gsd-pi 2.42.0-dev.97e9e30 → 2.42.0-dev.eedc83f

package/packages/pi-ai/dist/models.generated.js

@@ -87,40 +87,6 @@ export const MODELS = {
             contextWindow: 300000,
             maxTokens: 8192,
         },
-        "amazon.titan-text-express-v1": {
-            id: "amazon.titan-text-express-v1",
-            name: "Titan Text G1 - Express",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "amazon.titan-text-express-v1:0:8k": {
-            id: "amazon.titan-text-express-v1:0:8k",
-            name: "Titan Text G1 - Express",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "anthropic.claude-3-5-haiku-20241022-v1:0": {
             id: "anthropic.claude-3-5-haiku-20241022-v1:0",
             name: "Claude Haiku 3.5",
@@ -206,40 +172,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
-        "anthropic.claude-3-opus-20240229-v1:0": {
-            id: "anthropic.claude-3-opus-20240229-v1:0",
-            name: "Claude Opus 3",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
-        "anthropic.claude-3-sonnet-20240229-v1:0": {
-            id: "anthropic.claude-3-sonnet-20240229-v1:0",
-            name: "Claude Sonnet 3",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
         "anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5",
@@ -322,7 +254,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -373,43 +305,9 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "cohere.command-r-plus-v1:0": {
-            id: "cohere.command-r-plus-v1:0",
-            name: "Command R+",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "cohere.command-r-v1:0": {
-            id: "cohere.command-r-v1:0",
-            name: "Command R",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "deepseek.r1-v1:0": {
             id: "deepseek.r1-v1:0",
             name: "DeepSeek-R1",
@@ -444,8 +342,8 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 81920,
         },
-        "deepseek.v3.2-v1:0": {
-            id: "deepseek.v3.2-v1:0",
+        "deepseek.v3.2": {
+            id: "deepseek.v3.2",
             name: "DeepSeek-V3.2",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
@@ -509,7 +407,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -560,7 +458,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -611,7 +509,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "global.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -662,7 +560,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "google.gemma-3-27b-it": {
@@ -699,6 +597,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "meta.llama3-1-405b-instruct-v1:0": {
+            id: "meta.llama3-1-405b-instruct-v1:0",
+            name: "Llama 3.1 405B Instruct",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2.4,
+                output: 2.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
         "meta.llama3-1-70b-instruct-v1:0": {
             id: "meta.llama3-1-70b-instruct-v1:0",
             name: "Llama 3.1 70B Instruct",
@@ -886,6 +801,40 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "mistral.devstral-2-123b": {
+            id: "mistral.devstral-2-123b",
+            name: "Devstral 2 123B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+        "mistral.magistral-small-2509": {
+            id: "mistral.magistral-small-2509",
+            name: "Magistral Small 1.2",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 40000,
+        },
         "mistral.ministral-3-14b-instruct": {
             id: "mistral.ministral-3-14b-instruct",
             name: "Ministral 14B 3.0",
@@ -903,6 +852,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "mistral.ministral-3-3b-instruct": {
+            id: "mistral.ministral-3-3b-instruct",
+            name: "Ministral 3 3B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
         "mistral.ministral-3-8b-instruct": {
             id: "mistral.ministral-3-8b-instruct",
             name: "Ministral 3 8B",
@@ -920,22 +886,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "mistral.mistral-large-2402-v1:0": {
-            id: "mistral.mistral-large-2402-v1:0",
-            name: "Mistral Large (24.02)",
+        "mistral.mistral-large-3-675b-instruct": {
+            id: "mistral.mistral-large-3-675b-instruct",
+            name: "Mistral Large 3",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.5,
                 output: 1.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+        "mistral.pixtral-large-2502-v1:0": {
+            id: "mistral.pixtral-large-2502-v1:0",
+            name: "Pixtral Large (25.02)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 8192,
         },
         "mistral.voxtral-mini-3b-2507": {
             id: "mistral.voxtral-mini-3b-2507",
@@ -1022,6 +1005,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "nvidia.nemotron-nano-3-30b": {
+            id: "nvidia.nemotron-nano-3-30b",
+            name: "NVIDIA Nemotron Nano 3 30B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.24,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
         "nvidia.nemotron-nano-9b-v2": {
             id: "nvidia.nemotron-nano-9b-v2",
             name: "NVIDIA Nemotron Nano 9B v2",
@@ -1291,7 +1291,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "us.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -1342,7 +1342,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "writer.palmyra-x4-v1:0": {
@@ -1718,23 +1718,6 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
-            maxTokens: 128000,
-        },
-        "claude-opus-4-6[1m]": {
-            id: "claude-opus-4-6[1m]",
-            name: "Claude Opus 4.6 (1M)",
-            api: "anthropic-messages",
-            provider: "anthropic",
-            baseUrl: "https://api.anthropic.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
             contextWindow: 1000000,
             maxTokens: 128000,
         },
@@ -1820,216 +1803,44 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
     },
-    "anthropic-vertex": {
-        "claude-opus-4-6": {
-            id: "claude-opus-4-6",
-            name: "Claude Opus 4.6 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
+    "azure-openai-responses": {
+        "codex-mini-latest": {
+            id: "codex-mini-latest",
+            name: "Codex Mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
+                input: 1.5,
+                output: 6,
+                cacheRead: 0.375,
+                cacheWrite: 0,
             },
             contextWindow: 200000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
-        "claude-opus-4-6[1m]": {
-            id: "claude-opus-4-6[1m]",
-            name: "Claude Opus 4.6 1M (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
+        "gpt-4": {
+            id: "gpt-4",
+            name: "GPT-4",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text"],
             cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
+                input: 30,
+                output: 60,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
-        "claude-sonnet-4-6": {
-            id: "claude-sonnet-4-6",
-            name: "Claude Sonnet 4.6 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-sonnet-4-6[1m]": {
-            id: "claude-sonnet-4-6[1m]",
-            name: "Claude Sonnet 4.6 1M (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 1000000,
-            maxTokens: 64000,
-        },
-        "claude-sonnet-4-5@20250929": {
-            id: "claude-sonnet-4-5@20250929",
-            name: "Claude Sonnet 4.5 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-sonnet-4@20250514": {
-            id: "claude-sonnet-4@20250514",
-            name: "Claude Sonnet 4 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-opus-4-5@20251101": {
-            id: "claude-opus-4-5@20251101",
-            name: "Claude Opus 4.5 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "claude-opus-4-1@20250805": {
-            id: "claude-opus-4-1@20250805",
-            name: "Claude Opus 4.1 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "claude-opus-4@20250514": {
-            id: "claude-opus-4@20250514",
-            name: "Claude Opus 4 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "claude-haiku-4-5@20251001": {
-            id: "claude-haiku-4-5@20251001",
-            name: "Claude Haiku 4.5 (Vertex)",
-            api: "anthropic-vertex",
-            provider: "anthropic-vertex",
-            baseUrl: "https://us-central1-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-    },
-    "azure-openai-responses": {
-        "codex-mini-latest": {
-            id: "codex-mini-latest",
-            name: "Codex Mini",
-            api: "azure-openai-responses",
-            provider: "azure-openai-responses",
-            baseUrl: "",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.5,
-                output: 6,
-                cacheRead: 0.375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "gpt-4": {
-            id: "gpt-4",
-            name: "GPT-4",
-            api: "azure-openai-responses",
-            provider: "azure-openai-responses",
-            baseUrl: "",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 30,
-                output: 60,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 8192,
+            maxTokens: 8192,
         },
         "gpt-4-turbo": {
             id: "gpt-4-turbo",
@@ -2490,6 +2301,40 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "gpt-5.4-pro": {
             id: "gpt-5.4-pro",
             name: "GPT-5.4 Pro",
@@ -2730,7 +2575,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 144000,
             maxTokens: 32000,
         },
         "claude-opus-4.5": {
@@ -2748,7 +2593,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 160000,
             maxTokens: 32000,
         },
         "claude-opus-4.6": {
@@ -2766,7 +2611,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 144000,
             maxTokens: 64000,
         },
         "claude-sonnet-4": {
@@ -2784,7 +2629,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 216000,
             maxTokens: 16000,
         },
         "claude-sonnet-4.5": {
@@ -2802,7 +2647,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 144000,
             maxTokens: 32000,
         },
         "claude-sonnet-4.6": {
@@ -2820,7 +2665,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "gemini-2.5-pro": {
@@ -2915,7 +2760,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
+            contextWindow: 128000,
             maxTokens: 16384,
         },
         "gpt-4o": {
@@ -2934,8 +2779,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
-            maxTokens: 16384,
+            contextWindow: 128000,
+            maxTokens: 4096,
         },
         "gpt-5": {
             id: "gpt-5",
@@ -2970,7 +2815,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 264000,
             maxTokens: 64000,
         },
         "gpt-5.1": {
@@ -2988,7 +2833,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 264000,
             maxTokens: 64000,
         },
         "gpt-5.1-codex": {
@@ -3006,7 +2851,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
         "gpt-5.1-codex-max": {
@@ -3024,7 +2869,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
         "gpt-5.1-codex-mini": {
@@ -3042,7 +2887,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
         "gpt-5.2": {
@@ -3060,7 +2905,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 264000,
             maxTokens: 64000,
         },
         "gpt-5.2-codex": {
@@ -3078,7 +2923,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
         "gpt-5.3-codex": {
@@ -3117,6 +2962,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -3436,10 +3299,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 1,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -4700,6 +4563,40 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "MiniMax-M2.7": {
+            id: "MiniMax-M2.7",
+            name: "MiniMax-M2.7",
+            api: "anthropic-messages",
+            provider: "minimax",
+            baseUrl: "https://api.minimax.io/anthropic",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "MiniMax-M2.7-highspeed": {
+            id: "MiniMax-M2.7-highspeed",
+            name: "MiniMax-M2.7-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-cn": {
         "MiniMax-M2": {
@@ -4770,11 +4667,45 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "MiniMax-M2.7": {
+            id: "MiniMax-M2.7",
+            name: "MiniMax-M2.7",
+            api: "anthropic-messages",
+            provider: "minimax-cn",
+            baseUrl: "https://api.minimaxi.com/anthropic",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "MiniMax-M2.7-highspeed": {
+            id: "MiniMax-M2.7-highspeed",
+            name: "MiniMax-M2.7-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,
+        },
     },
     "mistral": {
         "codestral-latest": {
             id: "codestral-latest",
-            name: "Codestral",
+            name: "Codestral (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -4825,7 +4756,7 @@ export const MODELS = {
         },
         "devstral-medium-latest": {
             id: "devstral-medium-latest",
-            name: "Devstral 2",
+            name: "Devstral 2 (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -4893,7 +4824,7 @@ export const MODELS = {
         },
         "magistral-medium-latest": {
             id: "magistral-medium-latest",
-            name: "Magistral Medium",
+            name: "Magistral Medium (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -4927,7 +4858,7 @@ export const MODELS = {
         },
         "ministral-3b-latest": {
             id: "ministral-3b-latest",
-            name: "Ministral 3B",
+            name: "Ministral 3B (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -4944,7 +4875,7 @@ export const MODELS = {
         },
         "ministral-8b-latest": {
             id: "ministral-8b-latest",
-            name: "Ministral 8B",
+            name: "Ministral 8B (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -4995,7 +4926,7 @@ export const MODELS = {
         },
         "mistral-large-latest": {
             id: "mistral-large-latest",
-            name: "Mistral Large",
+            name: "Mistral Large (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -5046,7 +4977,7 @@ export const MODELS = {
         },
         "mistral-medium-latest": {
             id: "mistral-medium-latest",
-            name: "Mistral Medium",
+            name: "Mistral Medium (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -5097,7 +5028,7 @@ export const MODELS = {
         },
         "mistral-small-latest": {
             id: "mistral-small-latest",
-            name: "Mistral Small",
+            name: "Mistral Small (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -5182,7 +5113,7 @@ export const MODELS = {
         },
         "pixtral-large-latest": {
             id: "pixtral-large-latest",
-            name: "Pixtral Large",
+            name: "Pixtral Large (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -5692,6 +5623,40 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "gpt-5.4-pro": {
             id: "gpt-5.4-pro",
             name: "GPT-5.4 Pro",
@@ -6084,7 +6049,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "claude-sonnet-4": {
@@ -6155,23 +6120,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro": {
-            id: "gemini-3-pro",
-            name: "Gemini 3 Pro",
-            api: "google-generative-ai",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-3.1-pro": {
             id: "gemini-3.1-pro",
             name: "Gemini 3.1 Pro Preview",
@@ -6189,40 +6137,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "glm-4.6": {
-            id: "glm-4.6",
-            name: "GLM-4.6",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "glm-4.7": {
-            id: "glm-4.7",
-            name: "GLM-4.7",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -6427,6 +6341,40 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 Mini",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 Nano",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "gpt-5.4-pro": {
             id: "gpt-5.4-pro",
             name: "GPT-5.4 Pro",
@@ -6461,22 +6409,39 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "minimax-m2.1": {
-            id: "minimax-m2.1",
-            name: "MiniMax M2.1",
+        "mimo-v2-omni-free": {
+            id: "mimo-v2-omni-free",
+            name: "MiMo V2 Omni Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 64000,
+        },
+        "mimo-v2-pro-free": {
+            id: "mimo-v2-pro-free",
+            name: "MiMo V2 Pro Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.1,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 1048576,
+            maxTokens: 64000,
         },
         "minimax-m2.5": {
             id: "minimax-m2.5",
@@ -6512,6 +6477,23 @@ export const MODELS = {
             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,
+        },
     },
     "opencode-go": {
         "glm-5": {
@@ -6565,6 +6547,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "minimax-m2.7": {
+            id: "minimax-m2.7",
+            name: "MiniMax M2.7",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -7077,6 +7076,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "bytedance-seed/seed-2.0-lite": {
+            id: "bytedance-seed/seed-2.0-lite",
+            name: "ByteDance Seed: Seed-2.0-Lite",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "bytedance-seed/seed-2.0-mini": {
             id: "bytedance-seed/seed-2.0-mini",
             name: "ByteDance Seed: Seed-2.0-Mini",
@@ -7156,11 +7172,11 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.77,
-                cacheRead: 0.13,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 163840,
+            maxTokens: 4096,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -7230,23 +7246,6 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 4096,
         },
-        "deepseek/deepseek-v3.1-terminus:exacto": {
-            id: "deepseek/deepseek-v3.1-terminus:exacto",
-            name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.21,
-                output: 0.7899999999999999,
-                cacheRead: 0.16799999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 4096,
-        },
         "deepseek/deepseek-v3.2": {
             id: "deepseek/deepseek-v3.2",
             name: "DeepSeek: DeepSeek V3.2",
@@ -7256,13 +7255,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.39999999999999997,
-                cacheRead: 0,
+                input: 0.26,
+                output: 0.38,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 4096,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -7519,40 +7518,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemma-3-27b-it": {
-            id: "google/gemma-3-27b-it",
-            name: "Google: Gemma 3 27B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.04,
-                output: 0.15,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 65536,
-        },
-        "google/gemma-3-27b-it:free": {
-            id: "google/gemma-3-27b-it:free",
-            name: "Google: Gemma 3 27B (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: 131072,
-            maxTokens: 8192,
-        },
         "inception/mercury": {
             id: "inception/mercury",
             name: "Inception: Mercury",
@@ -7655,23 +7620,6 @@ export const MODELS = {
             contextWindow: 8192,
             maxTokens: 16384,
         },
-        "meta-llama/llama-3.1-405b-instruct": {
-            id: "meta-llama/llama-3.1-405b-instruct",
-            name: "Meta: Llama 3.1 405B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 4,
-                output: 4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 4096,
-        },
         "meta-llama/llama-3.1-70b-instruct": {
             id: "meta-llama/llama-3.1-70b-instruct",
             name: "Meta: Llama 3.1 70B Instruct",
@@ -7737,8 +7685,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 128000,
+            contextWindow: 65536,
+            maxTokens: 4096,
         },
         "meta-llama/llama-4-maverick": {
             id: "meta-llama/llama-4-maverick",
@@ -7834,28 +7782,62 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.295,
-                output: 1.2,
-                cacheRead: 0.03,
+                input: 0.19999999999999998,
+                output: 1.17,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 196608,
+            maxTokens: 65536,
         },
-        "mistralai/codestral-2508": {
-            id: "mistralai/codestral-2508",
-            name: "Mistral: Codestral 2508",
+        "minimax/minimax-m2.5:free": {
+            id: "minimax/minimax-m2.5:free",
+            name: "MiniMax: MiniMax M2.5 (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 0.8999999999999999,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
+        "minimax/minimax-m2.7": {
+            id: "minimax/minimax-m2.7",
+            name: "MiniMax: MiniMax M2.7",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "mistralai/codestral-2508": {
+            id: "mistralai/codestral-2508",
+            name: "Mistral: Codestral 2508",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 0.8999999999999999,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
             contextWindow: 256000,
             maxTokens: 4096,
         },
@@ -7870,7 +7852,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7887,7 +7869,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7904,7 +7886,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7921,7 +7903,7 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.19999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7938,7 +7920,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7955,7 +7937,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.15,
-                cacheRead: 0,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7972,7 +7954,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -7989,7 +7971,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8006,7 +7988,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8023,7 +8005,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 1.5,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -8040,7 +8022,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8057,7 +8039,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8091,7 +8073,7 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 32768,
@@ -8114,6 +8096,23 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 16384,
         },
+        "mistralai/mistral-small-2603": {
+            id: "mistralai/mistral-small-2603",
+            name: "Mistral: Mistral Small 4",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            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)",
@@ -8140,13 +8139,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.06,
-                output: 0.18,
-                cacheRead: 0.03,
+                input: 0.075,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 128000,
+            maxTokens: 4096,
         },
         "mistralai/mistral-small-creative": {
             id: "mistralai/mistral-small-creative",
@@ -8159,7 +8158,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 32768,
@@ -8176,7 +8175,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 65536,
@@ -8210,7 +8209,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8227,7 +8226,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 32000,
@@ -8267,23 +8266,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
-        "moonshotai/kimi-k2-0905:exacto": {
-            id: "moonshotai/kimi-k2-0905:exacto",
-            name: "MoonshotAI: Kimi K2 0905 (exacto)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 4096,
-        },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
             name: "MoonshotAI: Kimi K2 Thinking",
@@ -8403,6 +8385,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "NVIDIA: Nemotron 3 Super",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.5,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
+        "nvidia/nemotron-3-super-120b-a12b:free": {
+            id: "nvidia/nemotron-3-super-120b-a12b:free",
+            name: "NVIDIA: Nemotron 3 Super (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: 262144,
+            maxTokens: 262144,
+        },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
             id: "nvidia/nemotron-nano-12b-v2-vl:free",
             name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -9100,6 +9116,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-mini": {
+            id: "openai/gpt-5.4-mini",
+            name: "OpenAI: GPT-5.4 Mini",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.4-nano": {
+            id: "openai/gpt-5.4-nano",
+            name: "OpenAI: GPT-5.4 Nano",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "OpenAI: GPT-5.4 Pro",
@@ -9134,23 +9184,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
-        "openai/gpt-oss-120b:exacto": {
-            id: "openai/gpt-oss-120b:exacto",
-            name: "OpenAI: gpt-oss-120b (exacto)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.039,
-                output: 0.19,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "openai/gpt-oss-120b:free": {
             id: "openai/gpt-oss-120b:free",
             name: "OpenAI: gpt-oss-120b (free)",
@@ -9178,12 +9211,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.03,
-                output: 0.14,
-                cacheRead: 0,
+                output: 0.11,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -9225,7 +9258,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 15,
@@ -9276,7 +9309,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.1,
@@ -9293,7 +9326,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.1,
@@ -9483,9 +9516,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.2,
-                cacheRead: 0.08,
+                input: 0.26,
+                output: 0.78,
+                cacheRead: 0.052000000000000005,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -9551,8 +9584,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
-                output: 3.1999999999999997,
+                input: 0.52,
+                output: 2.08,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9619,13 +9652,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.11,
-                output: 0.6,
-                cacheRead: 0.055,
+                input: 0.14950000000000002,
+                output: 1.495,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -9670,13 +9703,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.051,
-                output: 0.33999999999999997,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.39999999999999997,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
         "qwen/qwen3-32b": {
             id: "qwen/qwen3-32b",
@@ -9814,23 +9847,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwen3-coder:exacto": {
-            id: "qwen/qwen3-coder:exacto",
-            name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.22,
-                output: 1.7999999999999998,
-                cacheRead: 0.022,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "qwen/qwen3-coder:free": {
             id: "qwen/qwen3-coder:free",
             name: "Qwen: Qwen3 Coder 480B A35B (free)",
@@ -9857,9 +9873,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 1.2,
-                output: 6,
-                cacheRead: 0.24,
+                input: 0.78,
+                output: 3.9,
+                cacheRead: 0.156,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9925,13 +9941,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 1.2,
+                input: 0.0975,
+                output: 0.78,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -9959,8 +9975,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.26,
+                output: 2.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9993,8 +10009,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.13,
+                output: 1.56,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10120,6 +10136,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen/qwen3.5-9b": {
+            id: "qwen/qwen3.5-9b",
+            name: "Qwen: Qwen3.5-9B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 4096,
+        },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
             name: "Qwen: Qwen3.5-Flash",
@@ -10129,8 +10162,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.065,
+                output: 0.26,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10164,12 +10197,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.15,
-                output: 0.39999999999999997,
+                output: 0.58,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 32768,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
         "relace/relace-search": {
             id: "relace/relace-search",
@@ -10214,13 +10247,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.65,
-                output: 0.75,
+                input: 0.85,
+                output: 0.85,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 32768,
+            contextWindow: 131072,
+            maxTokens: 16384,
         },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
@@ -10299,9 +10332,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.85,
-                cacheRead: 0.125,
+                input: 0.3,
+                output: 1.1,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -10443,6 +10476,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "x-ai/grok-4.20-beta": {
+            id: "x-ai/grok-4.20-beta",
+            name: "xAI: Grok 4.20 Beta",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 4096,
+        },
         "x-ai/grok-code-fast-1": {
             id: "x-ai/grok-code-fast-1",
             name: "xAI: Grok Code Fast 1",
@@ -10477,6 +10527,40 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "xiaomi/mimo-v2-omni": {
+            id: "xiaomi/mimo-v2-omni",
+            name: "Xiaomi: MiMo-V2-Omni",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "xiaomi/mimo-v2-pro": {
+            id: "xiaomi/mimo-v2-pro",
+            name: "Xiaomi: MiMo-V2-Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
             name: "Z.ai: GLM 4 32B ",
@@ -10579,23 +10663,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 204800,
         },
-        "z-ai/glm-4.6:exacto": {
-            id: "z-ai/glm-4.6:exacto",
-            name: "Z.ai: GLM 4.6 (exacto)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.44,
-                output: 1.76,
-                cacheRead: 0.11,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "z-ai/glm-4.6v": {
             id: "z-ai/glm-4.6v",
             name: "Z.ai: GLM 4.6V",
@@ -10622,13 +10689,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.38,
-                output: 1.9800000000000002,
-                cacheRead: 0.19,
+                input: 0.39,
+                output: 1.75,
+                cacheRead: 0.195,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 65535,
         },
         "z-ai/glm-4.7-flash": {
             id: "z-ai/glm-4.7-flash",
@@ -10661,8 +10728,25 @@ export const MODELS = {
                 cacheRead: 0.119,
                 cacheWrite: 0,
             },
+            contextWindow: 80000,
+            maxTokens: 131072,
+        },
+        "z-ai/glm-5-turbo": {
+            id: "z-ai/glm-5-turbo",
+            name: "Z.ai: GLM 5 Turbo",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.96,
+                output: 3.1999999999999997,
+                cacheRead: 0.192,
+                cacheWrite: 0,
+            },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
     },
     "vercel-ai-gateway": {
@@ -10675,7 +10759,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.12,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10726,13 +10810,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
+                input: 0.29,
+                output: 0.59,
+                cacheRead: 0.145,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 40960,
         },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10743,9 +10827,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.9000000000000004,
-                cacheRead: 0,
+                input: 0.22999999999999998,
+                output: 2.3,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262114,
@@ -10762,7 +10846,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 1.5999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10777,13 +10861,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.27,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 160000,
-            maxTokens: 32768,
+            contextWindow: 262144,
+            maxTokens: 8192,
         },
         "alibaba/qwen3-coder-next": {
             id: "alibaba/qwen3-coder-next",
@@ -10791,7 +10875,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.5,
@@ -10819,6 +10903,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "alibaba/qwen3-max": {
+            id: "alibaba/qwen3-max",
+            name: "Qwen3 Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 1.2,
+                output: 6,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "alibaba/qwen3-max-preview": {
             id: "alibaba/qwen3-max-preview",
             name: "Qwen3 Max Preview",
@@ -10966,8 +11067,8 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
             contextWindow: 200000,
             maxTokens: 8192,
@@ -11176,6 +11277,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 8000,
         },
+        "deepseek/deepseek-r1": {
+            id: "deepseek/deepseek-r1",
+            name: "DeepSeek-R1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.35,
+                output: 5.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
         "deepseek/deepseek-v3": {
             id: "deepseek/deepseek-v3",
             name: "DeepSeek V3 0324",
@@ -11202,13 +11320,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.21,
-                output: 0.7899999999999999,
+                input: 0.5,
+                output: 1.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 128000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -11221,7 +11339,7 @@ export const MODELS = {
             cost: {
                 input: 0.27,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -11236,9 +11354,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.28,
+                output: 0.42,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11261,72 +11379,72 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
-        "google/gemini-2.5-flash": {
-            id: "google/gemini-2.5-flash",
-            name: "Gemini 2.5 Flash",
+        "google/gemini-2.0-flash": {
+            id: "google/gemini-2.0-flash",
+            name: "Gemini 2.0 Flash",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
+            reasoning: false,
+            input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 65536,
+            contextWindow: 1048576,
+            maxTokens: 8192,
         },
-        "google/gemini-2.5-flash-lite": {
-            id: "google/gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite",
+        "google/gemini-2.0-flash-lite": {
+            id: "google/gemini-2.0-flash-lite",
+            name: "Gemini 2.0 Flash Lite",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.01,
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 8192,
         },
-        "google/gemini-2.5-flash-lite-preview-09-2025": {
-            id: "google/gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-2025",
+        "google/gemini-2.5-flash": {
+            id: "google/gemini-2.5-flash",
+            name: "Gemini 2.5 Flash",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.01,
+                input: 0.3,
+                output: 2.5,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "google/gemini-2.5-flash-preview-09-2025": {
-            id: "google/gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-2025",
+        "google/gemini-2.5-flash-lite": {
+            id: "google/gemini-2.5-flash-lite",
+            name: "Gemini 2.5 Flash Lite",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.03,
+                input: 0.09999999999999999,
+                output: 0.39999999999999997,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "google/gemini-2.5-pro": {
@@ -11336,11 +11454,11 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11361,7 +11479,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65000,
         },
         "google/gemini-3-pro-preview": {
             id: "google/gemini-3-pro-preview",
@@ -11463,7 +11581,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 100000,
         },
         "meituan/longcat-flash-thinking": {
             id: "meituan/longcat-flash-thinking",
@@ -11491,13 +11609,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.72,
+                output: 0.72,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 16384,
+            contextWindow: 128000,
+            maxTokens: 8192,
         },
         "meta/llama-3.1-8b": {
             id: "meta/llama-3.1-8b",
@@ -11508,12 +11626,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.03,
-                output: 0.049999999999999996,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 128000,
             maxTokens: 16384,
         },
         "meta/llama-3.2-11b": {
@@ -11576,12 +11694,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.24,
+                output: 0.9700000000000001,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 128000,
             maxTokens: 8192,
         },
         "meta/llama-4-scout": {
@@ -11593,12 +11711,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
-                output: 0.3,
+                input: 0.16999999999999998,
+                output: 0.66,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 128000,
             maxTokens: 8192,
         },
         "minimax/minimax-m2": {
@@ -11629,8 +11747,8 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.15,
-                cacheWrite: 0,
+                cacheRead: 0.03,
+                cacheWrite: 0.375,
             },
             contextWindow: 204800,
             maxTokens: 131072,
@@ -11683,8 +11801,42 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0.375,
             },
-            contextWindow: 4096,
-            maxTokens: 4096,
+            contextWindow: 204800,
+            maxTokens: 131000,
+        },
+        "minimax/minimax-m2.7": {
+            id: "minimax/minimax-m2.7",
+            name: "Minimax M2.7",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 204800,
+            maxTokens: 131000,
+        },
+        "minimax/minimax-m2.7-highspeed": {
+            id: "minimax/minimax-m2.7-highspeed",
+            name: "MiniMax M2.7 High Speed",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.06,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 204800,
+            maxTokens: 131100,
         },
         "mistral/codestral": {
             id: "mistral/codestral",
@@ -11712,8 +11864,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.39999999999999997,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11746,8 +11898,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.09999999999999999,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11763,8 +11915,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.04,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11780,8 +11932,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.15,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11865,14 +12017,31 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "moonshotai/kimi-k2-0905": {
+            id: "moonshotai/kimi-k2-0905",
+            name: "Kimi K2 0905",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
             name: "Kimi K2 Thinking",
@@ -11882,13 +12051,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.47,
-                output: 2,
-                cacheRead: 0.14100000000000001,
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 216144,
-            maxTokens: 216144,
+            contextWindow: 262114,
+            maxTokens: 262114,
         },
         "moonshotai/kimi-k2-thinking-turbo": {
             id: "moonshotai/kimi-k2-thinking-turbo",
@@ -11916,9 +12085,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 2.4,
-                output: 10,
-                cacheRead: 0,
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -11933,13 +12102,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2.8,
-                cacheRead: 0,
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262114,
+            maxTokens: 262114,
         },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
@@ -11967,31 +12136,14 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.16,
+                input: 0.06,
+                output: 0.22999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/codex-mini": {
-            id: "openai/codex-mini",
-            name: "Codex Mini",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.5,
-                output: 6,
-                cacheRead: 0.375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/gpt-4-turbo": {
             id: "openai/gpt-4-turbo",
             name: "GPT-4 Turbo",
@@ -12054,7 +12206,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -12105,7 +12257,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12135,11 +12287,11 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12156,7 +12308,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12173,7 +12325,7 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.39999999999999997,
-                cacheRead: 0.01,
+                cacheRead: 0.005,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12207,7 +12359,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12258,7 +12410,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -12275,7 +12427,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12292,7 +12444,7 @@ export const MODELS = {
             cost: {
                 input: 1.75,
                 output: 14,
-                cacheRead: 0.18,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12397,42 +12549,59 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
+            contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-pro": {
-            id: "openai/gpt-5.4-pro",
-            name: "GPT 5.4 Pro",
+        "openai/gpt-5.4-mini": {
+            id: "openai/gpt-5.4-mini",
+            name: "GPT 5.4 Mini",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 30,
-                output: 180,
-                cacheRead: 0,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-oss-120b": {
-            id: "openai/gpt-oss-120b",
-            name: "gpt-oss-120b",
+        "openai/gpt-5.4-nano": {
+            id: "openai/gpt-5.4-nano",
+            name: "GPT 5.4 Nano",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.5,
+                input: 0.19999999999999998,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.4-pro": {
+            id: "openai/gpt-5.4-pro",
+            name: "GPT 5.4 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 1050000,
+            maxTokens: 128000,
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
@@ -12621,40 +12790,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "vercel/v0-1.0-md": {
-            id: "vercel/v0-1.0-md",
-            name: "v0-1.0-md",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32000,
-        },
-        "vercel/v0-1.5-md": {
-            id: "vercel/v0-1.5-md",
-            name: "v0-1.5-md",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "xai/grok-2-vision": {
             id: "xai/grok-2-vision",
             name: "Grok 2 Vision",
@@ -12683,7 +12818,7 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
+                cacheRead: 0.75,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12700,7 +12835,7 @@ export const MODELS = {
             cost: {
                 input: 5,
                 output: 25,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12717,7 +12852,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.5,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12751,7 +12886,7 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
+                cacheRead: 0.75,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -12825,6 +12960,57 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "xai/grok-4.20-multi-agent-beta": {
+            id: "xai/grok-4.20-multi-agent-beta",
+            name: "Grok 4.20 Multi Agent Beta",
+            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-non-reasoning-beta": {
+            id: "xai/grok-4.20-non-reasoning-beta",
+            name: "Grok 4.20 Beta 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-reasoning-beta": {
+            id: "xai/grok-4.20-reasoning-beta",
+            name: "Grok 4.20 Beta 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-code-fast-1": {
             id: "xai/grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -12851,17 +13037,34 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.29,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 32000,
         },
-        "zai/glm-4.5": {
-            id: "zai/glm-4.5",
-            name: "GLM-4.5",
+        "xiaomi/mimo-v2-pro": {
+            id: "xiaomi/mimo-v2-pro",
+            name: "MiMo V2 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "zai/glm-4.5": {
+            id: "zai/glm-4.5",
+            name: "GLM-4.5",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -12870,11 +13073,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.2,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 128000,
+            maxTokens: 96000,
         },
         "zai/glm-4.5-air": {
             id: "zai/glm-4.5-air",
@@ -12899,16 +13102,16 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
                 input: 0.6,
                 output: 1.7999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
-            contextWindow: 65536,
-            maxTokens: 16384,
+            contextWindow: 66000,
+            maxTokens: 16000,
         },
         "zai/glm-4.6": {
             id: "zai/glm-4.6",
@@ -12919,8 +13122,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.44999999999999996,
-                output: 1.7999999999999998,
+                input: 0.6,
+                output: 2.2,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },
@@ -12970,14 +13173,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.43,
-                output: 1.75,
-                cacheRead: 0.08,
+                input: 0.6,
+                output: 2.2,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 200000,
             maxTokens: 120000,
         },
+        "zai/glm-4.7-flash": {
+            id: "zai/glm-4.7-flash",
+            name: "GLM 4.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131000,
+        },
         "zai/glm-4.7-flashx": {
             id: "zai/glm-4.7-flashx",
             name: "GLM 4.7 FlashX",
@@ -12997,7 +13217,7 @@ export const MODELS = {
         },
         "zai/glm-5": {
             id: "zai/glm-5",
-            name: "GLM-5",
+            name: "GLM 5",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -13010,7 +13230,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202800,
-            maxTokens: 131072,
+            maxTokens: 131100,
+        },
+        "zai/glm-5-turbo": {
+            id: "zai/glm-5-turbo",
+            name: "GLM 5 Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 131100,
         },
     },
     "xai": {
@@ -13337,6 +13574,40 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "grok-4.20-0309-non-reasoning": {
+            id: "grok-4.20-0309-non-reasoning",
+            name: "Grok 4.20 (Non-Reasoning)",
+            api: "openai-completions",
+            provider: "xai",
+            baseUrl: "https://api.x.ai/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 30000,
+        },
+        "grok-4.20-0309-reasoning": {
+            id: "grok-4.20-0309-reasoning",
+            name: "Grok 4.20 (Reasoning)",
+            api: "openai-completions",
+            provider: "xai",
+            baseUrl: "https://api.x.ai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 30000,
+        },
         "grok-beta": {
             id: "grok-beta",
             name: "Grok Beta",
@@ -13552,748 +13823,24 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-    },
-    "alibaba-coding-plan": {
-        "qwen3.5-plus": {
-            id: "qwen3.5-plus",
-            name: "Qwen3.5 Plus",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 983616,
-            maxTokens: 65536,
-            compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-        },
-        "qwen3-max-2026-01-23": {
-            id: "qwen3-max-2026-01-23",
-            name: "Qwen3 Max 2026-01-23",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 258048,
-            maxTokens: 32768,
-            compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-        },
-        "qwen3-coder-next": {
-            id: "qwen3-coder-next",
-            name: "Qwen3 Coder Next",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 65536,
-            compat: { supportsDeveloperRole: false },
-        },
-        "qwen3-coder-plus": {
-            id: "qwen3-coder-plus",
-            name: "Qwen3 Coder Plus",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 997952,
-            maxTokens: 65536,
-            compat: { supportsDeveloperRole: false },
-        },
-        "MiniMax-M2.5": {
-            id: "MiniMax-M2.5",
-            name: "MiniMax M2.5",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 196608,
-            maxTokens: 65536,
-            compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: true, maxTokensField: "max_tokens" },
-        },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM-5",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 16384,
-            compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-        },
-        "glm-4.7": {
-            id: "glm-4.7",
-            name: "GLM-4.7",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 169984,
-            maxTokens: 16384,
-            compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-        },
-        "kimi-k2.5": {
-            id: "kimi-k2.5",
-            name: "Kimi K2.5",
-            api: "openai-completions",
-            provider: "alibaba-coding-plan",
-            baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 258048,
-            maxTokens: 32768,
-            compat: { thinkingFormat: "zai", supportsDeveloperRole: false },
-        },
-    },
-    "ollama-cloud": {
-        "cogito-2.1:671b": {
-            id: "cogito-2.1:671b",
-            name: "Cogito 2.1 671B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 32000,
-        },
-        "deepseek-v3.1:671b": {
-            id: "deepseek-v3.1:671b",
-            name: "DeepSeek V3.1 671B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
-        "deepseek-v3.2": {
-            id: "deepseek-v3.2",
-            name: "DeepSeek V3.2",
+        "glm-5-turbo": {
+            id: "glm-5-turbo",
+            name: "GLM-5-Turbo",
             api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 65536,
-        },
-        "devstral-2:123b": {
-            id: "devstral-2:123b",
-            name: "Devstral 2 123B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "devstral-small-2:24b": {
-            id: "devstral-small-2:24b",
-            name: "Devstral Small 2 24B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemma3:12b": {
-            id: "gemma3:12b",
-            name: "Gemma 3 12B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "gemma3:27b": {
-            id: "gemma3:27b",
-            name: "Gemma 3 27B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "gemma3:4b": {
-            id: "gemma3:4b",
-            name: "Gemma 3 4B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "glm-4.6": {
-            id: "glm-4.6",
-            name: "GLM 4.6",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
-        "glm-4.7": {
-            id: "glm-4.7",
-            name: "GLM 4.7",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM 5",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
-        "gpt-oss:120b": {
-            id: "gpt-oss:120b",
-            name: "GPT-OSS 120B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "gpt-oss:20b": {
-            id: "gpt-oss:20b",
-            name: "GPT-OSS 20B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "kimi-k2:1t": {
-            id: "kimi-k2:1t",
-            name: "Kimi K2 1T",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "kimi-k2.5": {
-            id: "kimi-k2.5",
-            name: "Kimi K2.5",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "kimi-k2-thinking": {
-            id: "kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "minimax-m2.1": {
-            id: "minimax-m2.1",
-            name: "Minimax M2.1",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "minimax-m2.5": {
-            id: "minimax-m2.5",
-            name: "Minimax M2.5",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "minimax-m2": {
-            id: "minimax-m2",
-            name: "Minimax M2",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 128000,
-        },
-        "ministral-3:14b": {
-            id: "ministral-3:14b",
-            name: "Ministral 3 14B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 128000,
-        },
-        "ministral-3:3b": {
-            id: "ministral-3:3b",
-            name: "Ministral 3 3B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 128000,
-        },
-        "ministral-3:8b": {
-            id: "ministral-3:8b",
-            name: "Ministral 3 8B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 128000,
-        },
-        "mistral-large-3:675b": {
-            id: "mistral-large-3:675b",
-            name: "Mistral Large 3 675B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "nemotron-3-nano:30b": {
-            id: "nemotron-3-nano:30b",
-            name: "Nemotron 3 Nano 30B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
-        "nemotron-3-super": {
-            id: "nemotron-3-super",
-            name: "Nemotron 3 Super",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "qwen3.5:397b": {
-            id: "qwen3.5:397b",
-            name: "Qwen 3.5 397B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 81920,
-        },
-        "qwen3-coder:480b": {
-            id: "qwen3-coder:480b",
-            name: "Qwen 3 Coder 480B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "qwen3-coder-next": {
-            id: "qwen3-coder-next",
-            name: "Qwen 3 Coder Next",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "qwen3-next:80b": {
-            id: "qwen3-next:80b",
-            name: "Qwen 3 Next 80B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "qwen3-vl:235b-instruct": {
-            id: "qwen3-vl:235b-instruct",
-            name: "Qwen 3 VL 235B Instruct",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
+            contextWindow: 200000,
             maxTokens: 131072,
         },
-        "qwen3-vl:235b": {
-            id: "qwen3-vl:235b",
-            name: "Qwen 3 VL 235B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "rnj-1:8b": {
-            id: "rnj-1:8b",
-            name: "RNJ 1 8B",
-            api: "openai-completions",
-            provider: "ollama-cloud",
-            baseUrl: "https://ollama.com/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 4096,
-        },
     },
 };
 //# sourceMappingURL=models.generated.js.map