From a4bc053e316a3d8d1ec3ad94f396ba528656e6a0 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 2 Nov 2026 13:25:15 +0000 Subject: [PATCH] fix(model_prices): consolidate verified pricing and Aplomb metadata Absorb verified pricing from #49547 and #49548 and Aplomb 1 metadata from #49539. Preserve provider tiers and remove an identical duplicate retirement key. Co-authored-by: Liutasil501 Co-authored-by: Adam Dalloul <47503782+Adam-Dalloul@users.noreply.github.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 42 ++++++++++++------- model_prices_and_context_window.json | 42 ++++++++++++------- 2 files changed, 56 insertions(+), 28 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a122ab8db09..62a6ff2d181 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1,4 +1,19 @@ { + "empiriolabs/aplomb-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "empiriolabs", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://empiriolabs.ai/models/aplomb-1", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages", + "/v1/decisions" + ], + "supports_vision": true + }, "sample_spec": { "code_interpreter_cost_per_session": 0.0, "computer_use_input_cost_per_1k_tokens": 0.0, @@ -23959,7 +23974,7 @@ "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost": 3.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -24033,7 +24048,7 @@ "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.5e-07, - "cache_read_input_token_cost": 2.16e-07, + "cache_read_input_token_cost": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -48970,7 +48985,6 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { - "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-07, "deprecation_date": "2026-11-04", "input_cost_per_token": 2e-06, @@ -64541,7 +64555,7 @@ "supports_vision": false }, "novita/deepseek/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 1.3200000000000002e-07, + "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, @@ -64653,13 +64667,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-venti": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 1.65e-07, + "input_cost_per_token": 8.25e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 2.475e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -64762,13 +64776,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-tall": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4.5000000000000003e-07, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.475e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.6e-06, + "output_cost_per_token": 1.43e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -66193,9 +66207,9 @@ "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "cache_read_input_token_cost": 1.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", @@ -66574,8 +66588,8 @@ "deepinfra/google/gemma-4-31B-it": { "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a122ab8db09..62a6ff2d181 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1,4 +1,19 @@ { + "empiriolabs/aplomb-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "empiriolabs", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://empiriolabs.ai/models/aplomb-1", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages", + "/v1/decisions" + ], + "supports_vision": true + }, "sample_spec": { "code_interpreter_cost_per_session": 0.0, "computer_use_input_cost_per_1k_tokens": 0.0, @@ -23959,7 +23974,7 @@ "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost": 3.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -24033,7 +24048,7 @@ "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.5e-07, - "cache_read_input_token_cost": 2.16e-07, + "cache_read_input_token_cost": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -48970,7 +48985,6 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { - "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-07, "deprecation_date": "2026-11-04", "input_cost_per_token": 2e-06, @@ -64541,7 +64555,7 @@ "supports_vision": false }, "novita/deepseek/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 1.3200000000000002e-07, + "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, @@ -64653,13 +64667,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-venti": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 1.65e-07, + "input_cost_per_token": 8.25e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 2.475e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -64762,13 +64776,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-tall": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4.5000000000000003e-07, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.475e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.6e-06, + "output_cost_per_token": 1.43e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -66193,9 +66207,9 @@ "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "cache_read_input_token_cost": 1.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", @@ -66574,8 +66588,8 @@ "deepinfra/google/gemma-4-31B-it": { "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true,