From e2ded4121e5e5fab9b2887c68832d34f15da1871 Mon Sep 17 00:00:00 2001
From: Charm <124303983+charmcli@users.noreply.github.com>
Date: Thu, 12 Mar 2026 03:04:30 +0000
Subject: [PATCH] chore: auto-update generated files

---
 internal/providers/configs/huggingface.json |  61 +++++-
 internal/providers/configs/openrouter.json  | 230 ++++++++++----------
 internal/providers/configs/synthetic.json   |  19 ++
 internal/providers/configs/venice.json      |  13 ++
 internal/providers/configs/vercel.json      | 230 ++++++++++++--------
 5 files changed, 335 insertions(+), 218 deletions(-)

diff --git a/internal/providers/configs/huggingface.json b/internal/providers/configs/huggingface.json
index d3f3a8e4bf701c0d40a4fa07e067c55c173deede..8cb6ca8360a6538f095648587892e1c1965ec738 100644
--- a/internal/providers/configs/huggingface.json
+++ b/internal/providers/configs/huggingface.json
@@ -7,6 +7,19 @@
   "default_large_model_id": "moonshotai/Kimi-K2-Instruct-0905:groq",
   "default_small_model_id": "openai/gpt-oss-20b:groq",
   "models": [
+    {
+      "id": "MiniMaxAI/MiniMax-M2.1:fireworks-ai",
+      "name": "MiniMaxAI/MiniMax-M2.1 (fireworks-ai)",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 204800,
+      "default_max_tokens": 8192,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "MiniMaxAI/MiniMax-M2.5:fireworks-ai",
       "name": "MiniMaxAI/MiniMax-M2.5 (fireworks-ai)",
@@ -33,6 +46,19 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "Qwen/Qwen3-8B:fireworks-ai",
+      "name": "Qwen/Qwen3-8B (fireworks-ai)",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 40960,
+      "default_max_tokens": 8192,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "Qwen/Qwen3-VL-30B-A3B-Instruct:fireworks-ai",
       "name": "Qwen/Qwen3-VL-30B-A3B-Instruct (fireworks-ai)",
@@ -125,8 +151,8 @@
       "options": {}
     },
     {
-      "id": "moonshotai/Kimi-K2-Instruct-0905:groq",
-      "name": "moonshotai/Kimi-K2-Instruct-0905 (groq)",
+      "id": "moonshotai/Kimi-K2-Instruct-0905:fireworks-ai",
+      "name": "moonshotai/Kimi-K2-Instruct-0905 (fireworks-ai)",
       "cost_per_1m_in": 0,
       "cost_per_1m_out": 0,
       "cost_per_1m_in_cached": 0,
@@ -138,8 +164,8 @@
       "options": {}
     },
     {
-      "id": "moonshotai/Kimi-K2-Thinking:fireworks-ai",
-      "name": "moonshotai/Kimi-K2-Thinking (fireworks-ai)",
+      "id": "moonshotai/Kimi-K2-Instruct-0905:groq",
+      "name": "moonshotai/Kimi-K2-Instruct-0905 (groq)",
       "cost_per_1m_in": 0,
       "cost_per_1m_out": 0,
       "cost_per_1m_in_cached": 0,
@@ -151,8 +177,8 @@
       "options": {}
     },
     {
-      "id": "moonshotai/Kimi-K2.5:fireworks-ai",
-      "name": "moonshotai/Kimi-K2.5 (fireworks-ai)",
+      "id": "moonshotai/Kimi-K2-Thinking:fireworks-ai",
+      "name": "moonshotai/Kimi-K2-Thinking (fireworks-ai)",
       "cost_per_1m_in": 0,
       "cost_per_1m_out": 0,
       "cost_per_1m_in_cached": 0,
@@ -164,13 +190,13 @@
       "options": {}
     },
     {
-      "id": "openai/gpt-oss-120b:cerebras",
-      "name": "openai/gpt-oss-120b (cerebras)",
-      "cost_per_1m_in": 0.25,
-      "cost_per_1m_out": 0.69,
+      "id": "moonshotai/Kimi-K2.5:fireworks-ai",
+      "name": "moonshotai/Kimi-K2.5 (fireworks-ai)",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 262144,
       "default_max_tokens": 8192,
       "can_reason": false,
       "supports_attachments": false,
@@ -241,6 +267,19 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "zai-org/GLM-4.7:fireworks-ai",
+      "name": "zai-org/GLM-4.7 (fireworks-ai)",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 202752,
+      "default_max_tokens": 8192,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "zai-org/GLM-5:fireworks-ai",
       "name": "zai-org/GLM-5 (fireworks-ai)",
diff --git a/internal/providers/configs/openrouter.json b/internal/providers/configs/openrouter.json
index 968a25ef7ade70cca5ed8a36105d73107b199c5c..0056f2c12fe96531a032f20ff2b1fcfe08d533d7 100644
--- a/internal/providers/configs/openrouter.json
+++ b/internal/providers/configs/openrouter.json
@@ -135,8 +135,8 @@
       "name": "Anthropic: Claude 3.5 Sonnet",
       "cost_per_1m_in": 6,
       "cost_per_1m_out": 30,
-      "cost_per_1m_in_cached": 7.5,
-      "cost_per_1m_out_cached": 0.6,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
       "context_window": 200000,
       "default_max_tokens": 4096,
       "can_reason": false,
@@ -566,12 +566,12 @@
     {
       "id": "deepseek/deepseek-chat-v3.1",
       "name": "DeepSeek: DeepSeek V3.1",
-      "cost_per_1m_in": 0.21,
-      "cost_per_1m_out": 0.79,
+      "cost_per_1m_in": 0.2,
+      "cost_per_1m_out": 0.8,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.13,
+      "cost_per_1m_out_cached": 0.1,
       "context_window": 163840,
-      "default_max_tokens": 16384,
+      "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -585,12 +585,12 @@
     {
       "id": "deepseek/deepseek-v3.1-terminus",
       "name": "DeepSeek: DeepSeek V3.1 Terminus",
-      "cost_per_1m_in": 0.21,
-      "cost_per_1m_out": 0.79,
+      "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,
+      "cost_per_1m_out_cached": 0.115,
       "context_window": 163840,
-      "default_max_tokens": 16384,
+      "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -838,7 +838,7 @@
       "cost_per_1m_in_cached": 0.08333,
       "cost_per_1m_out_cached": 0.05,
       "context_window": 1048576,
-      "default_max_tokens": 32767,
+      "default_max_tokens": 32768,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -951,6 +951,44 @@
       "supports_attachments": true,
       "options": {}
     },
+    {
+      "id": "openrouter/healer-alpha",
+      "name": "Healer Alpha",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 262144,
+      "default_max_tokens": 32768,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": true,
+      "options": {}
+    },
+    {
+      "id": "openrouter/hunter-alpha",
+      "name": "Hunter Alpha",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 1048576,
+      "default_max_tokens": 32768,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "inception/mercury",
       "name": "Inception: Mercury",
@@ -1100,25 +1138,6 @@
       "supports_attachments": true,
       "options": {}
     },
-    {
-      "id": "minimax/minimax-m1",
-      "name": "MiniMax: MiniMax M1",
-      "cost_per_1m_in": 0.44,
-      "cost_per_1m_out": 1.76,
-      "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
-      "context_window": 1000000,
-      "default_max_tokens": 20000,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "minimax/minimax-m2",
       "name": "MiniMax: MiniMax M2",
@@ -1165,7 +1184,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0.03,
       "context_window": 204800,
-      "default_max_tokens": 65536,
+      "default_max_tokens": 65550,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -1301,7 +1320,7 @@
       "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": {}
@@ -1374,12 +1393,12 @@
     {
       "id": "mistralai/mistral-small-3.2-24b-instruct",
       "name": "Mistral: Mistral Small 3.2 24B",
-      "cost_per_1m_in": 0.1,
-      "cost_per_1m_out": 0.3,
+      "cost_per_1m_in": 0.06,
+      "cost_per_1m_out": 0.18,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_out_cached": 0.03,
       "context_window": 131072,
-      "default_max_tokens": 13107,
+      "default_max_tokens": 65536,
       "can_reason": false,
       "supports_attachments": true,
       "options": {}
@@ -1465,12 +1484,12 @@
     {
       "id": "moonshotai/kimi-k2",
       "name": "MoonshotAI: Kimi K2 0711",
-      "cost_per_1m_in": 0.55,
-      "cost_per_1m_out": 2.2,
+      "cost_per_1m_in": 0.57,
+      "cost_per_1m_out": 2.3,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131000,
-      "default_max_tokens": 13100,
+      "context_window": 131072,
+      "default_max_tokens": 65536,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1481,9 +1500,9 @@
       "cost_per_1m_in": 0.6,
       "cost_per_1m_out": 2.5,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_out_cached": 0.3,
       "context_window": 262144,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 26214,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -1596,6 +1615,25 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "nvidia/nemotron-3-super-120b-a12b:free",
+      "name": "NVIDIA: Nemotron 3 Super (free)",
+      "cost_per_1m_in": 0,
+      "cost_per_1m_out": 0,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 262144,
+      "default_max_tokens": 131072,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "nvidia/nemotron-nano-12b-v2-vl:free",
       "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -1713,7 +1751,7 @@
       "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": {}
@@ -1987,7 +2025,7 @@
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.13,
+      "cost_per_1m_out_cached": 0.125,
       "context_window": 400000,
       "default_max_tokens": 64000,
       "can_reason": true,
@@ -2097,7 +2135,7 @@
       "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": {}
@@ -2251,12 +2289,12 @@
     {
       "id": "openai/gpt-oss-20b",
       "name": "OpenAI: gpt-oss-20b",
-      "cost_per_1m_in": 0.045,
-      "cost_per_1m_out": 0.18,
+      "cost_per_1m_in": 0.03,
+      "cost_per_1m_out": 0.14,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 16384,
+      "default_max_tokens": 13107,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -2490,25 +2528,6 @@
       "supports_attachments": false,
       "options": {}
     },
-    {
-      "id": "qwen/qwq-32b",
-      "name": "Qwen: QwQ 32B",
-      "cost_per_1m_in": 0.15,
-      "cost_per_1m_out": 0.58,
-      "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
-      "default_max_tokens": 65536,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "qwen/qwen-plus-2025-07-28",
       "name": "Qwen: Qwen Plus 0728",
@@ -2609,12 +2628,12 @@
     {
       "id": "qwen/qwen3-14b",
       "name": "Qwen: Qwen3 14B",
-      "cost_per_1m_in": 0.12,
-      "cost_per_1m_out": 0.24,
+      "cost_per_1m_in": 0.2275,
+      "cost_per_1m_out": 0.91,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 40960,
-      "default_max_tokens": 20480,
+      "context_window": 131072,
+      "default_max_tokens": 4096,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -2657,25 +2676,6 @@
       "supports_attachments": false,
       "options": {}
     },
-    {
-      "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_cached": 0,
-      "cost_per_1m_out_cached": 0.055,
-      "context_window": 262144,
-      "default_max_tokens": 131072,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "qwen/qwen3-30b-a3b",
       "name": "Qwen: Qwen3 30B A3B",
@@ -2703,7 +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": {}
@@ -2711,11 +2711,11 @@
     {
       "id": "qwen/qwen3-32b",
       "name": "Qwen: Qwen3 32B",
-      "cost_per_1m_in": 0.08,
-      "cost_per_1m_out": 0.28,
+      "cost_per_1m_in": 0.104,
+      "cost_per_1m_out": 0.416,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 40960,
+      "context_window": 131072,
       "default_max_tokens": 4096,
       "can_reason": true,
       "reasoning_levels": [
@@ -2782,11 +2782,11 @@
       "id": "qwen/qwen3-coder",
       "name": "Qwen: Qwen3 Coder 480B A35B",
       "cost_per_1m_in": 0.22,
-      "cost_per_1m_out": 1,
+      "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": 32768,
       "can_reason": false,
       "supports_attachments": false,
       "options": {}
@@ -2904,8 +2904,8 @@
     {
       "id": "qwen/qwen3-next-80b-a3b-thinking",
       "name": "Qwen: Qwen3 Next 80B A3B Thinking",
-      "cost_per_1m_in": 0.15,
-      "cost_per_1m_out": 1.2,
+      "cost_per_1m_in": 0.3,
+      "cost_per_1m_out": 0.3,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
@@ -2936,8 +2936,8 @@
     {
       "id": "qwen/qwen3-vl-235b-a22b-thinking",
       "name": "Qwen: Qwen3 VL 235B A22B Thinking",
-      "cost_per_1m_in": 0,
-      "cost_per_1m_out": 0,
+      "cost_per_1m_in": 0.26,
+      "cost_per_1m_out": 2.6,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
@@ -2968,12 +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",
@@ -3336,7 +3336,7 @@
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0.11,
       "context_window": 131072,
-      "default_max_tokens": 49152,
+      "default_max_tokens": 48000,
       "can_reason": true,
       "reasoning_levels": [
         "low",
@@ -3350,12 +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",
@@ -3528,10 +3528,10 @@
     {
       "id": "x-ai/grok-3-mini",
       "name": "xAI: Grok 3 Mini",
-      "cost_per_1m_in": 0.3,
-      "cost_per_1m_out": 0.5,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 4,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.075,
+      "cost_per_1m_out_cached": 0.15,
       "context_window": 131072,
       "default_max_tokens": 13107,
       "can_reason": true,
@@ -3547,10 +3547,10 @@
     {
       "id": "x-ai/grok-3-mini-beta",
       "name": "xAI: Grok 3 Mini Beta",
-      "cost_per_1m_in": 0.3,
-      "cost_per_1m_out": 0.5,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 4,
       "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0.075,
+      "cost_per_1m_out_cached": 0.15,
       "context_window": 131072,
       "default_max_tokens": 13107,
       "can_reason": true,
diff --git a/internal/providers/configs/synthetic.json b/internal/providers/configs/synthetic.json
index 4533d0eb0bef431ac58a63f8c55298e305b2f477..e2a209aee3389bc04b1a55f867b304be837d342b 100644
--- a/internal/providers/configs/synthetic.json
+++ b/internal/providers/configs/synthetic.json
@@ -217,6 +217,25 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
+      "name": "NVIDIA Nemotron 3 Super 120B A12B NVFP4",
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 3,
+      "cost_per_1m_in_cached": 0.6,
+      "cost_per_1m_out_cached": 0.6,
+      "context_window": 262144,
+      "default_max_tokens": 32768,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507",
       "name": "Qwen3 235B A22B Thinking 2507",
diff --git a/internal/providers/configs/venice.json b/internal/providers/configs/venice.json
index eca1fcbe4fc35322c65f748cc9f8f0afbbe399e8..1830def83abb6a9213e02d28d981105c4d5de62c 100644
--- a/internal/providers/configs/venice.json
+++ b/internal/providers/configs/venice.json
@@ -503,6 +503,19 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "mistral-small-3-2-24b-instruct",
+      "name": "Mistral Small 3.2 24B Instruct",
+      "cost_per_1m_in": 0.09375,
+      "cost_per_1m_out": 0.25,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 256000,
+      "default_max_tokens": 32768,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "nvidia-nemotron-3-nano-30b-a3b",
       "name": "NVIDIA Nemotron 3 Nano 30B",
diff --git a/internal/providers/configs/vercel.json b/internal/providers/configs/vercel.json
index 43b3b5facce3a868e8b39bcea2f05d7044f0e8a9..b56d4980b59c9616f91cab2801178714d9150dc9 100644
--- a/internal/providers/configs/vercel.json
+++ b/internal/providers/configs/vercel.json
@@ -51,8 +51,8 @@
       "name": "Claude 3.5 Sonnet (2024-06-20)",
       "cost_per_1m_in": 3,
       "cost_per_1m_out": 15,
-      "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_in_cached": 0.3,
+      "cost_per_1m_out_cached": 3.75,
       "context_window": 200000,
       "default_max_tokens": 8000,
       "can_reason": false,
@@ -334,11 +334,30 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "deepseek/deepseek-r1",
+      "name": "DeepSeek-R1",
+      "cost_per_1m_in": 1.35,
+      "cost_per_1m_out": 5.4,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 128000,
+      "default_max_tokens": 8000,
+      "can_reason": true,
+      "reasoning_levels": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "default_reasoning_effort": "medium",
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "deepseek/deepseek-v3.1",
       "name": "DeepSeek-V3.1",
-      "cost_per_1m_in": 0.21,
-      "cost_per_1m_out": 0.79,
+      "cost_per_1m_in": 0.5,
+      "cost_per_1m_out": 1.5,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 163840,
@@ -416,17 +435,11 @@
       "name": "GLM 4.5V",
       "cost_per_1m_in": 0.6,
       "cost_per_1m_out": 1.8,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in_cached": 0.11,
       "cost_per_1m_out_cached": 0,
-      "context_window": 65536,
+      "context_window": 66000,
       "default_max_tokens": 8000,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
+      "can_reason": false,
       "supports_attachments": true,
       "options": {}
     },
@@ -452,11 +465,11 @@
     {
       "id": "zai/glm-4.7",
       "name": "GLM 4.7",
-      "cost_per_1m_in": 0.43,
-      "cost_per_1m_out": 1.75,
-      "cost_per_1m_in_cached": 0.08,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 2.2,
+      "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 202752,
+      "context_window": 200000,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -509,9 +522,9 @@
     {
       "id": "zai/glm-5",
       "name": "GLM 5",
-      "cost_per_1m_in": 0.8,
-      "cost_per_1m_out": 2.56,
-      "cost_per_1m_in_cached": 0.16,
+      "cost_per_1m_in": 1,
+      "cost_per_1m_out": 3.2,
+      "cost_per_1m_in_cached": 0.2,
       "cost_per_1m_out_cached": 0,
       "context_window": 202800,
       "default_max_tokens": 8000,
@@ -530,9 +543,9 @@
       "name": "GLM-4.5",
       "cost_per_1m_in": 0.6,
       "cost_per_1m_out": 2.2,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in_cached": 0.11,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 128000,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -644,7 +657,7 @@
       "name": "GPT 5.1 Thinking",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0.13,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -663,7 +676,7 @@
       "name": "GPT 5.2",
       "cost_per_1m_in": 1.75,
       "cost_per_1m_out": 14,
-      "cost_per_1m_in_cached": 0.18,
+      "cost_per_1m_in_cached": 0.175,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -760,7 +773,7 @@
       "cost_per_1m_out": 15,
       "cost_per_1m_in_cached": 0.25,
       "cost_per_1m_out_cached": 0,
-      "context_window": 200000,
+      "context_window": 1050000,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -779,7 +792,7 @@
       "cost_per_1m_out": 180,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 200000,
+      "context_window": 1050000,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -835,7 +848,7 @@
       "name": "GPT-4.1 nano",
       "cost_per_1m_in": 0.1,
       "cost_per_1m_out": 0.4,
-      "cost_per_1m_in_cached": 0.03,
+      "cost_per_1m_in_cached": 0.025,
       "cost_per_1m_out_cached": 0,
       "context_window": 1047576,
       "default_max_tokens": 8000,
@@ -874,7 +887,7 @@
       "name": "GPT-5",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0.13,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -893,7 +906,7 @@
       "name": "GPT-5 mini",
       "cost_per_1m_in": 0.25,
       "cost_per_1m_out": 2,
-      "cost_per_1m_in_cached": 0.03,
+      "cost_per_1m_in_cached": 0.025,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -912,7 +925,7 @@
       "name": "GPT-5 nano",
       "cost_per_1m_in": 0.05,
       "cost_per_1m_out": 0.4,
-      "cost_per_1m_in_cached": 0.01,
+      "cost_per_1m_in_cached": 0.005,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -950,7 +963,7 @@
       "name": "GPT-5-Codex",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0.13,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -961,7 +974,7 @@
         "high"
       ],
       "default_reasoning_effort": "medium",
-      "supports_attachments": true,
+      "supports_attachments": false,
       "options": {}
     },
     {
@@ -969,7 +982,7 @@
       "name": "GPT-5.1 Instant",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0.13,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 128000,
       "default_max_tokens": 8000,
@@ -988,7 +1001,7 @@
       "name": "GPT-5.1-Codex",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0.13,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 400000,
       "default_max_tokens": 8000,
@@ -1021,12 +1034,38 @@
       "supports_attachments": true,
       "options": {}
     },
+    {
+      "id": "google/gemini-2.0-flash",
+      "name": "Gemini 2.0 Flash",
+      "cost_per_1m_in": 0.15,
+      "cost_per_1m_out": 0.6,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 1048576,
+      "default_max_tokens": 8000,
+      "can_reason": false,
+      "supports_attachments": true,
+      "options": {}
+    },
+    {
+      "id": "google/gemini-2.0-flash-lite",
+      "name": "Gemini 2.0 Flash Lite",
+      "cost_per_1m_in": 0.075,
+      "cost_per_1m_out": 0.3,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 1048576,
+      "default_max_tokens": 8000,
+      "can_reason": false,
+      "supports_attachments": true,
+      "options": {}
+    },
     {
       "id": "google/gemini-2.5-flash",
       "name": "Gemini 2.5 Flash",
       "cost_per_1m_in": 0.3,
       "cost_per_1m_out": 2.5,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in_cached": 0.03,
       "cost_per_1m_out_cached": 0,
       "context_window": 1000000,
       "default_max_tokens": 8000,
@@ -1037,7 +1076,7 @@
         "high"
       ],
       "default_reasoning_effort": "medium",
-      "supports_attachments": false,
+      "supports_attachments": true,
       "options": {}
     },
     {
@@ -1102,7 +1141,7 @@
       "name": "Gemini 2.5 Pro",
       "cost_per_1m_in": 1.25,
       "cost_per_1m_out": 10,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in_cached": 0.125,
       "cost_per_1m_out_cached": 0,
       "context_window": 1048576,
       "default_max_tokens": 8000,
@@ -1113,7 +1152,7 @@
         "high"
       ],
       "default_reasoning_effort": "medium",
-      "supports_attachments": false,
+      "supports_attachments": true,
       "options": {}
     },
     {
@@ -1381,8 +1420,8 @@
     {
       "id": "moonshotai/kimi-k2",
       "name": "Kimi K2",
-      "cost_per_1m_in": 0.5,
-      "cost_per_1m_out": 2,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 2.5,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
@@ -1391,14 +1430,27 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "moonshotai/kimi-k2-0905",
+      "name": "Kimi K2 0905",
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 2.5,
+      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 256000,
+      "default_max_tokens": 8000,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "moonshotai/kimi-k2-thinking",
       "name": "Kimi K2 Thinking",
-      "cost_per_1m_in": 0.47,
-      "cost_per_1m_out": 2,
-      "cost_per_1m_in_cached": 0.141,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 2.5,
+      "cost_per_1m_in_cached": 0.15,
       "cost_per_1m_out_cached": 0,
-      "context_window": 216144,
+      "context_window": 262114,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -1445,11 +1497,11 @@
     {
       "id": "moonshotai/kimi-k2.5",
       "name": "Kimi K2.5",
-      "cost_per_1m_in": 0.5,
-      "cost_per_1m_out": 2.8,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 3,
+      "cost_per_1m_in_cached": 0.1,
       "cost_per_1m_out_cached": 0,
-      "context_window": 256000,
+      "context_window": 262114,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -1464,11 +1516,11 @@
     {
       "id": "meta/llama-3.1-70b",
       "name": "Llama 3.1 70B Instruct",
-      "cost_per_1m_in": 0.4,
-      "cost_per_1m_out": 0.4,
+      "cost_per_1m_in": 0.72,
+      "cost_per_1m_out": 0.72,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 128000,
       "default_max_tokens": 8000,
       "can_reason": false,
       "supports_attachments": false,
@@ -1477,11 +1529,11 @@
     {
       "id": "meta/llama-3.1-8b",
       "name": "Llama 3.1 8B Instruct",
-      "cost_per_1m_in": 0.03,
-      "cost_per_1m_out": 0.05,
+      "cost_per_1m_in": 0.1,
+      "cost_per_1m_out": 0.1,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 128000,
       "default_max_tokens": 8000,
       "can_reason": false,
       "supports_attachments": false,
@@ -1529,11 +1581,11 @@
     {
       "id": "meta/llama-4-maverick",
       "name": "Llama 4 Maverick 17B Instruct",
-      "cost_per_1m_in": 0.15,
-      "cost_per_1m_out": 0.6,
+      "cost_per_1m_in": 0.24,
+      "cost_per_1m_out": 0.97,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 128000,
       "default_max_tokens": 8000,
       "can_reason": false,
       "supports_attachments": true,
@@ -1542,11 +1594,11 @@
     {
       "id": "meta/llama-4-scout",
       "name": "Llama 4 Scout 17B Instruct",
-      "cost_per_1m_in": 0.08,
-      "cost_per_1m_out": 0.3,
+      "cost_per_1m_in": 0.17,
+      "cost_per_1m_out": 0.66,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
+      "context_window": 128000,
       "default_max_tokens": 8000,
       "can_reason": false,
       "supports_attachments": true,
@@ -1619,9 +1671,9 @@
     {
       "id": "xiaomi/mimo-v2-flash",
       "name": "MiMo V2 Flash",
-      "cost_per_1m_in": 0.09,
-      "cost_per_1m_out": 0.29,
-      "cost_per_1m_in_cached": 0,
+      "cost_per_1m_in": 0.1,
+      "cost_per_1m_out": 0.3,
+      "cost_per_1m_in_cached": 0.02,
       "cost_per_1m_out_cached": 0,
       "context_window": 262144,
       "default_max_tokens": 8000,
@@ -1659,8 +1711,8 @@
       "name": "MiniMax M2.1",
       "cost_per_1m_in": 0.3,
       "cost_per_1m_out": 1.2,
-      "cost_per_1m_in_cached": 0.15,
-      "cost_per_1m_out_cached": 0,
+      "cost_per_1m_in_cached": 0.03,
+      "cost_per_1m_out_cached": 0.375,
       "context_window": 204800,
       "default_max_tokens": 8000,
       "can_reason": true,
@@ -1817,8 +1869,8 @@
     {
       "id": "nvidia/nemotron-nano-9b-v2",
       "name": "Nvidia Nemotron Nano 9B V2",
-      "cost_per_1m_in": 0.04,
-      "cost_per_1m_out": 0.16,
+      "cost_per_1m_in": 0.06,
+      "cost_per_1m_out": 0.23,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
       "context_window": 131072,
@@ -1862,11 +1914,11 @@
     {
       "id": "alibaba/qwen-3-32b",
       "name": "Qwen 3 32B",
-      "cost_per_1m_in": 0.1,
-      "cost_per_1m_out": 0.3,
+      "cost_per_1m_in": 0.29,
+      "cost_per_1m_out": 0.59,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 40960,
+      "context_window": 131072,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -1881,11 +1933,11 @@
     {
       "id": "alibaba/qwen3-coder-30b-a3b",
       "name": "Qwen 3 Coder 30B A3B Instruct",
-      "cost_per_1m_in": 0.07,
-      "cost_per_1m_out": 0.27,
+      "cost_per_1m_in": 0.15,
+      "cost_per_1m_out": 0.6,
       "cost_per_1m_in_cached": 0,
       "cost_per_1m_out_cached": 0,
-      "context_window": 160000,
+      "context_window": 262144,
       "default_max_tokens": 8000,
       "can_reason": true,
       "reasoning_levels": [
@@ -2012,6 +2064,19 @@
       "supports_attachments": false,
       "options": {}
     },
+    {
+      "id": "alibaba/qwen3-max",
+      "name": "Qwen3 Max",
+      "cost_per_1m_in": 1.2,
+      "cost_per_1m_out": 6,
+      "cost_per_1m_in_cached": 0.24,
+      "cost_per_1m_out_cached": 0,
+      "context_window": 262144,
+      "default_max_tokens": 8000,
+      "can_reason": false,
+      "supports_attachments": false,
+      "options": {}
+    },
     {
       "id": "alibaba/qwen3-max-preview",
       "name": "Qwen3 Max Preview",
@@ -2153,25 +2218,6 @@
       "supports_attachments": false,
       "options": {}
     },
-    {
-      "id": "openai/gpt-oss-120b",
-      "name": "gpt-oss-120b",
-      "cost_per_1m_in": 0.1,
-      "cost_per_1m_out": 0.5,
-      "cost_per_1m_in_cached": 0,
-      "cost_per_1m_out_cached": 0,
-      "context_window": 131072,
-      "default_max_tokens": 8000,
-      "can_reason": true,
-      "reasoning_levels": [
-        "low",
-        "medium",
-        "high"
-      ],
-      "default_reasoning_effort": "medium",
-      "supports_attachments": false,
-      "options": {}
-    },
     {
       "id": "openai/gpt-oss-20b",
       "name": "gpt-oss-20b",