From c5da8eb41cdf10f3ba5171ecb0d2ad6600c9489a Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 24 Aug 2026 13:13:19 +0000 Subject: [PATCH] fix(model_prices): correct Claude 3 1-hour cache write rates, add W&B and Vertex retirement dates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 9 +++++++-- model_prices_and_context_window.json | 9 +++++++-- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2263f02dc90..b201a74cdc2 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12306,7 +12306,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 5e-07, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-04-20", "input_cost_per_token": 2.5e-07, @@ -12325,7 +12325,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2026-01-05", "input_cost_per_token": 1.5e-05, @@ -31641,6 +31641,7 @@ "supports_vision": false }, "multimodalembedding": { + "deprecation_date": "2027-04-01", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -42448,6 +42449,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "deprecation_date": "2026-08-25", "max_tokens": 262000, "max_input_tokens": 262000, "max_output_tokens": 262000, @@ -42458,6 +42460,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2-Instruct": { + "deprecation_date": "2026-03-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -42482,6 +42485,7 @@ "supports_vision": true }, "wandb/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-08-25", "max_tokens": 197000, "max_input_tokens": 197000, "max_output_tokens": 197000, @@ -53247,6 +53251,7 @@ "supports_vision": true }, "wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "max_input_tokens": 262000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2263f02dc90..b201a74cdc2 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12306,7 +12306,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 5e-07, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-04-20", "input_cost_per_token": 2.5e-07, @@ -12325,7 +12325,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2026-01-05", "input_cost_per_token": 1.5e-05, @@ -31641,6 +31641,7 @@ "supports_vision": false }, "multimodalembedding": { + "deprecation_date": "2027-04-01", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -42448,6 +42449,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "deprecation_date": "2026-08-25", "max_tokens": 262000, "max_input_tokens": 262000, "max_output_tokens": 262000, @@ -42458,6 +42460,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2-Instruct": { + "deprecation_date": "2026-03-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -42482,6 +42485,7 @@ "supports_vision": true }, "wandb/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-08-25", "max_tokens": 197000, "max_input_tokens": 197000, "max_output_tokens": 197000, @@ -53247,6 +53251,7 @@ "supports_vision": true }, "wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "max_input_tokens": 262000,