From 5339d96b6fca9dfd3eb7c806e25fcf81ff7b8afb Mon Sep 17 00:00:00 2001 From: stimQQ Date: Thu, 22 Oct 2026 13:28:05 +0900 Subject: [PATCH] fix(apimodels): update gpt-6-astra prices to the current list apimodels.app raised gpt-6-astra to 3.4 / 17 per 1M tokens with cache read at 0.34; the above 272k rates keep the same x2 input and x1.5 output steps --- litellm/model_prices_and_context_window_backup.json | 12 ++++++------ model_prices_and_context_window.json | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6b58e6e1640..b9118c4e435 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -71610,17 +71610,17 @@ "supports_vision": true }, "apimodels/gpt-6-astra": { - "cache_read_input_token_cost": 2.4e-07, - "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, - "input_cost_per_token": 2.4e-06, - "input_cost_per_token_above_272k_tokens": 4.8e-06, + "cache_read_input_token_cost": 3.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 6.8e-07, + "input_cost_per_token": 3.4e-06, + "input_cost_per_token_above_272k_tokens": 6.8e-06, "litellm_provider": "apimodels", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token": 1.7e-05, + "output_cost_per_token_above_272k_tokens": 2.55e-05, "source": "https://apimodels.app/models/gpt-6-astra", "supports_function_calling": true, "supports_prompt_caching": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6b58e6e1640..b9118c4e435 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -71610,17 +71610,17 @@ "supports_vision": true }, "apimodels/gpt-6-astra": { - "cache_read_input_token_cost": 2.4e-07, - "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, - "input_cost_per_token": 2.4e-06, - "input_cost_per_token_above_272k_tokens": 4.8e-06, + "cache_read_input_token_cost": 3.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 6.8e-07, + "input_cost_per_token": 3.4e-06, + "input_cost_per_token_above_272k_tokens": 6.8e-06, "litellm_provider": "apimodels", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token": 1.7e-05, + "output_cost_per_token_above_272k_tokens": 2.55e-05, "source": "https://apimodels.app/models/gpt-6-astra", "supports_function_calling": true, "supports_prompt_caching": true,