diff --git a/conf/models/302ai.json b/conf/models/302ai.json index d499d34443..1ac370c6a2 100644 --- a/conf/models/302ai.json +++ b/conf/models/302ai.json @@ -17,7 +17,8 @@ "models": [ { "name": "kimi-k2.6", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat", "vision" @@ -32,7 +33,8 @@ }, { "name": "gpt-5.5", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -43,7 +45,8 @@ }, { "name": "gpt-5.4", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -54,7 +57,8 @@ }, { "name": "gpt-5.4-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -65,7 +69,8 @@ }, { "name": "gpt-5.4-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -76,7 +81,8 @@ }, { "name": "gpt-5.2-pro", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -87,7 +93,8 @@ }, { "name": "gpt-5.2", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -98,7 +105,8 @@ }, { "name": "gpt-5.1", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -109,7 +117,8 @@ }, { "name": "gpt-5.1-chat-latest", - "max_tokens": 400000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -120,7 +129,8 @@ }, { "name": "gpt-5", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -131,7 +141,8 @@ }, { "name": "gpt-5-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -142,7 +153,8 @@ }, { "name": "gpt-5-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -153,7 +165,8 @@ }, { "name": "gpt-5-chat-latest", - "max_tokens": 400000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -164,7 +177,8 @@ }, { "name": "gpt-4.1", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -175,7 +189,8 @@ }, { "name": "gpt-4.1-mini", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -186,7 +201,8 @@ }, { "name": "gpt-4.1-nano", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -197,7 +213,8 @@ }, { "name": "gpt-4.5-preview", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], @@ -207,7 +224,8 @@ }, { "name": "gpt-4o-mini", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -218,7 +236,8 @@ }, { "name": "gpt-4o", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -229,7 +248,8 @@ }, { "name": "gpt-3.5-turbo", - "max_tokens": 4096, + "content_length": 16385, + "max_output": 4096, "model_types": [ "chat" ], @@ -239,7 +259,8 @@ }, { "name": "gpt-3.5-turbo-16k-0613", - "max_tokens": 16385, + "content_length": 16385, + "max_output": 4096, "model_types": [ "chat" ], diff --git a/conf/models/aliyun.json b/conf/models/aliyun.json index e0cc8f4ef4..0f4c845149 100644 --- a/conf/models/aliyun.json +++ b/conf/models/aliyun.json @@ -16,7 +16,8 @@ "models": [ { "name": "qwen-flash", - "max_tokens": 995904, + "content_length": 1048576, + "max_output": 8192, "model_types": [ "chat" ], @@ -33,7 +34,8 @@ }, { "name": "qwen3-vl-plus", - "max_tokens": 256000, + "content_length": 262144, + "max_output": 8192, "model_types": [ "vision", "chat" diff --git a/conf/models/anthropic.json b/conf/models/anthropic.json index 98b1571c3b..d031c4b0f4 100644 --- a/conf/models/anthropic.json +++ b/conf/models/anthropic.json @@ -12,7 +12,8 @@ "models": [ { "name": "claude-opus-4-8", - "max_tokens": 128000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -20,7 +21,8 @@ }, { "name": "claude-opus-4-7", - "max_tokens": 128000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -28,7 +30,8 @@ }, { "name": "claude-opus-4-6", - "max_tokens": 128000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -36,7 +39,8 @@ }, { "name": "claude-opus-4-5-20251101", - "max_tokens": 128000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat", "vision" @@ -44,7 +48,8 @@ }, { "name": "claude-opus-4-1-20250805", - "max_tokens": 128000, + "content_length": 200000, + "max_output": 32000, "model_types": [ "chat", "vision" @@ -52,7 +57,8 @@ }, { "name": "claude-opus-4-20250514", - "max_tokens": 128000, + "content_length": 200000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -60,7 +66,8 @@ }, { "name": "claude-sonnet-4-6", - "max_tokens": 64000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -77,7 +84,8 @@ }, { "name": "claude-sonnet-4-20250514", - "max_tokens": 64000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat", "vision" @@ -85,7 +93,8 @@ }, { "name": "claude-haiku-4-5-20251001", - "max_tokens": 64000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat", "vision" @@ -93,7 +102,8 @@ }, { "name": "claude-3-7-sonnet-20250219", - "max_tokens": 64000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat", "vision" @@ -101,7 +111,8 @@ }, { "name": "claude-3-5-sonnet-20241022", - "max_tokens": 8192, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -109,7 +120,8 @@ }, { "name": "claude-3-5-haiku-20241022", - "max_tokens": 8192, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat", "vision" diff --git a/conf/models/astraflow.json b/conf/models/astraflow.json index 89a4fd6238..6b33a8fd0e 100644 --- a/conf/models/astraflow.json +++ b/conf/models/astraflow.json @@ -35,7 +35,8 @@ }, { "name": "claude-opus-4-7", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat" ], @@ -45,7 +46,8 @@ }, { "name": "claude-opus-4-6", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat" ], @@ -66,7 +68,8 @@ }, { "name": "claude-haiku-4-5-20251001", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat" ], @@ -76,7 +79,8 @@ }, { "name": "gpt-5.4", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat" ], @@ -86,7 +90,8 @@ }, { "name": "gpt-5.4-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat" ], @@ -96,7 +101,8 @@ }, { "name": "gpt-5.4-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat" ], @@ -106,7 +112,8 @@ }, { "name": "gpt-4o-mini", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], @@ -116,7 +123,8 @@ }, { "name": "Qwen/Qwen3-Max", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -126,7 +134,8 @@ }, { "name": "Qwen/Qwen3-Coder", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat" ], @@ -136,7 +145,8 @@ }, { "name": "Qwen/Qwen3-32B", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -146,7 +156,8 @@ }, { "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -156,7 +167,8 @@ }, { "name": "kimi-k2.6", - "max_tokens": 200000, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -166,7 +178,8 @@ }, { "name": "glm-5.1", - "max_tokens": 128000, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -176,7 +189,8 @@ }, { "name": "MiniMax-M2.7", - "max_tokens": 1000000, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -186,7 +200,8 @@ }, { "name": "MiniMax-M2", - "max_tokens": 1000000, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -196,7 +211,8 @@ }, { "name": "gemini-2.5-pro", - "max_tokens": 1000000, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat" ], @@ -206,7 +222,8 @@ }, { "name": "gemini-2.5-flash", - "max_tokens": 1000000, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat" ], diff --git a/conf/models/avian.json b/conf/models/avian.json index d12fcc7998..fc6b0352a0 100644 --- a/conf/models/avian.json +++ b/conf/models/avian.json @@ -11,7 +11,8 @@ "models": [ { "name": "deepseek/deepseek-v4-pro", - "max_tokens": 164000, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -21,7 +22,8 @@ }, { "name": "deepseek/deepseek-v4-flash", - "max_tokens": 164000, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -31,7 +33,8 @@ }, { "name": "deepseek/deepseek-v3.2", - "max_tokens": 164000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -41,7 +44,8 @@ }, { "name": "moonshotai/kimi-k2.5", - "max_tokens": 131000, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -51,7 +55,8 @@ }, { "name": "z-ai/glm-5", - "max_tokens": 131000, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -61,7 +66,8 @@ }, { "name": "minimax/minimax-m2.5", - "max_tokens": 1000000, + "content_length": 204800, + "max_output": 196608, "model_types": [ "chat" ], diff --git a/conf/models/baichuan.json b/conf/models/baichuan.json index 80c024297c..cfe927d32f 100644 --- a/conf/models/baichuan.json +++ b/conf/models/baichuan.json @@ -11,7 +11,8 @@ "models": [ { "name": "Baichuan4", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -21,7 +22,8 @@ }, { "name": "Baichuan4-Air", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -31,7 +33,8 @@ }, { "name": "Baichuan4-Turbo", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -41,7 +44,8 @@ }, { "name": "Baichuan-M3", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -51,7 +55,8 @@ }, { "name": "Baichuan-M3-plus", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -61,7 +66,8 @@ }, { "name": "Baichuan-M2-plus", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -71,7 +77,8 @@ }, { "name": "Baichuan-M2", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -81,7 +88,8 @@ }, { "name": "Baichuan3-Turbo", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -91,7 +99,8 @@ }, { "name": "Baichuan3-Turbo-128k", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -101,7 +110,8 @@ }, { "name": "Baichuan2-Turbo", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/baidu.json b/conf/models/baidu.json index b1e44cefa5..726ffddaa1 100644 --- a/conf/models/baidu.json +++ b/conf/models/baidu.json @@ -14,7 +14,8 @@ "models": [ { "name": "deepseek-v3.2", - "max_tokens": 98304, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -38,7 +40,8 @@ }, { "name": "deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -52,7 +55,8 @@ }, { "name": "qwen3-32b", - "max_tokens": 30720, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -62,7 +66,8 @@ }, { "name": "qwen3-4b", - "max_tokens": 30720, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -72,7 +77,8 @@ }, { "name": "ernie-5.0", - "max_tokens": 121856, + "content_length": 121856, + "max_output": 8192, "model_types": [ "vision" ] diff --git a/conf/models/bedrock.json b/conf/models/bedrock.json index ab885b493e..69a94e7eac 100644 --- a/conf/models/bedrock.json +++ b/conf/models/bedrock.json @@ -9,105 +9,120 @@ "models": [ { "name": "anthropic.claude-3-5-sonnet-20241022-v2:0", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "anthropic.claude-3-5-haiku-20241022-v1:0", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "anthropic.claude-3-opus-20240229-v1:0", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "anthropic.claude-3-sonnet-20240229-v1:0", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "anthropic.claude-3-haiku-20240307-v1:0", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "meta.llama3-1-405b-instruct-v1:0", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta.llama3-1-70b-instruct-v1:0", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta.llama3-1-8b-instruct-v1:0", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "mistral.mistral-large-2407-v1:0", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "mistral.mixtral-8x7b-instruct-v0:1", - "max_tokens": 32000, + "content_length": 32000, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "amazon.nova-pro-v1:0", - "max_tokens": 300000, + "content_length": 300000, + "max_output": 5000, "model_types": [ "chat" ] }, { "name": "amazon.nova-lite-v1:0", - "max_tokens": 300000, + "content_length": 300000, + "max_output": 5000, "model_types": [ "chat" ] }, { "name": "amazon.nova-micro-v1:0", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 5000, "model_types": [ "chat" ] }, { "name": "cohere.command-r-plus-v1:0", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "cohere.command-r-v1:0", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 4096, "model_types": [ "chat" ] diff --git a/conf/models/cohere.json b/conf/models/cohere.json index a985534485..244c9a6b2b 100644 --- a/conf/models/cohere.json +++ b/conf/models/cohere.json @@ -15,56 +15,64 @@ "models": [ { "name": "command-a-plus-05-2026", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 65536, "model_types": [ "chat" ] }, { "name": "command-a-03-2025", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "command-r7b-12-2024", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "command-a-translate-08-2025", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "command-a-reasoning-08-2025", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ] }, { "name": "command-a-vision-07-2025", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "command-r-plus-08-2024", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 4096, "model_types": [ "chat" ] }, { "name": "command-r-08-2024", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 4096, "model_types": [ "chat" ] diff --git a/conf/models/cometapi.json b/conf/models/cometapi.json index 1e5d359ab7..62957a4d71 100644 --- a/conf/models/cometapi.json +++ b/conf/models/cometapi.json @@ -15,7 +15,8 @@ "models": [ { "name": "gpt-5.5", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -30,7 +31,8 @@ }, { "name": "gpt-5.4-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -45,7 +47,8 @@ }, { "name": "gpt-5", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -60,7 +63,8 @@ }, { "name": "gpt-4o", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -71,7 +75,8 @@ }, { "name": "claude-sonnet-4-6", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -82,7 +87,8 @@ }, { "name": "gemini-3-pro-preview", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat", "vision" @@ -93,7 +99,8 @@ }, { "name": "deepseek-v3.2", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -103,7 +110,8 @@ }, { "name": "qwen3-235b-a22b", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], diff --git a/conf/models/deepinfra.json b/conf/models/deepinfra.json index d892088efb..4269ba3e0a 100644 --- a/conf/models/deepinfra.json +++ b/conf/models/deepinfra.json @@ -16,7 +16,8 @@ "models": [ { "name": "deepseek-ai/DeepSeek-V3.2", - "max_tokens": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/deepseek.json b/conf/models/deepseek.json index f283973867..07a8f14a41 100644 --- a/conf/models/deepseek.json +++ b/conf/models/deepseek.json @@ -13,7 +13,8 @@ "models": [ { "name": "deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -27,7 +28,8 @@ }, { "name": "deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], diff --git a/conf/models/futurmix.json b/conf/models/futurmix.json index 8f085b56a3..a42fa858be 100644 --- a/conf/models/futurmix.json +++ b/conf/models/futurmix.json @@ -10,7 +10,8 @@ "models": [ { "name": "gpt-5.5", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -21,7 +22,8 @@ }, { "name": "gpt-5.4", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -32,7 +34,8 @@ }, { "name": "gpt-5.4-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -43,7 +46,8 @@ }, { "name": "gpt-5.4-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -54,7 +58,8 @@ }, { "name": "claude-opus-4-7", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -65,7 +70,8 @@ }, { "name": "claude-opus-4-6", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -76,7 +82,8 @@ }, { "name": "claude-sonnet-4-6", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -87,7 +94,8 @@ }, { "name": "claude-haiku-4-5-20251001", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 64000, "model_types": [ "chat", "vision" @@ -98,7 +106,8 @@ }, { "name": "gemini-3.1-pro-preview", - "max_tokens": 2000000, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat", "vision" @@ -109,7 +118,8 @@ }, { "name": "gemini-2.5-pro", - "max_tokens": 2000000, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat", "vision" @@ -120,7 +130,8 @@ }, { "name": "gemini-2.5-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat", "vision" @@ -131,7 +142,8 @@ }, { "name": "gemini-2.5-flash-lite", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat", "vision" diff --git a/conf/models/gitee.json b/conf/models/gitee.json index 98ae57d063..7ae3ea2dda 100644 --- a/conf/models/gitee.json +++ b/conf/models/gitee.json @@ -20,6 +20,7 @@ "models": [ { "name": "qwen3-8b", + "content_length": 131072, "max_output": 32768, "model_types": [ "chat" @@ -30,6 +31,7 @@ }, { "name": "qwen3-0.6b", + "content_length": 32768, "max_output": 32768, "model_types": [ "chat" @@ -40,7 +42,8 @@ }, { "name": "glm-4.7-flash", - "max_output": 204800, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], diff --git a/conf/models/google.json b/conf/models/google.json index f8568e0606..86ab91d47d 100644 --- a/conf/models/google.json +++ b/conf/models/google.json @@ -11,7 +11,8 @@ "models": [ { "name": "gemini-2.5-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat" ], diff --git a/conf/models/greenpt.json b/conf/models/greenpt.json index 36a61bbd93..c9b1a48da9 100644 --- a/conf/models/greenpt.json +++ b/conf/models/greenpt.json @@ -14,7 +14,8 @@ "models": [ { "name": "glm-5.2", - "max_tokens": 1000000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "kimi-k2.7-code", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], diff --git a/conf/models/groq.json b/conf/models/groq.json index 6f97725348..8fbd9ca613 100644 --- a/conf/models/groq.json +++ b/conf/models/groq.json @@ -13,7 +13,8 @@ "models": [ { "name": "llama-3.1-8b-instant", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -23,7 +24,8 @@ }, { "name": "llama-3.3-70b-versatile", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -33,7 +35,8 @@ }, { "name": "openai/gpt-oss-120b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -43,7 +46,8 @@ }, { "name": "openai/gpt-oss-20b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -53,7 +57,8 @@ }, { "name": "groq/compound", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -63,7 +68,8 @@ }, { "name": "groq/compound-mini", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -73,27 +79,8 @@ }, { "name": "openai/gpt-oss-20b", - "max_tokens": 131072, - "model_types": [ - "chat" - ], - "tools": { - "support": true - } - }, - { - "name": "meta-llama/llama-4-scout-17b-16e-instruct", - "max_tokens": 131072, - "model_types": [ - "chat" - ], - "tools": { - "support": true - } - }, - { - "name": "qwen/qwen3-32b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], diff --git a/conf/models/huaweicloud.json b/conf/models/huaweicloud.json index b6502f14eb..2a5f5d802a 100755 --- a/conf/models/huaweicloud.json +++ b/conf/models/huaweicloud.json @@ -16,7 +16,8 @@ "models": [ { "name": "deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -30,7 +31,8 @@ }, { "name": "deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -44,7 +46,8 @@ }, { "name": "deepseek-v3.2", - "max_tokens": 163840, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -58,7 +61,8 @@ }, { "name": "deepseek-v3.1-terminus", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -72,7 +76,8 @@ }, { "name": "DeepSeek-V3", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -82,7 +87,8 @@ }, { "name": "deepseek-r1-250528", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 65536, "model_types": [ "chat" ], @@ -96,7 +102,8 @@ }, { "name": "qwen3-235b-a22b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -110,7 +117,8 @@ }, { "name": "qwen3-32b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -124,7 +132,8 @@ }, { "name": "qwen3-30b-a3b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -138,7 +147,8 @@ }, { "name": "kimi-k2.6", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -152,7 +162,8 @@ }, { "name": "longcat-flash-chat", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -162,7 +173,8 @@ }, { "name": "glm-5", - "max_tokens": 202752, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -176,7 +188,8 @@ }, { "name": "glm-5.1", - "max_tokens": 202752, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -190,7 +203,8 @@ }, { "name": "qwen2.5-vl-72b", - "max_tokens": 49152, + "content_length": 32768, + "max_output": 4096, "model_types": [ "chat", "vision" diff --git a/conf/models/huggingface.json b/conf/models/huggingface.json index fd7d0b774b..79f3419821 100644 --- a/conf/models/huggingface.json +++ b/conf/models/huggingface.json @@ -13,7 +13,8 @@ "models": [ { "name": "openai/gpt-oss-120b:fastest", - "max_tokens": 32768, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ] diff --git a/conf/models/hunyuan.json b/conf/models/hunyuan.json index 8004e9a748..a1ea4bcef1 100644 --- a/conf/models/hunyuan.json +++ b/conf/models/hunyuan.json @@ -15,7 +15,8 @@ "models": [ { "name": "hy3", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -25,7 +26,8 @@ }, { "name": "hy3-preview", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -35,7 +37,8 @@ }, { "name": "kimi-k3", - "max_tokens": 131072, + "content_length": 1000000, + "max_output": 131072, "model_types": [ "chat" ], @@ -45,7 +48,8 @@ }, { "name": "kimi-k2.7-code-highspeed", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -55,7 +59,8 @@ }, { "name": "kimi-k2.7-code", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -65,7 +70,8 @@ }, { "name": "glm-5.2", - "max_tokens": 131072, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat" ], @@ -75,7 +81,8 @@ }, { "name": "minimax-m3", - "max_tokens": 131072, + "content_length": 1024000, + "max_output": 131072, "model_types": [ "chat" ], @@ -85,7 +92,8 @@ }, { "name": "deepseek-v4-flash-202605", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -95,7 +103,8 @@ }, { "name": "deepseek-v4-pro-202606", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -105,7 +114,8 @@ }, { "name": "deepseek-v4-pro", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -115,7 +125,8 @@ }, { "name": "deepseek-v4-flash", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -125,7 +136,8 @@ }, { "name": "hy-mt2-pro", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ], @@ -135,7 +147,8 @@ }, { "name": "hy-mt2-plus", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ], @@ -145,7 +158,8 @@ }, { "name": "hy-mt2-lite", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ], @@ -155,7 +169,8 @@ }, { "name": "hy-role", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -165,7 +180,8 @@ }, { "name": "hunyuan-role-latest", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -175,7 +191,8 @@ }, { "name": "qwen3.5-flash", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat" ], @@ -185,7 +202,8 @@ }, { "name": "qwen3.5-plus", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 65536, "model_types": [ "chat" ], @@ -195,7 +213,8 @@ }, { "name": "glm-5.1", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -205,7 +224,8 @@ }, { "name": "glm-5", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -215,7 +235,8 @@ }, { "name": "glm-5-turbo", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -225,7 +246,8 @@ }, { "name": "kimi-k2.6", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -235,7 +257,8 @@ }, { "name": "kimi-k2.5", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -245,7 +268,8 @@ }, { "name": "minimax-m2.7", - "max_tokens": 131072, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -255,7 +279,8 @@ }, { "name": "minimax-m2.5", - "max_tokens": 131072, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -265,7 +290,8 @@ }, { "name": "deepseek-v3.2", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -275,7 +301,8 @@ }, { "name": "glm-5v-turbo", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -286,7 +313,8 @@ }, { "name": "hy-vision-2.0-instruct", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -297,7 +325,8 @@ }, { "name": "youtu-vita", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -308,7 +337,8 @@ }, { "name": "hunyuan-t1-vision-20250916", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -319,7 +349,8 @@ }, { "name": "hunyuan-turbos-vision-video-20250728", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" diff --git a/conf/models/jiekouai.json b/conf/models/jiekouai.json index 1f831a56c2..9deac93df9 100644 --- a/conf/models/jiekouai.json +++ b/conf/models/jiekouai.json @@ -13,7 +13,8 @@ "models": [ { "name": "deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -27,7 +28,8 @@ }, { "name": "deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -41,7 +43,8 @@ }, { "name": "zai-org/glm-4.5", - "max_tokens": 131072, + "content_length": 128000, + "max_output": 96000, "model_types": [ "chat" ], @@ -55,7 +58,8 @@ }, { "name": "zai-org/glm-4.5v", - "max_tokens": 131072, + "content_length": 65536, + "max_output": 16384, "model_types": [ "chat" ], @@ -69,7 +73,8 @@ }, { "name": "zai-org/glm-4.7", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -83,7 +88,8 @@ }, { "name": "zai-org/glm-4.7-flash", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -97,7 +103,8 @@ }, { "name": "zai-org/glm-5", - "max_tokens": 131072, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], diff --git a/conf/models/jina.json b/conf/models/jina.json index 87c64a81e0..ca934930d7 100644 --- a/conf/models/jina.json +++ b/conf/models/jina.json @@ -14,7 +14,8 @@ "models": [ { "name": "jina-vlm", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/longcat.json b/conf/models/longcat.json index 00896e7b85..b462481c24 100644 --- a/conf/models/longcat.json +++ b/conf/models/longcat.json @@ -11,7 +11,8 @@ "models": [ { "name": "LongCat-2.0", - "max_tokens": 131072, + "content_length": 1048576, + "max_output": 131072, "model_types": [ "chat" ], diff --git a/conf/models/minimax.json b/conf/models/minimax.json index 0c142a96a8..aed7cb84d1 100644 --- a/conf/models/minimax.json +++ b/conf/models/minimax.json @@ -15,7 +15,8 @@ "models": [ { "name": "MiniMax-M3", - "max_tokens": 1024000, + "content_length": 1024000, + "max_output": 131072, "model_types": [ "chat" ], @@ -26,7 +27,8 @@ }, { "name": "minimax-m2.7", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -37,7 +39,8 @@ }, { "name": "minimax-m2.7-highspeed", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 131072, "model_types": [ "chat" ], @@ -48,7 +51,8 @@ }, { "name": "minimax-m2.5", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -59,7 +63,8 @@ }, { "name": "minimax-m2.5-highspeed", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 131072, "model_types": [ "chat" ], @@ -70,7 +75,8 @@ }, { "name": "minimax-m2.1", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -81,7 +87,8 @@ }, { "name": "minimax-m2.1-highspeed", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 131072, "model_types": [ "chat" ], @@ -92,7 +99,8 @@ }, { "name": "minimax-m2", - "max_tokens": 204800, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], @@ -103,7 +111,8 @@ }, { "name": "minimax-m2-her", - "max_tokens": 65536, + "content_length": 65536, + "max_output": 16384, "model_types": [ "chat" ], diff --git a/conf/models/mistral.json b/conf/models/mistral.json index fd016e49ca..f140e337e7 100644 --- a/conf/models/mistral.json +++ b/conf/models/mistral.json @@ -15,7 +15,8 @@ "models": [ { "name": "mistral-large-latest", - "max_tokens": 128000, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -37,7 +38,8 @@ }, { "name": "mistral-medium-latest", - "max_tokens": 128000, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -47,7 +49,8 @@ }, { "name": "mistral-small-latest", - "max_tokens": 128000, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -57,7 +60,8 @@ }, { "name": "ministral-8b-latest", - "max_tokens": 128000, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -67,7 +71,8 @@ }, { "name": "ministral-3b-latest", - "max_tokens": 128000, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -77,7 +82,8 @@ }, { "name": "pixtral-large-latest", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat", "vision" @@ -88,7 +94,8 @@ }, { "name": "codestral-latest", - "max_tokens": 256000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -98,7 +105,8 @@ }, { "name": "open-mistral-nemo", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -108,7 +116,8 @@ }, { "name": "open-mistral-7b", - "max_tokens": 32000, + "content_length": 32768, + "max_output": 32768, "model_types": [ "chat" ], @@ -118,7 +127,8 @@ }, { "name": "open-mixtral-8x7b", - "max_tokens": 32000, + "content_length": 32768, + "max_output": 32768, "model_types": [ "chat" ], @@ -128,7 +138,8 @@ }, { "name": "open-mixtral-8x22b", - "max_tokens": 64000, + "content_length": 65536, + "max_output": 65536, "model_types": [ "chat" ], @@ -138,7 +149,8 @@ }, { "name": "magistral-medium-latest", - "max_tokens": 40000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -148,7 +160,8 @@ }, { "name": "magistral-small-latest", - "max_tokens": 40000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], diff --git a/conf/models/moonshot.json b/conf/models/moonshot.json index b1b03ee15c..8fda6e3db8 100644 --- a/conf/models/moonshot.json +++ b/conf/models/moonshot.json @@ -13,7 +13,7 @@ "models": [ { "name": "kimi-k3", - "content_length": 1048576, + "content_length": 1000000, "max_output": 131072, "model_types": [ "chat", @@ -61,7 +61,8 @@ }, { "name": "kimi-k2.6", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat", "vision" @@ -76,7 +77,8 @@ }, { "name": "kimi-k2.5", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat", "vision" @@ -91,7 +93,8 @@ }, { "name": "moonshot-v1-8k", - "max_tokens": 8000, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -102,7 +105,8 @@ }, { "name": "moonshot-v1-32k", - "max_tokens": 32000, + "content_length": 32768, + "max_output": 32768, "model_types": [ "chat" ], @@ -112,7 +116,8 @@ }, { "name": "moonshot-v1-128k", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -122,7 +127,8 @@ }, { "name": "moonshot-v1-8k-vision-preview", - "max_tokens": 8000, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -133,7 +139,8 @@ }, { "name": "moonshot-v1-32k-vision-preview", - "max_tokens": 32000, + "content_length": 32768, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -144,7 +151,8 @@ }, { "name": "moonshot-v1-128k-vision-preview", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat", "vision" diff --git a/conf/models/n1n.json b/conf/models/n1n.json index 4ba945afd3..ce5f011e7d 100644 --- a/conf/models/n1n.json +++ b/conf/models/n1n.json @@ -13,7 +13,8 @@ "models": [ { "name": "gpt-4o-mini", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -24,7 +25,8 @@ }, { "name": "gpt-4o", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -35,7 +37,8 @@ }, { "name": "gpt-5.2", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -46,7 +49,8 @@ }, { "name": "claude-sonnet-4-6", - "max_tokens": 200000, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -57,7 +61,8 @@ }, { "name": "deepseek-v3-0324", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -67,7 +72,8 @@ }, { "name": "deepseek-v3-1-250821", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -77,7 +83,8 @@ }, { "name": "deepseek-v3-1-think-250821", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -87,7 +94,8 @@ }, { "name": "kimi-k2-250905", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -97,7 +105,8 @@ }, { "name": "qwen3-coder-plus", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat" ], diff --git a/conf/models/novita.json b/conf/models/novita.json index 80f9093ae2..bddaaae858 100644 --- a/conf/models/novita.json +++ b/conf/models/novita.json @@ -14,7 +14,8 @@ "models": [ { "name": "deepseek/deepseek-v4-pro", - "max_tokens": 65536, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "meta-llama/llama-3.3-70b-instruct", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 120000, "model_types": [ "chat" ], @@ -34,7 +36,8 @@ }, { "name": "qwen/qwen3-30b-a3b-fp8", - "max_tokens": 32768, + "content_length": 256000, + "max_output": 128000, "model_types": [ "chat" ], @@ -44,7 +47,8 @@ }, { "name": "qwen/qwen3-235b-a22b-fp8", - "max_tokens": 32768, + "content_length": 40960, + "max_output": 20000, "model_types": [ "chat" ], @@ -54,7 +58,8 @@ }, { "name": "moonshotai/kimi-k2-instruct", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -64,7 +69,8 @@ }, { "name": "google/gemma-3-27b-it", - "max_tokens": 131072, + "content_length": 98304, + "max_output": 16384, "model_types": [ "chat" ], @@ -74,7 +80,8 @@ }, { "name": "mistralai/mistral-nemo", - "max_tokens": 131072, + "content_length": 60288, + "max_output": 16000, "model_types": [ "chat" ], diff --git a/conf/models/nvidia.json b/conf/models/nvidia.json index 00b1acbe99..9d4ee14d64 100644 --- a/conf/models/nvidia.json +++ b/conf/models/nvidia.json @@ -13,7 +13,8 @@ "models": [ { "name": "deepseek-ai/deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -23,7 +24,8 @@ }, { "name": "deepseek-ai/deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -33,14 +35,16 @@ }, { "name": "google/diffusiongemma-26b-a4b-it", - "max_tokens": 8192, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "google/gemma-4-31b-it", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -50,21 +54,24 @@ }, { "name": "meta/llama-3.1-70b-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta/llama-3.1-8b-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta/llama-3.2-11b-vision-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -72,21 +79,24 @@ }, { "name": "meta/llama-3.2-1b-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta/llama-3.2-3b-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta/llama-3.2-90b-vision-instruct", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -97,28 +107,32 @@ }, { "name": "meta/llama-3.3-70b-instruct", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "meta/llama-guard-4-12b", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "minimaxai/minimax-m3", - "max_tokens": 8192, + "content_length": 1048576, + "max_output": 16384, "model_types": [ "chat" ] }, { "name": "mistralai/mistral-medium-3.5-128b", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat", "vision" @@ -129,7 +143,8 @@ }, { "name": "mistralai/mistral-nemotron", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -139,7 +154,8 @@ }, { "name": "moonshotai/kimi-k2.6", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat", "vision" @@ -150,14 +166,16 @@ }, { "name": "nvidia/ising-calibration-1.5-31b", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "nvidia/llama-3.1-nemotron-nano-8b-v1", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -167,7 +185,8 @@ }, { "name": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -175,7 +194,8 @@ }, { "name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -185,7 +205,8 @@ }, { "name": "nvidia/llama-3.3-nemotron-super-49b-v1", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -195,7 +216,8 @@ }, { "name": "nvidia/llama-3.3-nemotron-super-49b-v1.5", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -216,7 +238,8 @@ }, { "name": "nvidia/nemotron-3-nano-30b-a3b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -226,7 +249,8 @@ }, { "name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -241,7 +265,8 @@ }, { "name": "nvidia/nemotron-3-super-120b-a12b", - "max_tokens": 131072, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -251,21 +276,24 @@ }, { "name": "nvidia/nemotron-3-ultra-550b-a55b", - "max_tokens": 8192, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "nvidia/nemotron-3.5-content-safety", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "nvidia/nemotron-mini-4b-instruct", - "max_tokens": 4096, + "content_length": 8192, + "max_output": 4096, "model_types": [ "chat" ], @@ -275,7 +303,8 @@ }, { "name": "nvidia/nemotron-nano-12b-v2-vl", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -297,7 +326,8 @@ }, { "name": "nvidia/nvidia-nemotron-nano-9b-v2", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -307,14 +337,16 @@ }, { "name": "nvidia/riva-translate-4b-instruct-v2", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "openai/gpt-oss-120b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -324,35 +356,40 @@ }, { "name": "openai/gpt-oss-20b", - "max_tokens": 8192, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ] }, { "name": "poolside/laguna-xs-2.1", - "max_tokens": 8192, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "stepfun-ai/step-3.7-flash", - "max_tokens": 8192, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "thinkingmachines/inkling", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "z-ai/glm-5.2", - "max_tokens": 8192, + "content_length": 1000000, + "max_output": 128000, "model_types": [ "chat" ] diff --git a/conf/models/openai.json b/conf/models/openai.json index 1ba96ed74b..1f3e2ffd73 100644 --- a/conf/models/openai.json +++ b/conf/models/openai.json @@ -15,7 +15,8 @@ "models": [ { "name": "gpt-5.5", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -26,7 +27,8 @@ }, { "name": "gpt-5.4", - "max_tokens": 400000, + "content_length": 1050000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -37,7 +39,8 @@ }, { "name": "gpt-5.4-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -48,7 +51,8 @@ }, { "name": "gpt-5.4-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -59,7 +63,8 @@ }, { "name": "gpt-5.2-pro", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -70,7 +75,8 @@ }, { "name": "gpt-5.2", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -81,7 +87,8 @@ }, { "name": "gpt-5.1", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -92,7 +99,8 @@ }, { "name": "gpt-5.1-chat-latest", - "max_tokens": 400000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -103,7 +111,8 @@ }, { "name": "gpt-5", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -114,7 +123,8 @@ }, { "name": "gpt-5-mini", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -125,7 +135,8 @@ }, { "name": "gpt-5-nano", - "max_tokens": 400000, + "content_length": 400000, + "max_output": 128000, "model_types": [ "chat", "vision" @@ -136,7 +147,8 @@ }, { "name": "gpt-5-chat-latest", - "max_tokens": 400000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -147,7 +159,8 @@ }, { "name": "gpt-4.1", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -158,7 +171,8 @@ }, { "name": "gpt-4.1-mini", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -169,7 +183,8 @@ }, { "name": "gpt-4.1-nano", - "max_tokens": 1047576, + "content_length": 1047576, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -180,7 +195,8 @@ }, { "name": "gpt-4.5-preview", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], @@ -190,7 +206,8 @@ }, { "name": "gpt-4o-mini", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -201,7 +218,8 @@ }, { "name": "gpt-4o", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -212,7 +230,8 @@ }, { "name": "gpt-3.5-turbo", - "max_tokens": 4096, + "content_length": 16385, + "max_output": 4096, "model_types": [ "chat" ], @@ -222,7 +241,8 @@ }, { "name": "gpt-3.5-turbo-16k-0613", - "max_tokens": 16385, + "content_length": 16385, + "max_output": 4096, "model_types": [ "chat" ], @@ -260,7 +280,8 @@ }, { "name": "gpt-4", - "max_tokens": 8191, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ], @@ -270,7 +291,8 @@ }, { "name": "gpt-4-turbo", - "max_tokens": 8191, + "content_length": 128000, + "max_output": 4096, "model_types": [ "chat" ], @@ -280,7 +302,8 @@ }, { "name": "gpt-4-32k", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 4096, "model_types": [ "chat" ], diff --git a/conf/models/openrouter.json b/conf/models/openrouter.json index f2e3dc5d77..c357619fc9 100644 --- a/conf/models/openrouter.json +++ b/conf/models/openrouter.json @@ -17,7 +17,8 @@ "models": [ { "name": "google/gemma-4-31b-it", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -31,7 +32,8 @@ }, { "name": "minimax/minimax-m2.5", - "max_tokens": 196608, + "content_length": 204800, + "max_output": 196608, "model_types": [ "chat" ], @@ -45,7 +47,8 @@ }, { "name": "tencent/hy3-preview", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], diff --git a/conf/models/orcarouter.json b/conf/models/orcarouter.json index 1ee07900e1..609b3a5363 100644 --- a/conf/models/orcarouter.json +++ b/conf/models/orcarouter.json @@ -12,7 +12,8 @@ "models": [ { "name": "orcarouter/auto", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/perplexity.json b/conf/models/perplexity.json index 61c37d757f..793d3e2ebc 100644 --- a/conf/models/perplexity.json +++ b/conf/models/perplexity.json @@ -12,21 +12,24 @@ "models": [ { "name": "sonar", - "max_tokens": 127072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ] }, { "name": "sonar-pro", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat" ] }, { "name": "sonar-reasoning-pro", - "max_tokens": 127072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -37,7 +40,8 @@ }, { "name": "sonar-deep-research", - "max_tokens": 127072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ] diff --git a/conf/models/ppio.json b/conf/models/ppio.json index c4b2bf0ce1..5886b2acc7 100644 --- a/conf/models/ppio.json +++ b/conf/models/ppio.json @@ -14,7 +14,8 @@ "models": [ { "name": "deepseek/deepseek-v4-flash", - "max_output": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "deepseek/deepseek-v4-pro", - "max_output": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -34,7 +36,8 @@ }, { "name": "deepseek/deepseek-r1/community", - "max_output": 64000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -44,7 +47,8 @@ }, { "name": "deepseek/deepseek-v3/community", - "max_output": 64000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -54,7 +58,8 @@ }, { "name": "deepseek/deepseek-r1", - "max_output": 64000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -64,7 +69,8 @@ }, { "name": "deepseek/deepseek-v3", - "max_output": 64000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -74,7 +80,8 @@ }, { "name": "deepseek/deepseek-r1-distill-llama-70b", - "max_output": 32000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -84,7 +91,8 @@ }, { "name": "deepseek/deepseek-r1-distill-qwen-32b", - "max_output": 64000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -94,7 +102,8 @@ }, { "name": "deepseek/deepseek-r1-distill-qwen-14b", - "max_output": 64000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -104,7 +113,8 @@ }, { "name": "deepseek/deepseek-r1-distill-llama-8b", - "max_output": 32000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -114,7 +124,8 @@ }, { "name": "qwen/qwen-2.5-72b-instruct", - "max_output": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -124,7 +135,8 @@ }, { "name": "qwen/qwen-2-vl-72b-instruct", - "max_output": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -134,7 +146,8 @@ }, { "name": "meta-llama/llama-3.2-3b-instruct", - "max_output": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -144,7 +157,8 @@ }, { "name": "qwen/qwen2.5-32b-instruct", - "max_output": 32000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -154,7 +168,8 @@ }, { "name": "baichuan/baichuan2-13b-chat", - "max_output": 14336, + "content_length": 196608, + "max_output": 8192, "model_types": [ "chat" ], @@ -164,7 +179,8 @@ }, { "name": "meta-llama/llama-3.1-70b-instruct", - "max_output": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -174,7 +190,8 @@ }, { "name": "meta-llama/llama-3.1-8b-instruct", - "max_output": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -184,7 +201,8 @@ }, { "name": "01-ai/yi-1.5-34b-chat", - "max_output": 16384, + "content_length": 16384, + "max_output": 8192, "model_types": [ "chat" ], @@ -194,7 +212,8 @@ }, { "name": "01-ai/yi-1.5-9b-chat", - "max_output": 16384, + "content_length": 16384, + "max_output": 8192, "model_types": [ "chat" ], @@ -204,7 +223,8 @@ }, { "name": "thudm/glm-4-9b-chat", - "max_output": 32768, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], @@ -214,7 +234,8 @@ }, { "name": "qwen/qwen-2-7b-instruct", - "max_output": 32768, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/qiniu.json b/conf/models/qiniu.json index 0a72686fd6..5c2531c4f2 100644 --- a/conf/models/qiniu.json +++ b/conf/models/qiniu.json @@ -11,7 +11,8 @@ "models": [ { "name": "deepseek/deepseek-v4-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -25,7 +26,8 @@ }, { "name": "deepseek/deepseek-v4-pro", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -39,6 +41,8 @@ }, { "name": "moonshotai/kimi-k2.6", + "content_length": 262144, + "max_output": 131072, "model_types": [ "vision" ], @@ -49,12 +53,16 @@ }, { "name": "moonshotai/kimi-k2.5", + "content_length": 262144, + "max_output": 131072, "model_types": [ "vision" ] }, { "name": "z-ai/glm-5.1", + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -68,6 +76,8 @@ }, { "name": "z-ai/glm-5", + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -81,6 +91,8 @@ }, { "name": "minimax/minimax-m2.7", + "content_length": 204800, + "max_output": 16384, "model_types": [ "chat" ], @@ -94,6 +106,8 @@ }, { "name": "minimax/minimax-m2.5", + "content_length": 204800, + "max_output": 196608, "model_types": [ "chat" ], @@ -107,6 +121,8 @@ }, { "name": "minimax/minimax-m2.5-highspeed", + "content_length": 196608, + "max_output": 16384, "model_types": [ "chat" ], @@ -120,6 +136,8 @@ }, { "name": "minimax/minimax-m2.1", + "content_length": 204800, + "max_output": 16384, "model_types": [ "chat" ], @@ -129,7 +147,8 @@ }, { "name": "kimi-k2-thinking", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -143,6 +162,8 @@ }, { "name": "meituan/longcat-flash-lite", + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -152,6 +173,8 @@ }, { "name": "qwen3-max", + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -161,7 +184,8 @@ }, { "name": "z-ai/glm-4.6", - "max_tokens": 204800, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -175,6 +199,8 @@ }, { "name": "z-ai/glm-4.7", + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -184,6 +210,8 @@ }, { "name": "deepseek/deepseek-v3.2-251201", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -197,6 +225,8 @@ }, { "name": "deepseek/deepseek-v3.2-exp-thinking", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -210,6 +240,8 @@ }, { "name": "deepseek/deepseek-v3.1-terminus", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -219,6 +251,8 @@ }, { "name": "deepseek/deepseek-v3.1-terminus-thinking", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -232,6 +266,8 @@ }, { "name": "deepseek-v3.1", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -241,6 +277,8 @@ }, { "name": "deepseek-v3-0324", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -250,6 +288,8 @@ }, { "name": "deepseek-r1-0528", + "content_length": 131072, + "max_output": 65536, "model_types": [ "chat" ], @@ -263,6 +303,8 @@ }, { "name": "deepseek-r1", + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -276,7 +318,8 @@ }, { "name": "doubao-seed-1.6-flash", - "max_tokens": 262144, + "content_length": 256000, + "max_output": 16384, "model_types": [ "vision" ], @@ -287,14 +330,16 @@ }, { "name": "doubao-1.5-pro-32k", - "max_tokens": 131072, + "content_length": 32768, + "max_output": 4096, "model_types": [ "vision" ] }, { "name": "doubao-seed-1.6", - "max_tokens": 262144, + "content_length": 256000, + "max_output": 16384, "model_types": [ "vision" ], @@ -305,6 +350,8 @@ }, { "name": "doubao-seed-2.0-pro", + "content_length": 256000, + "max_output": 16384, "model_types": [ "vision" ], @@ -315,6 +362,8 @@ }, { "name": "doubao-seed-2.0-lite", + "content_length": 256000, + "max_output": 16384, "model_types": [ "chat" ], @@ -328,7 +377,8 @@ }, { "name": "doubao-seed-2.0-mini", - "max_tokens": 262144, + "content_length": 256000, + "max_output": 16384, "model_types": [ "vision" ], @@ -339,6 +389,8 @@ }, { "name": "doubao-seed-2.0-code", + "content_length": 256000, + "max_output": 16384, "model_types": [ "chat" ], @@ -352,6 +404,8 @@ }, { "name": "qwen3-next-80b-a3b-thinking", + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -365,6 +419,8 @@ }, { "name": "qwen3-235b-a22b-thinking-2507", + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -378,6 +434,8 @@ }, { "name": "qwen3-max-2026-01-23", + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -391,6 +449,8 @@ }, { "name": "qwen3-next-80b-a3b-instruct", + "content_length": 262144, + "max_output": 16384, "model_types": [ "chat" ], @@ -400,6 +460,8 @@ }, { "name": "qwen3-max-preview", + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -409,12 +471,16 @@ }, { "name": "qwen-2.5-vl-72b-instruct", + "content_length": 32768, + "max_output": 4096, "model_types": [ "vision" ] }, { "name": "qwen3-coder-480b-a35b-instruct", + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat" ], @@ -424,6 +490,8 @@ }, { "name": "qwen-turbo", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -437,6 +505,8 @@ }, { "name": "qwen3-235b-a22b-instruct-2507", + "content_length": 262144, + "max_output": 16384, "model_types": [ "chat" ], @@ -446,6 +516,8 @@ }, { "name": "qwen3-32b", + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -459,6 +531,8 @@ }, { "name": "qwen3-30b-a3b", + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -472,6 +546,8 @@ }, { "name": "qwen3-235b-a22b", + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -481,18 +557,24 @@ }, { "name": "qwen-2.5-vl-7b-instruct", + "content_length": 32768, + "max_output": 4096, "model_types": [ "vision" ] }, { "name": "qwen-vl-max-2025-01-25", + "content_length": 32768, + "max_output": 8192, "model_types": [ "vision" ] }, { "name": "qwen2.5-max-2025-01-25", + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -502,7 +584,8 @@ }, { "name": "minimax-m1", - "max_tokens": 1048576, + "content_length": 1000000, + "max_output": 131072, "model_types": [ "chat" ], @@ -516,6 +599,8 @@ }, { "name": "glm-4.5", + "content_length": 128000, + "max_output": 96000, "model_types": [ "chat" ], @@ -529,12 +614,16 @@ }, { "name": "qwen3-vl-30b-a3b-instruct", + "content_length": 262144, + "max_output": 8192, "model_types": [ "vision" ] }, { "name": "deepseek-v3", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -544,6 +633,8 @@ }, { "name": "qwen3-30b-a3b-thinking-2507", + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -557,6 +648,8 @@ }, { "name": "glm-4.5-air", + "content_length": 128000, + "max_output": 96000, "model_types": [ "chat" ], @@ -570,6 +663,8 @@ }, { "name": "qwen3.5-397b-a17b", + "content_length": 262144, + "max_output": 32768, "model_types": [ "vision" ], @@ -580,12 +675,16 @@ }, { "name": "qwen/qwen3.5-plus", + "content_length": 1048576, + "max_output": 65536, "model_types": [ "vision" ] }, { "name": "qwen/qwen3.6-plus", + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -599,6 +698,8 @@ }, { "name": "deepseek/deepseek-v3.2-exp", + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -608,6 +709,8 @@ }, { "name": "qwen/qwen3.7-max", + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -621,7 +724,8 @@ }, { "name": "qwen/qwen3.6-27b", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 32768, "model_types": [ "vision" ], @@ -632,6 +736,8 @@ }, { "name": "tencent/hy3-preview", + "content_length": 262144, + "max_output": 262144, "model_types": [ "chat" ], @@ -645,6 +751,8 @@ }, { "name": "qwen3.5-35b-a3b", + "content_length": 262144, + "max_output": 32768, "model_types": [ "vision" ], @@ -655,6 +763,8 @@ }, { "name": "qwen3-vl-30b-a3b-thinking", + "content_length": 262144, + "max_output": 8192, "model_types": [ "vision" ], @@ -665,6 +775,8 @@ }, { "name": "qwen3-30b-a3b-instruct-2507", + "content_length": 262144, + "max_output": 16384, "model_types": [ "chat" ], diff --git a/conf/models/replicate.json b/conf/models/replicate.json index 23553526d5..ca60f57537 100644 --- a/conf/models/replicate.json +++ b/conf/models/replicate.json @@ -12,28 +12,32 @@ "models": [ { "name": "meta/llama-4-maverick-instruct", - "max_tokens": 8192, + "content_length": 1048576, + "max_output": 131072, "model_types": [ "chat" ] }, { "name": "meta/llama-4-scout-instruct", - "max_tokens": 8192, + "content_length": 10485760, + "max_output": 131072, "model_types": [ "chat" ] }, { "name": "meta/meta-llama-3-70b-instruct", - "max_tokens": 8192, + "content_length": 8000, + "max_output": 8000, "model_types": [ "chat" ] }, { "name": "meta/meta-llama-3-8b-instruct", - "max_tokens": 8192, + "content_length": 8000, + "max_output": 8000, "model_types": [ "chat" ] diff --git a/conf/models/siliconflow.json b/conf/models/siliconflow.json index 02dfd4a6ab..fb1c07d1c5 100644 --- a/conf/models/siliconflow.json +++ b/conf/models/siliconflow.json @@ -16,7 +16,8 @@ "models": [ { "name": "Pro/deepseek-ai/DeepSeek-V4-Pro", - "max_output": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -30,7 +31,8 @@ }, { "name": "Pro/deepseek-ai/DeepSeek-V4-Flash", - "max_output": 1048576, + "content_length": 1048576, + "max_output": 393216, "model_types": [ "chat" ], @@ -44,7 +46,8 @@ }, { "name": "Pro/moonshotai/Kimi-K2.6", - "max_output": 262144, + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat", "vision" @@ -59,7 +62,8 @@ }, { "name": "Pro/zai-org/GLM-5.1", - "max_output": 204800, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -73,6 +77,7 @@ }, { "name": "qwen/qwen3-8b", + "content_length": 131072, "max_output": 32768, "model_types": [ "chat" @@ -83,7 +88,8 @@ }, { "name": "qwen/qwen3.5-4b", - "max_output": 262144, + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -93,7 +99,8 @@ }, { "name": "tencent/hunyuan-mt-7b", - "max_output": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/stepfun.json b/conf/models/stepfun.json index 419bd0841f..0deb22ce6a 100644 --- a/conf/models/stepfun.json +++ b/conf/models/stepfun.json @@ -14,7 +14,8 @@ "models": [ { "name": "step-3.5-flash", - "max_tokens": 32768, + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "step-3.5-flash-paid", - "max_tokens": 32768, + "content_length": 262144, + "max_output": 32768, "model_types": [ "chat" ], @@ -34,7 +36,8 @@ }, { "name": "step-2-16k", - "max_tokens": 16384, + "content_length": 16384, + "max_output": 8192, "model_types": [ "chat" ], @@ -44,7 +47,8 @@ }, { "name": "step-1-256k", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -54,7 +58,8 @@ }, { "name": "step-1-128k", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -64,7 +69,8 @@ }, { "name": "step-1-32k", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat" ], @@ -74,7 +80,8 @@ }, { "name": "step-1-8k", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 4096, "model_types": [ "chat" ], @@ -84,7 +91,8 @@ }, { "name": "step-1-flash", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 4096, "model_types": [ "chat" ], @@ -94,7 +102,8 @@ }, { "name": "step-1v-32k", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -105,7 +114,8 @@ }, { "name": "step-1v-8k", - "max_tokens": 8192, + "content_length": 8192, + "max_output": 4096, "model_types": [ "chat", "vision" @@ -116,7 +126,8 @@ }, { "name": "step-1o-vision-32k", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "chat", "vision" diff --git a/conf/models/togetherai.json b/conf/models/togetherai.json index b43acf35fc..690ec34c1d 100644 --- a/conf/models/togetherai.json +++ b/conf/models/togetherai.json @@ -15,7 +15,8 @@ "models": [ { "name": "openai/gpt-oss-20b", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -25,7 +26,8 @@ }, { "name": "meta-llama/Llama-3.3-70B-Instruct-Turbo", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -35,7 +37,8 @@ }, { "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", - "max_tokens": 262144, + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat" ], diff --git a/conf/models/tokenhub.json b/conf/models/tokenhub.json index a9b6d3895d..c7849200d8 100644 --- a/conf/models/tokenhub.json +++ b/conf/models/tokenhub.json @@ -12,7 +12,8 @@ "models": [ { "name": "gpt-4o-mini", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -23,7 +24,8 @@ }, { "name": "gpt-4o", - "max_tokens": 128000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat", "vision" @@ -34,7 +36,8 @@ }, { "name": "gpt-4", - "max_tokens": 8191, + "content_length": 8192, + "max_output": 8192, "model_types": [ "chat" ], @@ -44,7 +47,8 @@ }, { "name": "gpt-4-turbo", - "max_tokens": 8191, + "content_length": 128000, + "max_output": 4096, "model_types": [ "chat" ], @@ -54,7 +58,8 @@ }, { "name": "claude-3-5-sonnet", - "max_tokens": 8192, + "content_length": 200000, + "max_output": 8192, "model_types": [ "chat", "vision" @@ -65,7 +70,8 @@ }, { "name": "gemini-1.5-pro", - "max_tokens": 1048576, + "content_length": 2097152, + "max_output": 8192, "model_types": [ "chat" ], @@ -79,7 +85,8 @@ }, { "name": "gemini-1.5-flash", - "max_tokens": 1048576, + "content_length": 1048576, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/tokenpony.json b/conf/models/tokenpony.json index 5c9e9e95c1..d95f5e1823 100644 --- a/conf/models/tokenpony.json +++ b/conf/models/tokenpony.json @@ -11,7 +11,8 @@ "models": [ { "name": "qwen3-8b", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -21,7 +22,8 @@ }, { "name": "deepseek-v3-0324", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -31,7 +33,8 @@ }, { "name": "qwen3-32b", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 32768, "model_types": [ "chat" ], @@ -41,7 +44,8 @@ }, { "name": "kimi-k2-instruct-0905", - "max_tokens": 256000, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -51,7 +55,8 @@ }, { "name": "deepseek-r1-0528", - "max_tokens": 164000, + "content_length": 131072, + "max_output": 65536, "model_types": [ "chat" ], @@ -61,7 +66,8 @@ }, { "name": "qwen3-coder-480b", - "max_tokens": 1024000, + "content_length": 262144, + "max_output": 65536, "model_types": [ "chat" ], @@ -71,7 +77,8 @@ }, { "name": "hunyuan-a13b-instruct", - "max_tokens": 256000, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -81,7 +88,8 @@ }, { "name": "qwen3-next-80b-a3b-instruct", - "max_tokens": 1024000, + "content_length": 262144, + "max_output": 16384, "model_types": [ "chat" ], @@ -91,7 +99,8 @@ }, { "name": "deepseek-v3.2-exp", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -101,7 +110,8 @@ }, { "name": "deepseek-v3.1-terminus", - "max_tokens": 128000, + "content_length": 131072, + "max_output": 8192, "model_types": [ "chat" ], @@ -111,7 +121,8 @@ }, { "name": "qwen3-vl-235b-a22b-instruct", - "max_tokens": 262000, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -121,7 +132,8 @@ }, { "name": "qwen3-vl-30b-a3b-instruct", - "max_tokens": 262000, + "content_length": 262144, + "max_output": 8192, "model_types": [ "chat" ], @@ -131,7 +143,8 @@ }, { "name": "deepseek-ocr", - "max_tokens": 8000, + "content_length": 8000, + "max_output": 8000, "model_types": [ "chat" ], @@ -141,7 +154,8 @@ }, { "name": "qwen3-235b-a22b-instruct-2507", - "max_tokens": 256000, + "content_length": 262144, + "max_output": 16384, "model_types": [ "chat" ], @@ -151,7 +165,8 @@ }, { "name": "glm-4.6", - "max_tokens": 200000, + "content_length": 200000, + "max_output": 128000, "model_types": [ "chat" ], @@ -161,7 +176,8 @@ }, { "name": "minimax-m2", - "max_tokens": 200000, + "content_length": 204800, + "max_output": 128000, "model_types": [ "chat" ], diff --git a/conf/models/upstage.json b/conf/models/upstage.json index 7fb1233d3a..ac2a5d223f 100644 --- a/conf/models/upstage.json +++ b/conf/models/upstage.json @@ -12,7 +12,8 @@ "models": [ { "name": "solar-pro3", - "max_tokens": 65536, + "content_length": 128000, + "max_output": 4096, "model_types": [ "chat" ], @@ -22,7 +23,8 @@ }, { "name": "solar-pro2", - "max_tokens": 65536, + "content_length": 32768, + "max_output": 4096, "model_types": [ "chat" ], @@ -32,7 +34,8 @@ }, { "name": "solar-pro", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 4096, "model_types": [ "chat" ], @@ -42,7 +45,8 @@ }, { "name": "solar-mini", - "max_tokens": 32768, + "content_length": 4096, + "max_output": 4096, "model_types": [ "chat" ], diff --git a/conf/models/volcengine.json b/conf/models/volcengine.json index 34bab3ecf4..6da91e021b 100644 --- a/conf/models/volcengine.json +++ b/conf/models/volcengine.json @@ -14,7 +14,8 @@ "models": [ { "name": "doubao-seed-2-0-pro-260215", - "max_tokens": 262144, + "content_length": 256000, + "max_output": 16384, "model_types": [ "chat" ], diff --git a/conf/models/xai.json b/conf/models/xai.json index 9cd24f5584..f4c382d090 100644 --- a/conf/models/xai.json +++ b/conf/models/xai.json @@ -14,7 +14,8 @@ "models": [ { "name": "grok-4", - "max_tokens": 256000, + "content_length": 262144, + "max_output": 131072, "model_types": [ "chat" ], @@ -24,7 +25,8 @@ }, { "name": "grok-3", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -34,7 +36,8 @@ }, { "name": "grok-3-fast", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -44,7 +47,8 @@ }, { "name": "grok-3-mini", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -54,7 +58,8 @@ }, { "name": "grok-3-mini-mini-fast", - "max_tokens": 131072, + "content_length": 131072, + "max_output": 131072, "model_types": [ "chat" ], @@ -64,7 +69,8 @@ }, { "name": "grok-2-vision", - "max_tokens": 32768, + "content_length": 32768, + "max_output": 8192, "model_types": [ "vision" ] diff --git a/conf/models/xiaomi.json b/conf/models/xiaomi.json index deb9a2bd1c..21c4864cd9 100644 --- a/conf/models/xiaomi.json +++ b/conf/models/xiaomi.json @@ -9,7 +9,8 @@ "models": [ { "name": "mimo-v2.5-pro", - "max_tokens": 1048576, + "content_length": 128000, + "max_output": 8192, "model_types": [ "chat" ], @@ -19,7 +20,8 @@ }, { "name": "mimo-v2.5", - "max_tokens": 1048576, + "content_length": 128000, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/xunfei.json b/conf/models/xunfei.json index aa04ec5d4a..e45eb7af6f 100644 --- a/conf/models/xunfei.json +++ b/conf/models/xunfei.json @@ -10,7 +10,8 @@ "models": [ { "name": "spark-x", - "max_tokens": 134144, + "content_length": 128000, + "max_output": 8192, "model_types": [ "chat" ], diff --git a/conf/models/zhipu-ai.json b/conf/models/zhipu-ai.json index 5d951d1cef..c55522420e 100644 --- a/conf/models/zhipu-ai.json +++ b/conf/models/zhipu-ai.json @@ -35,7 +35,7 @@ }, { "name": "glm-5.1", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -50,7 +50,7 @@ }, { "name": "glm-5", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -65,7 +65,7 @@ }, { "name": "glm-5-turbo", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -80,7 +80,7 @@ }, { "name": "glm-5v-turbo", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -95,7 +95,7 @@ }, { "name": "glm-4.7", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -110,7 +110,7 @@ }, { "name": "glm-4.7-flashx", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -125,7 +125,7 @@ }, { "name": "glm-4.6", - "content_length": 204800, + "content_length": 200000, "max_output": 128000, "model_types": [ "chat" @@ -140,8 +140,8 @@ }, { "name": "glm-4.6v-Flash", - "content_length": 204800, - "max_output": 128000, + "content_length": 128000, + "max_output": 32768, "model_types": [ "chat", "vision" @@ -231,8 +231,8 @@ }, { "name": "glm-4.5v", - "content_length": 64000, - "max_output": 16000, + "content_length": 65536, + "max_output": 16384, "model_types": [ "vision" ], @@ -247,7 +247,7 @@ { "name": "glm-4-plus", "content_length": 128000, - "max_output": 32000, + "max_output": 4096, "model_types": [ "chat" ], @@ -258,7 +258,7 @@ { "name": "glm-4-0520", "content_length": 128000, - "max_output": 32000, + "max_output": 4096, "model_types": [ "chat" ], @@ -269,7 +269,7 @@ { "name": "glm-4", "content_length": 128000, - "max_output": 4000, + "max_output": 4096, "model_types": [ "chat" ], @@ -279,8 +279,8 @@ }, { "name": "glm-4-airx", - "content_length": 8000, - "max_output": 4000, + "content_length": 8192, + "max_output": 4096, "model_types": [ "chat" ], @@ -290,8 +290,8 @@ }, { "name": "glm-4-air", - "content_length": 8000, - "max_output": 4000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], @@ -302,7 +302,7 @@ { "name": "glm-4-flash", "content_length": 128000, - "max_output": 4000, + "max_output": 16384, "model_types": [ "chat" ], @@ -313,7 +313,7 @@ { "name": "glm-4-flashx", "content_length": 128000, - "max_output": 16000, + "max_output": 16384, "model_types": [ "chat" ], @@ -324,7 +324,7 @@ { "name": "glm-4-long", "content_length": 1000000, - "max_output": 4000, + "max_output": 4096, "model_types": [ "chat" ], @@ -334,16 +334,16 @@ }, { "name": "glm-4v", - "content_length": 16000, - "max_output": 1000, + "content_length": 16384, + "max_output": 1024, "model_types": [ "vision" ] }, { "name": "glm-4-9b", - "content_length": 8000, - "max_output": 1000, + "content_length": 128000, + "max_output": 16384, "model_types": [ "chat" ], diff --git a/internal/entity/models/model_test.go b/internal/entity/models/model_test.go index ef932c6195..6f524f1922 100644 --- a/internal/entity/models/model_test.go +++ b/internal/entity/models/model_test.go @@ -294,22 +294,22 @@ func TestPPIOProviderConfigLoadsIntoProviderManager(t *testing.T) { if err != nil { t.Fatalf("GetModelByName: %v", err) } - if *model.MaxOutput != 64000 { - t.Errorf("deepseek/deepseek-r1 max_tokens=%d", *model.MaxOutput) + if *model.MaxOutput != 32768 || *model.ContentLength != 131072 { + t.Errorf("deepseek/deepseek-r1 max_output=%d content_length=%d", *model.MaxOutput, *model.ContentLength) } model, err = pm.GetModelByName("ppio", "deepseek/deepseek-v4-pro") if err != nil { t.Fatalf("GetModelByName v4 pro: %v", err) } - if *model.MaxOutput != 1048576 { - t.Errorf("deepseek/deepseek-v4-pro max_tokens=%d", *model.MaxOutput) + if *model.MaxOutput != 393216 || *model.ContentLength != 1048576 { + t.Errorf("deepseek/deepseek-v4-pro max_output=%d content_length=%d", *model.MaxOutput, *model.ContentLength) } model, err = pm.GetModelByName("ppio", "deepseek/deepseek-v4-flash") if err != nil { t.Fatalf("GetModelByName v4 flash: %v", err) } - if *model.MaxOutput != 1048576 { - t.Errorf("deepseek/deepseek-v4-flash max_tokens=%d", *model.MaxOutput) + if *model.MaxOutput != 393216 || *model.ContentLength != 1048576 { + t.Errorf("deepseek/deepseek-v4-flash max_output=%d content_length=%d", *model.MaxOutput, *model.ContentLength) } if !model.ModelTypeMap["chat"] { t.Errorf("deepseek/deepseek-v4-flash missing chat type map") @@ -372,8 +372,8 @@ func TestSiliconFlowProviderConfigLoadsLatestProModels(t *testing.T) { if err != nil { t.Fatalf("GetModelByName DeepSeek-V4-Pro: %v", err) } - if *deepSeekV4Pro.MaxOutput != 1048576 { - t.Errorf("DeepSeek-V4-Pro max_tokens=%d", *deepSeekV4Pro.MaxOutput) + if *deepSeekV4Pro.MaxOutput != 393216 || *deepSeekV4Pro.ContentLength != 1048576 { + t.Errorf("DeepSeek-V4-Pro max_output=%d content_length=%d", *deepSeekV4Pro.MaxOutput, *deepSeekV4Pro.ContentLength) } if !deepSeekV4Pro.ModelTypeMap["chat"] { t.Errorf("DeepSeek-V4-Pro model types=%v, want chat", deepSeekV4Pro.ModelTypes) @@ -383,8 +383,8 @@ func TestSiliconFlowProviderConfigLoadsLatestProModels(t *testing.T) { if err != nil { t.Fatalf("GetModelByName Kimi-K2.6: %v", err) } - if *kimiK26.MaxOutput != 262144 { - t.Errorf("Kimi-K2.6 max_tokens=%d", *kimiK26.MaxOutput) + if *kimiK26.MaxOutput != 65536 || *kimiK26.ContentLength != 262144 { + t.Errorf("Kimi-K2.6 max_output=%d content_length=%d", *kimiK26.MaxOutput, *kimiK26.ContentLength) } if !kimiK26.ModelTypeMap["chat"] || !kimiK26.ModelTypeMap["vision"] { t.Errorf("Kimi-K2.6 model types=%v, want chat+vision", kimiK26.ModelTypes) @@ -394,7 +394,7 @@ func TestSiliconFlowProviderConfigLoadsLatestProModels(t *testing.T) { if err != nil { t.Fatalf("GetModelByName GLM-5.1: %v", err) } - if *glm51.MaxOutput != 204800 { - t.Errorf("GLM-5.1 max_tokens=%d", *glm51.MaxOutput) + if *glm51.MaxOutput != 128000 || *glm51.ContentLength != 200000 { + t.Errorf("GLM-5.1 max_output=%d content_length=%d", *glm51.MaxOutput, *glm51.ContentLength) } }