diff --git a/internal/providers/configs/aihubmix.json b/internal/providers/configs/aihubmix.json index 039279e980b7e88ba72a846eacaa01da47385a04..1dc056af0dba1b56fa6fc8fddb9be849a143ebc2 100644 --- a/internal/providers/configs/aihubmix.json +++ b/internal/providers/configs/aihubmix.json @@ -2125,6 +2125,42 @@ "default_reasoning_effort": "medium", "supports_attachments": true }, + { + "id": "grok-4-20-non-reasoning", + "name": "Grok 4 20", + "cost_per_1m_in": 2, + "cost_per_1m_out": 6, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0.5, + "context_window": 2000000, + "default_max_tokens": 200000, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true + }, + { + "id": "grok-4-20-reasoning", + "name": "Grok 4 20 (reasoning)", + "cost_per_1m_in": 2, + "cost_per_1m_out": 6, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0.5, + "context_window": 2000000, + "default_max_tokens": 200000, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": true + }, { "id": "grok-4-fast-non-reasoning", "name": "Grok 4 Fast", diff --git a/internal/providers/configs/cortecs.json b/internal/providers/configs/cortecs.json index 46a0b86cd616eb552dc97d5acbe85cd4cff18233..0ff80b3acd7f3e83b32a7c2b0a059f5cd43879b2 100644 --- a/internal/providers/configs/cortecs.json +++ b/internal/providers/configs/cortecs.json @@ -7,6 +7,60 @@ "default_large_model_id": "qwen3-coder-30b-a3b-instruct", "default_small_model_id": "glm-4.7-flash", "models": [ + { + "id": "glm-5.1", + "name": "GLM 5.1", + "cost_per_1m_in": 1.304, + "cost_per_1m_out": 4.099, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 202752, + "default_max_tokens": 20275, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": false + }, + { + "id": "qwen3.5-9b", + "name": "Qwen3.5 9B", + "cost_per_1m_in": 0.14, + "cost_per_1m_out": 0.186, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 262144, + "default_max_tokens": 26214, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": false + }, + { + "id": "nemotron-3-super-120b-a12b", + "name": "Nemotron 3 Super 120B A12B", + "cost_per_1m_in": 0.28, + "cost_per_1m_out": 0.839, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 262144, + "default_max_tokens": 26214, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": false + }, { "id": "qwen3-coder-next", "name": "Qwen3 Coder Next", diff --git a/internal/providers/configs/huggingface.json b/internal/providers/configs/huggingface.json index 8538eeace5cc6217656fea1f526a17b145be877f..90e4267c12e816346eecbb2ed35971c3dbc0d74f 100644 --- a/internal/providers/configs/huggingface.json +++ b/internal/providers/configs/huggingface.json @@ -7,18 +7,6 @@ "default_large_model_id": "moonshotai/Kimi-K2.5:fireworks-ai", "default_small_model_id": "openai/gpt-oss-20b:groq", "models": [ - { - "id": "MiniMaxAI/MiniMax-M2.1:fireworks-ai", - "name": "MiniMaxAI/MiniMax-M2.1 (fireworks-ai)", - "cost_per_1m_in": 0, - "cost_per_1m_out": 0, - "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 204800, - "default_max_tokens": 8192, - "can_reason": false, - "supports_attachments": false - }, { "id": "MiniMaxAI/MiniMax-M2.5:fireworks-ai", "name": "MiniMaxAI/MiniMax-M2.5 (fireworks-ai)", diff --git a/internal/providers/configs/ionet.json b/internal/providers/configs/ionet.json index 9eb44d5ef2a2fe882756b090ac5cfd1d3666b242..beeadd9bc49ea0a87fd686b2486cce639afd5bb8 100644 --- a/internal/providers/configs/ionet.json +++ b/internal/providers/configs/ionet.json @@ -7,6 +7,18 @@ "default_large_model_id": "moonshotai/Kimi-K2.5", "default_small_model_id": "zai-org/GLM-4.7-Flash", "models": [ + { + "id": "google/gemma-4-26b-a4b-it", + "name": "Google: Gemma 4 26B A4B", + "cost_per_1m_in": 0.145, + "cost_per_1m_out": 0.5, + "cost_per_1m_in_cached": 0.08, + "cost_per_1m_out_cached": 0, + "context_window": 262144, + "default_max_tokens": 26214, + "can_reason": false, + "supports_attachments": false + }, { "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", "name": "Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR", @@ -112,8 +124,8 @@ { "id": "openai/gpt-oss-120b", "name": "OpenAI: gpt-oss-120b", - "cost_per_1m_in": 0.02, - "cost_per_1m_out": 0.1, + "cost_per_1m_in": 0.1, + "cost_per_1m_out": 0.4, "cost_per_1m_in_cached": 0.01, "cost_per_1m_out_cached": 0.04, "context_window": 131072, diff --git a/internal/providers/configs/openrouter.json b/internal/providers/configs/openrouter.json index 596bdf07ead4ad95b30596541e7988e9583e8e12..8241206515bd14f9405d9f2d6687c934ffa49f14 100644 --- a/internal/providers/configs/openrouter.json +++ b/internal/providers/configs/openrouter.json @@ -129,7 +129,7 @@ "cost_per_1m_in_cached": 3.75, "cost_per_1m_out_cached": 0.3, "context_window": 200000, - "default_max_tokens": 32000, + "default_max_tokens": 64000, "can_reason": true, "reasoning_levels": [ "low", @@ -367,24 +367,6 @@ "default_reasoning_effort": "medium", "supports_attachments": false }, - { - "id": "arcee-ai/trinity-mini:free", - "name": "Arcee AI: Trinity Mini (free)", - "cost_per_1m_in": 0, - "cost_per_1m_out": 0, - "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 131072, - "default_max_tokens": 13107, - "can_reason": true, - "reasoning_levels": [ - "low", - "medium", - "high" - ], - "default_reasoning_effort": "medium", - "supports_attachments": false - }, { "id": "arcee-ai/virtuoso-large", "name": "Arcee AI: Virtuoso Large", @@ -550,10 +532,10 @@ { "id": "deepseek/deepseek-chat-v3.1", "name": "DeepSeek: DeepSeek V3.1", - "cost_per_1m_in": 0.21, - "cost_per_1m_out": 0.79, + "cost_per_1m_in": 0.56, + "cost_per_1m_out": 1.68, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.13, + "cost_per_1m_out_cached": 0.28, "context_window": 163840, "default_max_tokens": 16384, "can_reason": true, @@ -640,12 +622,12 @@ { "id": "deepseek/deepseek-r1-0528", "name": "DeepSeek: R1 0528", - "cost_per_1m_in": 0.45, - "cost_per_1m_out": 2.15, + "cost_per_1m_in": 0.8, + "cost_per_1m_out": 2.4, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.225, + "cost_per_1m_out_cached": 0, "context_window": 163840, - "default_max_tokens": 32768, + "default_max_tokens": 16384, "can_reason": true, "reasoning_levels": [ "low", @@ -874,12 +856,12 @@ { "id": "google/gemma-4-26b-a4b-it", "name": "Google: Gemma 4 26B A4B ", - "cost_per_1m_in": 0.1625, - "cost_per_1m_out": 0.5, + "cost_per_1m_in": 0.13, + "cost_per_1m_out": 0.4, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 256000, - "default_max_tokens": 4096, + "context_window": 262144, + "default_max_tokens": 65536, "can_reason": true, "reasoning_levels": [ "low", @@ -1024,12 +1006,12 @@ { "id": "meta-llama/llama-3.3-70b-instruct", "name": "Meta: Llama 3.3 70B Instruct", - "cost_per_1m_in": 0.135, - "cost_per_1m_out": 0.4, + "cost_per_1m_in": 0.25, + "cost_per_1m_out": 0.75, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, - "default_max_tokens": 60000, + "default_max_tokens": 13107, "can_reason": false, "supports_attachments": false }, @@ -1072,12 +1054,12 @@ { "id": "minimax/minimax-m2", "name": "MiniMax: MiniMax M2", - "cost_per_1m_in": 0.3, - "cost_per_1m_out": 1.2, + "cost_per_1m_in": 0.255, + "cost_per_1m_out": 1, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0.03, - "context_window": 204800, - "default_max_tokens": 65536, + "context_window": 196608, + "default_max_tokens": 98304, "can_reason": true, "reasoning_levels": [ "low", @@ -1093,9 +1075,9 @@ "cost_per_1m_in": 0.3, "cost_per_1m_out": 1.2, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.03, - "context_window": 204800, - "default_max_tokens": 65536, + "cost_per_1m_out_cached": 0, + "context_window": 196608, + "default_max_tokens": 19660, "can_reason": true, "reasoning_levels": [ "low", @@ -1108,12 +1090,12 @@ { "id": "minimax/minimax-m2.5", "name": "MiniMax: MiniMax M2.5", - "cost_per_1m_in": 0.34, - "cost_per_1m_out": 1.19, + "cost_per_1m_in": 0.2, + "cost_per_1m_out": 1.18, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.04, - "context_window": 198000, - "default_max_tokens": 16384, + "cost_per_1m_out_cached": 0, + "context_window": 196608, + "default_max_tokens": 98304, "can_reason": true, "reasoning_levels": [ "low", @@ -1461,7 +1443,7 @@ "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, - "default_max_tokens": 131072, + "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", @@ -1474,10 +1456,10 @@ { "id": "moonshotai/kimi-k2.5", "name": "MoonshotAI: Kimi K2.5", - "cost_per_1m_in": 0.44, - "cost_per_1m_out": 2.2, + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 2.8, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.22, + "cost_per_1m_out_cached": 0, "context_window": 262144, "default_max_tokens": 131072, "can_reason": true, @@ -1725,7 +1707,7 @@ "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0.5, "context_window": 1047576, - "default_max_tokens": 16384, + "default_max_tokens": 104757, "can_reason": false, "supports_attachments": true }, @@ -1999,9 +1981,9 @@ "cost_per_1m_in": 1.25, "cost_per_1m_out": 10, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.13, + "cost_per_1m_out_cached": 0.125, "context_window": 128000, - "default_max_tokens": 16000, + "default_max_tokens": 8192, "can_reason": false, "supports_attachments": true }, @@ -2230,12 +2212,12 @@ { "id": "openai/gpt-oss-120b", "name": "OpenAI: gpt-oss-120b", - "cost_per_1m_in": 0.039, - "cost_per_1m_out": 0.19, + "cost_per_1m_in": 0.09, + "cost_per_1m_out": 0.36, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, + "cost_per_1m_out_cached": 0.045, "context_window": 131072, - "default_max_tokens": 13107, + "default_max_tokens": 32768, "can_reason": true, "reasoning_levels": [ "low", @@ -2266,12 +2248,12 @@ { "id": "openai/gpt-oss-20b", "name": "OpenAI: gpt-oss-20b", - "cost_per_1m_in": 0.03, - "cost_per_1m_out": 0.14, + "cost_per_1m_in": 0.05, + "cost_per_1m_out": 0.2, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, + "cost_per_1m_out_cached": 0.05, "context_window": 131072, - "default_max_tokens": 13107, + "default_max_tokens": 65536, "can_reason": true, "reasoning_levels": [ "low", @@ -2617,6 +2599,24 @@ "can_reason": false, "supports_attachments": false }, + { + "id": "qwen/qwen3-14b", + "name": "Qwen: Qwen3 14B", + "cost_per_1m_in": 0.2275, + "cost_per_1m_out": 0.91, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 131072, + "default_max_tokens": 4096, + "can_reason": true, + "reasoning_levels": [ + "low", + "medium", + "high" + ], + "default_reasoning_effort": "medium", + "supports_attachments": false + }, { "id": "qwen/qwen3-235b-a22b", "name": "Qwen: Qwen3 235B A22B", @@ -2638,12 +2638,12 @@ { "id": "qwen/qwen3-235b-a22b-2507", "name": "Qwen: Qwen3 235B A22B Instruct 2507", - "cost_per_1m_in": 0.2, - "cost_per_1m_out": 0.8, + "cost_per_1m_in": 0.22, + "cost_per_1m_out": 0.88, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, - "default_max_tokens": 131072, + "default_max_tokens": 8192, "can_reason": false, "supports_attachments": false }, @@ -2764,8 +2764,8 @@ { "id": "qwen/qwen3-coder", "name": "Qwen: Qwen3 Coder 480B A35B", - "cost_per_1m_in": 0.22, - "cost_per_1m_out": 1.8, + "cost_per_1m_in": 0.975, + "cost_per_1m_out": 4.875, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, @@ -2800,12 +2800,12 @@ { "id": "qwen/qwen3-coder-next", "name": "Qwen: Qwen3 Coder Next", - "cost_per_1m_in": 0.12, - "cost_per_1m_out": 0.75, + "cost_per_1m_in": 0.15, + "cost_per_1m_out": 0.8, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.06, + "cost_per_1m_out_cached": 0.12, "context_window": 262144, - "default_max_tokens": 32768, + "default_max_tokens": 131072, "can_reason": false, "supports_attachments": false }, @@ -2896,12 +2896,12 @@ { "id": "qwen/qwen3-vl-235b-a22b-instruct", "name": "Qwen: Qwen3 VL 235B A22B Instruct", - "cost_per_1m_in": 0.25, - "cost_per_1m_out": 1.5, + "cost_per_1m_in": 0.21, + "cost_per_1m_out": 1.9, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 256000, - "default_max_tokens": 8192, + "context_window": 131072, + "default_max_tokens": 16384, "can_reason": false, "supports_attachments": true }, @@ -3088,12 +3088,12 @@ { "id": "qwen/qwen3.5-9b", "name": "Qwen: Qwen3.5-9B", - "cost_per_1m_in": 0.05, + "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.15, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 256000, - "default_max_tokens": 16384, + "context_window": 262144, + "default_max_tokens": 26214, "can_reason": true, "reasoning_levels": [ "low", @@ -3157,9 +3157,9 @@ "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 262144, - "default_max_tokens": 32768, + "cost_per_1m_out_cached": 0.02, + "context_window": 256000, + "default_max_tokens": 128000, "can_reason": true, "reasoning_levels": [ "low", @@ -3187,6 +3187,18 @@ "default_reasoning_effort": "medium", "supports_attachments": false }, + { + "id": "thedrummer/rocinante-12b", + "name": "TheDrummer: Rocinante 12B", + "cost_per_1m_in": 0.17, + "cost_per_1m_out": 0.43, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 32768, + "default_max_tokens": 16384, + "can_reason": false, + "supports_attachments": false + }, { "id": "thedrummer/unslopnemo-12b", "name": "TheDrummer: UnslopNemo 12B", @@ -3241,9 +3253,9 @@ "cost_per_1m_in": 0.1, "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.01, + "cost_per_1m_out_cached": 0.1, "context_window": 262144, - "default_max_tokens": 32768, + "default_max_tokens": 131072, "can_reason": true, "reasoning_levels": [ "low", @@ -3309,7 +3321,7 @@ "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0.11, "context_window": 131072, - "default_max_tokens": 49152, + "default_max_tokens": 48000, "can_reason": true, "reasoning_levels": [ "low", @@ -3376,12 +3388,12 @@ { "id": "z-ai/glm-4.6", "name": "Z.ai: GLM 4.6", - "cost_per_1m_in": 0.39, - "cost_per_1m_out": 1.9, + "cost_per_1m_in": 0.55, + "cost_per_1m_out": 2.2, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, + "cost_per_1m_out_cached": 0.11, "context_window": 204800, - "default_max_tokens": 102400, + "default_max_tokens": 65536, "can_reason": true, "reasoning_levels": [ "low", @@ -3448,11 +3460,11 @@ { "id": "z-ai/glm-5", "name": "Z.ai: GLM 5", - "cost_per_1m_in": 0.95, - "cost_per_1m_out": 2.55, + "cost_per_1m_in": 1, + "cost_per_1m_out": 3.2, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0.2, - "context_window": 204800, + "context_window": 202800, "default_max_tokens": 65536, "can_reason": true, "reasoning_levels": [ @@ -3544,10 +3556,10 @@ { "id": "x-ai/grok-3-mini", "name": "xAI: Grok 3 Mini", - "cost_per_1m_in": 0.3, - "cost_per_1m_out": 0.5, + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 4, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.075, + "cost_per_1m_out_cached": 0.15, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, @@ -3562,10 +3574,10 @@ { "id": "x-ai/grok-3-mini-beta", "name": "xAI: Grok 3 Mini Beta", - "cost_per_1m_in": 0.3, - "cost_per_1m_out": 0.5, + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 4, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.075, + "cost_per_1m_out_cached": 0.15, "context_window": 131072, "default_max_tokens": 13107, "can_reason": true, diff --git a/internal/providers/configs/venice.json b/internal/providers/configs/venice.json index f7dc787c4bc5a066f41c91ffbf509b4d465f8985..70400d1f8941238eb67a7eee23446d64a50765eb 100644 --- a/internal/providers/configs/venice.json +++ b/internal/providers/configs/venice.json @@ -430,57 +430,27 @@ { "id": "grok-41-fast", "name": "Grok 4.1 Fast", - "cost_per_1m_in": 0.25, - "cost_per_1m_out": 0.625, + "cost_per_1m_in": 0.23, + "cost_per_1m_out": 0.57, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 1000000, "default_max_tokens": 30000, "can_reason": true, - "reasoning_levels": [ - "low", - "medium", - "high" - ], - "default_reasoning_effort": "medium", "supports_attachments": true }, { "id": "grok-4-20-beta", "name": "Grok 4.20 Beta", - "cost_per_1m_in": 2.5, - "cost_per_1m_out": 7.5, + "cost_per_1m_in": 2.27, + "cost_per_1m_out": 6.8, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 2000000, "default_max_tokens": 128000, "can_reason": true, - "reasoning_levels": [ - "low", - "medium", - "high" - ], - "default_reasoning_effort": "medium", "supports_attachments": true }, - { - "id": "grok-code-fast-1", - "name": "Grok Code Fast 1", - "cost_per_1m_in": 0.25, - "cost_per_1m_out": 1.87, - "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 256000, - "default_max_tokens": 10000, - "can_reason": true, - "reasoning_levels": [ - "low", - "medium", - "high" - ], - "default_reasoning_effort": "medium", - "supports_attachments": false - }, { "id": "kimi-k2-thinking", "name": "Kimi K2 Thinking", @@ -787,7 +757,7 @@ }, { "id": "qwen-3-6-plus", - "name": "Qwen 3.6 Plus", + "name": "Qwen 3.6 Plus Uncensored", "cost_per_1m_in": 0.625, "cost_per_1m_out": 3.75, "cost_per_1m_in_cached": 0, diff --git a/internal/providers/configs/vercel.json b/internal/providers/configs/vercel.json index b7bdf6aaafe4580452027f7aa751943e08df0344..89c16968337a48871c6d6ea786d8119aa6a7662e 100644 --- a/internal/providers/configs/vercel.json +++ b/internal/providers/configs/vercel.json @@ -1161,7 +1161,7 @@ "name": "Gemini 3.1 Flash Lite Preview", "cost_per_1m_in": 0.25, "cost_per_1m_out": 1.5, - "cost_per_1m_in_cached": 0, + "cost_per_1m_in_cached": 0.03, "cost_per_1m_out_cached": 0, "context_window": 1000000, "default_max_tokens": 8000,