diff --git a/internal/providers/configs/openrouter.json b/internal/providers/configs/openrouter.json
index f3f214a1e868052448a01643a7273d744501640d..d395784e77e0a300ba952389b649c03cc6eaecdb 100644
--- a/internal/providers/configs/openrouter.json
+++ b/internal/providers/configs/openrouter.json
@@ -547,31 +547,25 @@
     {
       "id": "deepseek/deepseek-chat-v3-0324",
       "name": "DeepSeek: DeepSeek V3 0324",
-      "cost_per_1m_in": 0.77,
-      "cost_per_1m_out": 0.77,
+      "cost_per_1m_in": 0.27,
+      "cost_per_1m_out": 1.12,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_out_cached": 0.135,
       "context_window": 163840,
-      "default_max_tokens": 65536,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
+      "default_max_tokens": 81920,
+      "can_reason": false,
       "supports_attachments": false,
       "options": {}
     },
     {
       "id": "deepseek/deepseek-chat-v3.1",
       "name": "DeepSeek: DeepSeek V3.1",
-      "cost_per_1m_in": 0.2,
-      "cost_per_1m_out": 0.8,
+      "cost_per_1m_in": 0.21,
+      "cost_per_1m_out": 0.79,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.1,
+      "cost_per_1m_out_cached": 0.13,
       "context_window": 163840,
-      "default_max_tokens": 32768,
+      "default_max_tokens": 16384,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -585,11 +579,11 @@
     {
       "id": "deepseek/deepseek-v3.1-terminus",
       "name": "DeepSeek: DeepSeek V3.1 Terminus",
-      "cost_per_1m_in": 0.3,
-      "cost_per_1m_out": 0.95,
+      "cost_per_1m_in": 0.23,
+      "cost_per_1m_out": 0.9,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.13,
-      "context_window": 131072,
+      "cost_per_1m_out_cached": 0.115,
+      "context_window": 163840,
       "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
@@ -661,12 +655,12 @@
     {
       "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": 0.7,
+      "cost_per_1m_out": 2.5,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.225,
+      "cost_per_1m_out_cached": 0.35,
       "context_window": 163840,
-      "default_max_tokens": 32768,
+      "default_max_tokens": 16384,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -1060,19 +1054,6 @@
       "supports_attachments": false,
       "options": {}
     },
-    {
-      "id": "meta-llama/llama-3.1-405b-instruct",
-      "name": "Meta: Llama 3.1 405B Instruct",
-      "cost_per_1m_in": 5,
-      "cost_per_1m_out": 16,
-      "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
-      "context_window": 128000,
-      "default_max_tokens": 4096,
-      "can_reason": false,
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "meta-llama/llama-3.1-70b-instruct",
       "name": "Meta: Llama 3.1 70B Instruct",
@@ -1081,7 +1062,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 8192,
+      "default_max_tokens": 13107,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1089,12 +1070,12 @@
     {
       "id": "meta-llama/llama-3.3-70b-instruct",
       "name": "Meta: Llama 3.3 70B Instruct",
-      "cost_per_1m_in": 0.13,
-      "cost_per_1m_out": 0.4,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 0.6,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_out_cached": 0.6,
       "context_window": 131072,
-      "default_max_tokens": 13107,
+      "default_max_tokens": 65536,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1106,8 +1087,8 @@
       "cost_per_1m_out": 0,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 65536,
-      "default_max_tokens": 6553,
+      "context_window": 128000,
+      "default_max_tokens": 64000,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1320,7 +1301,7 @@
       "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": false,
       "supports_attachments": true,
       "options": {}
@@ -1377,19 +1358,6 @@
       "supports_attachments": false,
       "options": {}
     },
-    {
-      "id": "mistralai/mistral-small-24b-instruct-2501",
-      "name": "Mistral: Mistral Small 3",
-      "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": 32768,
-      "default_max_tokens": 1024,
-      "can_reason": false,
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "mistralai/mistral-small-3.1-24b-instruct:free",
       "name": "Mistral: Mistral Small 3.1 24B (free)",
@@ -1497,12 +1465,12 @@
     {
       "id": "moonshotai/kimi-k2",
       "name": "MoonshotAI: Kimi K2 0711",
-      "cost_per_1m_in": 0.6,
-      "cost_per_1m_out": 2.5,
+      "cost_per_1m_in": 0.57,
+      "cost_per_1m_out": 2.3,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.15,
+      "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 13107,
+      "default_max_tokens": 65536,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1513,7 +1481,7 @@
       "cost_per_1m_in": 0.6,
       "cost_per_1m_out": 2.5,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.15,
+      "cost_per_1m_out_cached": 0.3,
       "context_window": 262144,
       "default_max_tokens": 26214,
       "can_reason": false,
@@ -1543,11 +1511,11 @@
       "id": "moonshotai/kimi-k2.5",
       "name": "MoonshotAI: Kimi K2.5",
       "cost_per_1m_in": 0.45,
-      "cost_per_1m_out": 2.25,
+      "cost_per_1m_out": 2.2,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.07,
+      "cost_per_1m_out_cached": 0.225,
       "context_window": 262144,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 32767,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -1764,7 +1732,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0.5,
       "context_window": 1047576,
-      "default_max_tokens": 104757,
+      "default_max_tokens": 16384,
       "can_reason": false,
       "supports_attachments": true,
       "options": {}
@@ -2038,7 +2006,7 @@
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.125,
+      "cost_per_1m_out_cached": 0.13,
       "context_window": 400000,
       "default_max_tokens": 64000,
       "can_reason": true,
@@ -2148,7 +2116,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0.175,
       "context_window": 128000,
-      "default_max_tokens": 16000,
+      "default_max_tokens": 8192,
       "can_reason": false,
       "supports_attachments": true,
       "options": {}
@@ -2265,11 +2233,11 @@
       "id": "openai/gpt-oss-120b",
       "name": "OpenAI: gpt-oss-120b",
       "cost_per_1m_in": 0.05,
-      "cost_per_1m_out": 0.45,
+      "cost_per_1m_out": 0.25,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.025,
+      "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 32768,
+      "default_max_tokens": 16384,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -2302,12 +2270,12 @@
     {
       "id": "openai/gpt-oss-20b",
       "name": "OpenAI: gpt-oss-20b",
-      "cost_per_1m_in": 0.05,
-      "cost_per_1m_out": 0.2,
+      "cost_per_1m_in": 0.045,
+      "cost_per_1m_out": 0.18,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 13107,
+      "default_max_tokens": 16384,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -2679,8 +2647,8 @@
     {
       "id": "qwen/qwen3-235b-a22b-2507",
       "name": "Qwen: Qwen3 235B A22B Instruct 2507",
-      "cost_per_1m_in": 0.1,
-      "cost_per_1m_out": 0.1,
+      "cost_per_1m_in": 0.2,
+      "cost_per_1m_out": 0.8,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
@@ -2692,12 +2660,12 @@
     {
       "id": "qwen/qwen3-235b-a22b-thinking-2507",
       "name": "Qwen: Qwen3 235B A22B Thinking 2507",
-      "cost_per_1m_in": 0.11,
-      "cost_per_1m_out": 0.6,
+      "cost_per_1m_in": 0.1495,
+      "cost_per_1m_out": 1.495,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.055,
-      "context_window": 262144,
-      "default_max_tokens": 131072,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 131072,
+      "default_max_tokens": 13107,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -2735,7 +2703,7 @@
       "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": false,
       "supports_attachments": false,
       "options": {}
@@ -2800,12 +2768,12 @@
     {
       "id": "qwen/qwen3-coder-30b-a3b-instruct",
       "name": "Qwen: Qwen3 Coder 30B A3B Instruct",
-      "cost_per_1m_in": 0.07,
-      "cost_per_1m_out": 0.27,
+      "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": 160000,
-      "default_max_tokens": 16384,
+      "context_window": 262144,
+      "default_max_tokens": 26214,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -2813,12 +2781,12 @@
     {
       "id": "qwen/qwen3-coder",
       "name": "Qwen: Qwen3 Coder 480B A35B",
-      "cost_per_1m_in": 0.22,
-      "cost_per_1m_out": 1,
+      "cost_per_1m_in": 0.4,
+      "cost_per_1m_out": 1.8,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.022,
+      "cost_per_1m_out_cached": 0,
       "context_window": 262144,
-      "default_max_tokens": 26214,
+      "default_max_tokens": 131072,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -2852,12 +2820,12 @@
     {
       "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": 0.18,
+      "cost_per_1m_out": 1.35,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.06,
+      "cost_per_1m_out_cached": 0.18,
       "context_window": 262144,
-      "default_max_tokens": 32768,
+      "default_max_tokens": 131072,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -2910,8 +2878,8 @@
     {
       "id": "qwen/qwen3-next-80b-a3b-instruct",
       "name": "Qwen: Qwen3 Next 80B A3B Instruct",
-      "cost_per_1m_in": 0.15,
-      "cost_per_1m_out": 1.2,
+      "cost_per_1m_in": 0.1,
+      "cost_per_1m_out": 1.1,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
@@ -2955,8 +2923,8 @@
     {
       "id": "qwen/qwen3-vl-235b-a22b-instruct",
       "name": "Qwen: Qwen3 VL 235B A22B Instruct",
-      "cost_per_1m_in": 0.26,
-      "cost_per_1m_out": 1.04,
+      "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": 131072,
@@ -3000,12 +2968,12 @@
     {
       "id": "qwen/qwen3-vl-30b-a3b-thinking",
       "name": "Qwen: Qwen3 VL 30B A3B Thinking",
-      "cost_per_1m_in": 0.29,
-      "cost_per_1m_out": 1,
+      "cost_per_1m_in": 0.13,
+      "cost_per_1m_out": 1.56,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 262144,
-      "default_max_tokens": 131072,
+      "context_window": 131072,
+      "default_max_tokens": 16384,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -3069,7 +3037,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -3121,8 +3089,8 @@
     {
       "id": "qwen/qwen3.5-27b",
       "name": "Qwen: Qwen3.5-27B",
-      "cost_per_1m_in": 0.3,
-      "cost_per_1m_out": 2.4,
+      "cost_per_1m_in": 0.195,
+      "cost_per_1m_out": 1.56,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
@@ -3334,9 +3302,9 @@
       "cost_per_1m_in": 0.1,
       "cost_per_1m_out": 0.3,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.1,
+      "cost_per_1m_out_cached": 0.01,
       "context_window": 262144,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -3382,12 +3350,12 @@
     {
       "id": "z-ai/glm-4.5-air",
       "name": "Z.ai: GLM 4.5 Air",
-      "cost_per_1m_in": 0.14,
-      "cost_per_1m_out": 0.86,
+      "cost_per_1m_in": 0.2,
+      "cost_per_1m_out": 1.2,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 65536,
+      "default_max_tokens": 13107,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -3439,12 +3407,12 @@
     {
       "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",
@@ -3515,11 +3483,11 @@
     {
       "id": "z-ai/glm-5",
       "name": "Z.ai: GLM 5",
-      "cost_per_1m_in": 1,
-      "cost_per_1m_out": 3.2,
+      "cost_per_1m_in": 0.95,
+      "cost_per_1m_out": 2.55,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0.2,
-      "context_window": 202800,
+      "context_window": 204800,
       "default_max_tokens": 65536,
       "can_reason": true,
       "reasoning_levels": [
@@ -3534,10 +3502,10 @@
     {
       "id": "x-ai/grok-3",
       "name": "xAI: Grok 3",
-      "cost_per_1m_in": 5,
-      "cost_per_1m_out": 25,
+      "cost_per_1m_in": 3,
+      "cost_per_1m_out": 15,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 1.25,
+      "cost_per_1m_out_cached": 0.75,
       "context_window": 131072,
       "default_max_tokens": 13107,
       "can_reason": false,
@@ -3547,10 +3515,10 @@
     {
       "id": "x-ai/grok-3-beta",
       "name": "xAI: Grok 3 Beta",
-      "cost_per_1m_in": 5,
-      "cost_per_1m_out": 25,
+      "cost_per_1m_in": 3,
+      "cost_per_1m_out": 15,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 1.25,
+      "cost_per_1m_out_cached": 0.75,
       "context_window": 131072,
       "default_max_tokens": 13107,
       "can_reason": false,
@@ -3560,10 +3528,10 @@
     {
       "id": "x-ai/grok-3-mini",
       "name": "xAI: Grok 3 Mini",
-      "cost_per_1m_in": 0.6,
-      "cost_per_1m_out": 4,
+      "cost_per_1m_in": 0.3,
+      "cost_per_1m_out": 0.5,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.15,
+      "cost_per_1m_out_cached": 0.075,
       "context_window": 131072,
       "default_max_tokens": 13107,
       "can_reason": true,
@@ -3579,10 +3547,10 @@
     {
       "id": "x-ai/grok-3-mini-beta",
       "name": "xAI: Grok 3 Mini Beta",
-      "cost_per_1m_in": 0.6,
-      "cost_per_1m_out": 4,
+      "cost_per_1m_in": 0.3,
+      "cost_per_1m_out": 0.5,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.15,
+      "cost_per_1m_out_cached": 0.075,
       "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 1830def83abb6a9213e02d28d981105c4d5de62c..b18f3dcd8ac9e0333e1d9b3528b3663e99d5342a 100644
--- a/internal/providers/configs/venice.json
+++ b/internal/providers/configs/venice.json
@@ -382,6 +382,25 @@
       "supports_attachments": true,
       "options": {}
     },
+    {
+      "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_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 2000000,
+      "default_max_tokens": 32768,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": true,
+      "options": {}
+    },
     {
       "id": "grok-code-fast-1",
       "name": "Grok Code Fast 1",
@@ -635,6 +654,25 @@
         "top_p": 0.95
       }
     },
+    {
+      "id": "qwen3-5-9b",
+      "name": "Qwen 3.5 9B",
+      "cost_per_1m_in": 0.05,
+      "cost_per_1m_out": 0.15,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 256000,
+      "default_max_tokens": 32768,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": true,
+      "options": {}
+    },
     {
       "id": "qwen3-vl-235b-a22b",
       "name": "Qwen3 VL 235B",