diff --git a/internal/agent/hyper/provider.json b/internal/agent/hyper/provider.json index b71e1ceec4784d8e75d9b0c3f5995aa0e30525f6..0d5e9d9a5e369057c800c993d936612d6cecab2d 100644 --- a/internal/agent/hyper/provider.json +++ b/internal/agent/hyper/provider.json @@ -3,39 +3,51 @@ "id": "hyper", "api_endpoint": "https://hyper.charm.land/api/v1/fantasy", "type": "hyper", - "default_large_model_id": "kimi-k2.6", + "default_large_model_id": "glm-5.1", "default_small_model_id": "deepseek-v4-flash", "models": [ { "id": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", - "cost_per_1m_in": 0.1446, - "cost_per_1m_out": 0.2912, - "cost_per_1m_in_cached": 0.0723, + "cost_per_1m_in": 0.14, + "cost_per_1m_out": 0.28, + "cost_per_1m_in_cached": 0.0028, "cost_per_1m_out_cached": 0, - "context_window": 1048576, - "default_max_tokens": 104857, + "context_window": 1000000, + "default_max_tokens": 8000, "can_reason": true, - "supports_attachments": false + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true }, { "id": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", - "cost_per_1m_in": 1.6082, - "cost_per_1m_out": 3.2164, - "cost_per_1m_in_cached": 0.8041, + "cost_per_1m_in": 0.435, + "cost_per_1m_out": 0.87, + "cost_per_1m_in_cached": 0.0036, "cost_per_1m_out_cached": 0, - "context_window": 1048576, - "default_max_tokens": 60000, + "context_window": 1000000, + "default_max_tokens": 8000, "can_reason": true, - "supports_attachments": false + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true }, { "id": "gemma-4-26b-a4b-it", "name": "Gemma 4 26B A4B", - "cost_per_1m_in": 0.12, + "cost_per_1m_in": 0.116, "cost_per_1m_out": 0.408, - "cost_per_1m_in_cached": 0.06, + "cost_per_1m_in_cached": 0.058, "cost_per_1m_out_cached": 0, "context_window": 256000, "default_max_tokens": 25600, @@ -45,9 +57,9 @@ { "id": "glm-5", "name": "GLM-5", - "cost_per_1m_in": 0.92, - "cost_per_1m_out": 2.976, - "cost_per_1m_in_cached": 0.46, + "cost_per_1m_in": 0.96, + "cost_per_1m_out": 3.036, + "cost_per_1m_in_cached": 0.48, "cost_per_1m_out_cached": 0, "context_window": 202752, "default_max_tokens": 20275, @@ -56,22 +68,28 @@ }, { "id": "glm-5.1", - "name": "GLM-5.1", - "cost_per_1m_in": 1.33, - "cost_per_1m_out": 4.22, - "cost_per_1m_in_cached": 0.665, + "name": "GLM 5.1", + "cost_per_1m_in": 1.4, + "cost_per_1m_out": 4.4, + "cost_per_1m_in_cached": 0.26, "cost_per_1m_out_cached": 0, - "context_window": 202750, - "default_max_tokens": 3276, + "context_window": 202800, + "default_max_tokens": 8000, "can_reason": true, - "supports_attachments": false + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true }, { "id": "gpt-oss-120b", "name": "gpt-oss-120b", - "cost_per_1m_in": 0.19, - "cost_per_1m_out": 0.63, - "cost_per_1m_in_cached": 0.095, + "cost_per_1m_in": 0.18, + "cost_per_1m_out": 0.61, + "cost_per_1m_in_cached": 0.09, "cost_per_1m_out_cached": 0, "context_window": 131072, "default_max_tokens": 13107, @@ -99,21 +117,27 @@ { "id": "kimi-k2.6", "name": "Kimi K2.6", - "cost_per_1m_in": 0.956, + "cost_per_1m_in": 0.95, "cost_per_1m_out": 4, - "cost_per_1m_in_cached": 0.478, + "cost_per_1m_in_cached": 0.16, "cost_per_1m_out_cached": 0, - "context_window": 262142, - "default_max_tokens": 26214, + "context_window": 262000, + "default_max_tokens": 8000, "can_reason": true, - "supports_attachments": false + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true }, { "id": "llama-3.3-70b-instruct", "name": "Llama 3.3 70B Instruct", - "cost_per_1m_in": 0.45, - "cost_per_1m_out": 0.72, - "cost_per_1m_in_cached": 0.225, + "cost_per_1m_in": 0.523, + "cost_per_1m_out": 0.786, + "cost_per_1m_in_cached": 0.2615, "cost_per_1m_out_cached": 0, "context_window": 128000, "default_max_tokens": 12800, @@ -135,27 +159,15 @@ { "id": "minimax-m2.7", "name": "MiniMax M2.7", - "cost_per_1m_in": 0.38, - "cost_per_1m_out": 1.52, - "cost_per_1m_in_cached": 0.19, + "cost_per_1m_in": 0.44, + "cost_per_1m_out": 1.76, + "cost_per_1m_in_cached": 0.22, "cost_per_1m_out_cached": 0, "context_window": 204800, "default_max_tokens": 20480, "can_reason": false, "supports_attachments": false }, - { - "id": "mistral-large-instruct-2411", - "name": "Mistral Large Instruct 2411", - "cost_per_1m_in": 2, - "cost_per_1m_out": 6, - "cost_per_1m_in_cached": 1, - "cost_per_1m_out_cached": 0, - "context_window": 128000, - "default_max_tokens": 12800, - "can_reason": false, - "supports_attachments": false - }, { "id": "qwen3.6-flash", "name": "Qwen3.6-Flash", @@ -207,9 +219,9 @@ { "id": "qwen3-coder-480b-a35b-instruct-int4-mixed-ar", "name": "Qwen3 Coder 480B A35B Instruct INT4 Mixed AR", - "cost_per_1m_in": 0.736, - "cost_per_1m_out": 2.03, - "cost_per_1m_in_cached": 0.368, + "cost_per_1m_in": 0.801, + "cost_per_1m_out": 2.185, + "cost_per_1m_in_cached": 0.4005, "cost_per_1m_out_cached": 0, "context_window": 106000, "default_max_tokens": 10600, @@ -219,9 +231,9 @@ { "id": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct", - "cost_per_1m_in": 0.1175, - "cost_per_1m_out": 1.136, - "cost_per_1m_in_cached": 0.05875, + "cost_per_1m_in": 0.1295, + "cost_per_1m_out": 1.216, + "cost_per_1m_in_cached": 0.06475, "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 26214,