "number", + "minimum": 0 + }, + "output_cost_per_token_above_272k_tokens_batches": { + "type": "number", + "minimum": 0 + }, "input_cost_per_token_cache_hit": { "type": "number", "minimum": 0 diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index cc203950794..0e1977a5e78 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -792,6 +792,10 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_audio_token_batches": {"type": "number"}, "input_cost_per_image_token_batches": {"type": "number"}, "input_cost_per_token_batches": {"type": "number"}, + "cache_creation_input_token_cost_above_272k_tokens_batches": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens_batches": {"type": "number"}, + "input_cost_per_token_above_272k_tokens_batches": {"type": "number"}, + "output_cost_per_token_above_272k_tokens_batches": {"type": "number"}, "input_cost_per_video_token_batches": {"type": "number"}, "input_cost_per_token_cache_hit": {"type": "number"}, "input_cost_per_video_per_second": {"type": "number"},