diff --git a/internal/agent/hyper/provider.json b/internal/agent/hyper/provider.json index eaff83c710da702b0de3982babe87cdf7a5f5cb7..a3675cd11b9fc7b369608f402da740f71e4cc792 100644 --- a/internal/agent/hyper/provider.json +++ b/internal/agent/hyper/provider.json @@ -43,9 +43,9 @@ { "id": "gemma-4-26b-a4b-it", "name": "Gemma 4 26B A4B", - "cost_per_1m_in": 0.102, - "cost_per_1m_out": 0.394, - "cost_per_1m_in_cached": 0.051, + "cost_per_1m_in": 0.1325, + "cost_per_1m_out": 0.44, + "cost_per_1m_in_cached": 0.06625, "cost_per_1m_out_cached": 0, "context_window": 256000, "default_max_tokens": 25600, @@ -55,9 +55,9 @@ { "id": "glm-5", "name": "GLM-5", - "cost_per_1m_in": 0.99, - "cost_per_1m_out": 3.07, - "cost_per_1m_in_cached": 0.495, + "cost_per_1m_in": 0.92, + "cost_per_1m_out": 2.976, + "cost_per_1m_in_cached": 0.46, "cost_per_1m_out_cached": 0, "context_window": 202752, "default_max_tokens": 20275, @@ -85,9 +85,9 @@ { "id": "gpt-oss-120b", "name": "gpt-oss-120b", - "cost_per_1m_in": 0.178, - "cost_per_1m_out": 0.68, - "cost_per_1m_in_cached": 0.089, + "cost_per_1m_in": 0.176, + "cost_per_1m_out": 0.652, + "cost_per_1m_in_cached": 0.088, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, @@ -103,9 +103,9 @@ { "id": "kimi-k2.5", "name": "Kimi K2.5", - "cost_per_1m_in": 0.518, - "cost_per_1m_out": 2.57, - "cost_per_1m_in_cached": 0.259, + "cost_per_1m_in": 0.58, + "cost_per_1m_out": 3, + "cost_per_1m_in_cached": 0.29, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214, @@ -133,9 +133,9 @@ { "id": "llama-3.3-70b-instruct", "name": "Llama 3.3 70B Instruct", - "cost_per_1m_in": 0.574, - "cost_per_1m_out": 0.668, - "cost_per_1m_in_cached": 0.287, + "cost_per_1m_in": 0.614, + "cost_per_1m_out": 0.864, + "cost_per_1m_in_cached": 0.307, "cost_per_1m_out_cached": 0, "context_window": 128000, "default_max_tokens": 12800, @@ -145,9 +145,9 @@ { "id": "llama-4-maverick-17b-128e-instruct-fp8", "name": "Llama 4 Maverick 17B 128E Instruct FP8", - "cost_per_1m_in": 0.35, - "cost_per_1m_out": 1.08, - "cost_per_1m_in_cached": 0.175, + "cost_per_1m_in": 0.28, + "cost_per_1m_out": 0.9, + "cost_per_1m_in_cached": 0.14, "cost_per_1m_out_cached": 0, "context_window": 430000, "default_max_tokens": 43000, @@ -223,9 +223,9 @@ { "id": "qwen3-coder-480b-a35b-instruct-int4-mixed-ar", "name": "Qwen3 Coder 480B A35B Instruct INT4 Mixed AR", - "cost_per_1m_in": 0.531, - "cost_per_1m_out": 2.605, - "cost_per_1m_in_cached": 0.2655, + "cost_per_1m_in": 0.541, + "cost_per_1m_out": 2.705, + "cost_per_1m_in_cached": 0.2705, "cost_per_1m_out_cached": 0, "context_window": 106000, "default_max_tokens": 10600, @@ -235,9 +235,9 @@ { "id": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct", - "cost_per_1m_in": 0.128, - "cost_per_1m_out": 1.28, - "cost_per_1m_in_cached": 0.064, + "cost_per_1m_in": 0.1175, + "cost_per_1m_out": 1.196, + "cost_per_1m_in_cached": 0.05875, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214,