@hyperspaceng/neural-ai 0.63.0 → 0.64.1

package/dist/models.generated.js

@@ -815,8 +815,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 131072,
+            contextWindow: 196608,
+            maxTokens: 98304,
         },
         "mistral.devstral-2-123b": {
             id: "mistral.devstral-2-123b",
@@ -1056,6 +1056,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "nvidia.nemotron-super-3-120b": {
+            id: "nvidia.nemotron-super-3-120b",
+            name: "NVIDIA Nemotron 3 Super 120B A12B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.65,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1444,8 +1461,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 101376,
         },
     },
     "anthropic": {
@@ -2284,6 +2301,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -3443,6 +3477,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "gemma-3-27b-it": {
+            id: "gemma-3-27b-it",
+            name: "Gemma 3 27B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
     },
     "google-antigravity": {
         "claude-opus-4-5-thinking": {
@@ -3908,6 +3959,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.1-pro-preview-customtools": {
+            id: "gemini-3.1-pro-preview-customtools",
+            name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
     },
     "groq": {
         "deepseek-r1-distill-llama-70b": {
@@ -3944,6 +4012,40 @@ export const MODELS = {
             contextWindow: 8192,
             maxTokens: 8192,
         },
+        "groq/compound": {
+            id: "groq/compound",
+            name: "Compound",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "groq/compound-mini": {
+            id: "groq/compound-mini",
+            name: "Compound Mini",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "llama-3.1-8b-instant": {
             id: "llama-3.1-8b-instant",
             name: "Llama 3.1 8B Instant",
@@ -4131,6 +4233,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "openai/gpt-oss-safeguard-20b": {
+            id: "openai/gpt-oss-safeguard-20b",
+            name: "Safety GPT OSS 20B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.037,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 65536,
+        },
         "qwen-qwq-32b": {
             id: "qwen-qwq-32b",
             name: "Qwen QwQ 32B",
@@ -4163,7 +4282,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 40960,
         },
     },
     "huggingface": {
@@ -4529,91 +4648,6 @@ export const MODELS = {
         },
     },
     "minimax": {
-        "MiniMax-M2": {
-            id: "MiniMax-M2",
-            name: "MiniMax-M2",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1": {
-            id: "MiniMax-M2.1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1-highspeed": {
-            id: "MiniMax-M2.1-highspeed",
-            name: "MiniMax-M2.1-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5": {
-            id: "MiniMax-M2.5",
-            name: "MiniMax-M2.5",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5-highspeed": {
-            id: "MiniMax-M2.5-highspeed",
-            name: "MiniMax-M2.5-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.06,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "MiniMax-M2.7": {
             id: "MiniMax-M2.7",
             name: "MiniMax-M2.7",
@@ -4650,91 +4684,6 @@ export const MODELS = {
         },
     },
     "minimax-cn": {
-        "MiniMax-M2": {
-            id: "MiniMax-M2",
-            name: "MiniMax-M2",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1": {
-            id: "MiniMax-M2.1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1-highspeed": {
-            id: "MiniMax-M2.1-highspeed",
-            name: "MiniMax-M2.1-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5": {
-            id: "MiniMax-M2.5",
-            name: "MiniMax-M2.5",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5-highspeed": {
-            id: "MiniMax-M2.5-highspeed",
-            name: "MiniMax-M2.5-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.06,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "MiniMax-M2.7": {
             id: "MiniMax-M2.7",
             name: "MiniMax-M2.7",
@@ -5094,22 +5043,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "mistral-small-2603": {
+            id: "mistral-small-2603",
+            name: "Mistral Small 4",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral-small-latest": {
             id: "mistral-small-latest",
             name: "Mistral Small (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.3,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "open-mistral-7b": {
             id: "open-mistral-7b",
@@ -5640,6 +5606,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -6559,12 +6542,29 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "nemotron-3-super-free": {
+            id: "nemotron-3-super-free",
+            name: "Nemotron 3 Super Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "nemotron-3-super-free": {
-            id: "nemotron-3-super-free",
-            name: "Nemotron 3 Super Free",
+        "qwen3.6-plus-free": {
+            id: "qwen3.6-plus-free",
+            name: "Qwen3.6 Plus Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -6576,8 +6576,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 1048576,
+            maxTokens: 64000,
         },
     },
     "opencode-go": {
@@ -7535,23 +7535,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3-pro-preview": {
-            id: "google/gemini-3-pro-preview",
-            name: "Google: Gemini 3 Pro Preview",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -7654,22 +7637,22 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 32000,
         },
-        "kwaipilot/kat-coder-pro": {
-            id: "kwaipilot/kat-coder-pro",
-            name: "Kwaipilot: KAT-Coder-Pro V1",
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kwaipilot: KAT-Coder-Pro V2",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.207,
-                output: 0.828,
-                cacheRead: 0.0414,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 128000,
+            maxTokens: 80000,
         },
         "meituan/longcat-flash-chat": {
             id: "meituan/longcat-flash-chat",
@@ -7867,9 +7850,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.17,
-                cacheRead: 0.09999999999999999,
+                input: 0.19,
+                output: 1.15,
+                cacheRead: 0.095,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -8198,23 +8181,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "mistralai/mistral-small-3.1-24b-instruct:free": {
-            id: "mistralai/mistral-small-3.1-24b-instruct:free",
-            name: "Mistral: Mistral Small 3.1 24B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "mistralai/mistral-small-3.2-24b-instruct": {
             id: "mistralai/mistral-small-3.2-24b-instruct",
             name: "Mistral: Mistral Small 3.2 24B",
@@ -8326,13 +8292,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 2.2,
+                input: 0.5700000000000001,
+                output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
         "moonshotai/kimi-k2-0905": {
             id: "moonshotai/kimi-k2-0905",
@@ -8394,8 +8360,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.27,
-                output: 1,
+                input: 0.135,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -8481,7 +8447,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.5,
-                cacheRead: 0.04,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9573,7 +9539,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32768,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "qwen/qwen-max": {
             id: "qwen/qwen-max",
@@ -9813,23 +9779,6 @@ export const MODELS = {
             contextWindow: 40960,
             maxTokens: 40960,
         },
-        "qwen/qwen3-4b:free": {
-            id: "qwen/qwen3-4b:free",
-            name: "Qwen: Qwen3 4B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 40960,
-            maxTokens: 4096,
-        },
         "qwen/qwen3-8b": {
             id: "qwen/qwen3-8b",
             name: "Qwen: Qwen3 8B",
@@ -10236,7 +10185,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -10272,6 +10221,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.6-plus-preview:free": {
+            id: "qwen/qwen3.6-plus-preview:free",
+            name: "Qwen: Qwen3.6 Plus Preview (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "qwen/qwq-32b": {
             id: "qwen/qwq-32b",
             name: "Qwen: QwQ 32B",
@@ -10289,6 +10255,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "reka/reka-edge": {
+            id: "reka/reka-edge",
+            name: "Reka Edge",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 16384,
+            maxTokens: 16384,
+        },
         "relace/relace-search": {
             id: "relace/relace-search",
             name: "Relace: Relace Search",
@@ -10351,11 +10334,11 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0.02,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "stepfun/step-3.5-flash:free": {
             id: "stepfun/step-3.5-flash:free",
@@ -10861,12 +10844,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
-                output: 0.463,
-                cacheRead: 0,
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 32768,
             maxTokens: 16384,
         },
         "alibaba/qwen-3-30b": {
@@ -10895,13 +10878,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.29,
-                output: 0.59,
-                cacheRead: 0.145,
+                input: 0.16,
+                output: 0.64,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 40960,
+            contextWindow: 128000,
+            maxTokens: 8192,
         },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10929,13 +10912,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.022,
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 66536,
+            maxTokens: 65536,
         },
         "alibaba/qwen3-coder-30b-a3b": {
             id: "alibaba/qwen3-coder-30b-a3b",
@@ -11405,13 +11388,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
+                input: 0.56,
+                output: 1.68,
+                cacheRead: 0.28,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -11651,6 +11634,23 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 16384,
         },
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kat Coder Pro V2",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "meituan/longcat-flash-chat": {
             id: "meituan/longcat-flash-chat",
             name: "LongCat Flash Chat",
@@ -11666,7 +11666,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 100000,
+            maxTokens: 8192,
         },
         "meituan/longcat-flash-thinking": {
             id: "meituan/longcat-flash-thinking",
@@ -11711,13 +11711,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.22,
+                output: 0.22,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta/llama-3.2-11b": {
             id: "meta/llama-3.2-11b",
@@ -11779,12 +11779,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.24,
-                output: 0.9700000000000001,
+                input: 0.35,
+                output: 1.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 524288,
             maxTokens: 8192,
         },
         "meta/llama-4-scout": {
@@ -12688,6 +12688,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "gpt-oss-20b",
@@ -12833,8 +12850,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 1,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12850,8 +12867,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13045,6 +13062,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "xai/grok-4.20-multi-agent": {
+            id: "xai/grok-4.20-multi-agent",
+            name: "Grok 4.20 Multi-Agent",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 2000000,
+        },
         "xai/grok-4.20-multi-agent-beta": {
             id: "xai/grok-4.20-multi-agent-beta",
             name: "Grok 4.20 Multi Agent Beta",
@@ -13062,6 +13096,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
+        "xai/grok-4.20-non-reasoning": {
+            id: "xai/grok-4.20-non-reasoning",
+            name: "Grok 4.20 Non-Reasoning",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 2000000,
+        },
         "xai/grok-4.20-non-reasoning-beta": {
             id: "xai/grok-4.20-non-reasoning-beta",
             name: "Grok 4.20 Beta Non-Reasoning",
@@ -13079,6 +13130,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
+        "xai/grok-4.20-reasoning": {
+            id: "xai/grok-4.20-reasoning",
+            name: "Grok 4.20 Reasoning",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 2000000,
+        },
         "xai/grok-4.20-reasoning-beta": {
             id: "xai/grok-4.20-reasoning-beta",
             name: "Grok 4.20 Beta Reasoning",
@@ -13122,9 +13190,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.02,
+                input: 0.09,
+                output: 0.29,
+                cacheRead: 0.045,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13260,7 +13328,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.2,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -13890,6 +13958,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-4.7-flashx": {
+            id: "glm-4.7-flashx",
+            name: "GLM-4.7-FlashX",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.4,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",