@draht/ai 2026.3.6 → 2026.3.14

package/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",
@@ -376,40 +308,6 @@ export const MODELS = {
             contextWindow: 200000,
             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",
@@ -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",
@@ -1803,7 +1803,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
     },
@@ -2298,7 +2298,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.4-pro": {
@@ -2871,7 +2871,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 264000,
             maxTokens: 64000,
         },
         "gpt-5.2-codex": {
@@ -2889,7 +2889,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 400000,
             maxTokens: 128000,
         },
         "gpt-5.3-codex": {
@@ -3247,10 +3247,10 @@ 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,
@@ -3427,6 +3427,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
+        "claude-sonnet-4-6": {
+            id: "claude-sonnet-4-6",
+            name: "Claude Sonnet 4.6 (Antigravity)",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash (Antigravity)",
@@ -4568,10 +4585,10 @@ export const MODELS = {
     "mistral": {
         "codestral-latest": {
             id: "codestral-latest",
-            name: "Codestral",
-            api: "openai-completions",
+            name: "Codestral (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4586,9 +4603,9 @@ export const MODELS = {
         "devstral-2512": {
             id: "devstral-2512",
             name: "Devstral 2",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4603,9 +4620,9 @@ export const MODELS = {
         "devstral-medium-2507": {
             id: "devstral-medium-2507",
             name: "Devstral Medium",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4619,10 +4636,10 @@ export const MODELS = {
         },
         "devstral-medium-latest": {
             id: "devstral-medium-latest",
-            name: "Devstral 2",
-            api: "openai-completions",
+            name: "Devstral 2 (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4637,9 +4654,9 @@ export const MODELS = {
         "devstral-small-2505": {
             id: "devstral-small-2505",
             name: "Devstral Small 2505",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4654,9 +4671,9 @@ export const MODELS = {
         "devstral-small-2507": {
             id: "devstral-small-2507",
             name: "Devstral Small",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4671,9 +4688,9 @@ export const MODELS = {
         "labs-devstral-small-2512": {
             id: "labs-devstral-small-2512",
             name: "Devstral Small 2",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4687,10 +4704,10 @@ export const MODELS = {
         },
         "magistral-medium-latest": {
             id: "magistral-medium-latest",
-            name: "Magistral Medium",
-            api: "openai-completions",
+            name: "Magistral Medium (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -4705,9 +4722,9 @@ export const MODELS = {
         "magistral-small": {
             id: "magistral-small",
             name: "Magistral Small",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -4721,10 +4738,10 @@ export const MODELS = {
         },
         "ministral-3b-latest": {
             id: "ministral-3b-latest",
-            name: "Ministral 3B",
-            api: "openai-completions",
+            name: "Ministral 3B (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4738,10 +4755,10 @@ export const MODELS = {
         },
         "ministral-8b-latest": {
             id: "ministral-8b-latest",
-            name: "Ministral 8B",
-            api: "openai-completions",
+            name: "Ministral 8B (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4756,9 +4773,9 @@ export const MODELS = {
         "mistral-large-2411": {
             id: "mistral-large-2411",
             name: "Mistral Large 2.1",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4773,9 +4790,9 @@ export const MODELS = {
         "mistral-large-2512": {
             id: "mistral-large-2512",
             name: "Mistral Large 3",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4789,10 +4806,10 @@ export const MODELS = {
         },
         "mistral-large-latest": {
             id: "mistral-large-latest",
-            name: "Mistral Large",
-            api: "openai-completions",
+            name: "Mistral Large (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4807,9 +4824,9 @@ export const MODELS = {
         "mistral-medium-2505": {
             id: "mistral-medium-2505",
             name: "Mistral Medium 3",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4824,9 +4841,9 @@ export const MODELS = {
         "mistral-medium-2508": {
             id: "mistral-medium-2508",
             name: "Mistral Medium 3.1",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4840,10 +4857,10 @@ export const MODELS = {
         },
         "mistral-medium-latest": {
             id: "mistral-medium-latest",
-            name: "Mistral Medium",
-            api: "openai-completions",
+            name: "Mistral Medium (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4858,9 +4875,9 @@ export const MODELS = {
         "mistral-nemo": {
             id: "mistral-nemo",
             name: "Mistral Nemo",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4875,9 +4892,9 @@ export const MODELS = {
         "mistral-small-2506": {
             id: "mistral-small-2506",
             name: "Mistral Small 3.2",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4891,10 +4908,10 @@ export const MODELS = {
         },
         "mistral-small-latest": {
             id: "mistral-small-latest",
-            name: "Mistral Small",
-            api: "openai-completions",
+            name: "Mistral Small (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4909,9 +4926,9 @@ export const MODELS = {
         "open-mistral-7b": {
             id: "open-mistral-7b",
             name: "Mistral 7B",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4926,9 +4943,9 @@ export const MODELS = {
         "open-mixtral-8x22b": {
             id: "open-mixtral-8x22b",
             name: "Mixtral 8x22B",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4943,9 +4960,9 @@ export const MODELS = {
         "open-mixtral-8x7b": {
             id: "open-mixtral-8x7b",
             name: "Mixtral 8x7B",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4960,9 +4977,9 @@ export const MODELS = {
         "pixtral-12b": {
             id: "pixtral-12b",
             name: "Pixtral 12B",
-            api: "openai-completions",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4976,10 +4993,10 @@ export const MODELS = {
         },
         "pixtral-large-latest": {
             id: "pixtral-large-latest",
-            name: "Pixtral Large",
-            api: "openai-completions",
+            name: "Pixtral Large (latest)",
+            api: "mistral-conversations",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai/v1",
+            baseUrl: "https://api.mistral.ai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5483,7 +5500,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.4-pro": {
@@ -5760,6 +5777,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
+        "gpt-5.4": {
+            id: "gpt-5.4",
+            name: "GPT-5.4",
+            api: "openai-codex-responses",
+            provider: "openai-codex",
+            baseUrl: "https://chatgpt.com/backend-api",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
     },
     "opencode": {
         "big-pickle": {
@@ -6187,23 +6221,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.3-codex-spark": {
-            id: "gpt-5.3-codex-spark",
-            name: "GPT-5.3 Codex Spark",
-            api: "openai-responses",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 128000,
-        },
         "gpt-5.4": {
             id: "gpt-5.4",
             name: "GPT-5.4",
@@ -6218,7 +6235,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.4-pro": {
@@ -6255,6 +6272,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "mimo-v2-flash-free": {
+            id: "mimo-v2-flash-free",
+            name: "MiMo V2 Flash 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: 262144,
+            maxTokens: 65536,
+        },
         "minimax-m2.1": {
             id: "minimax-m2.1",
             name: "MiniMax M2.1",
@@ -6306,6 +6340,23 @@ 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": {
@@ -6871,6 +6922,23 @@ 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",
@@ -6950,11 +7018,11 @@ 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",
@@ -7024,23 +7092,6 @@ 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",
@@ -7050,13 +7101,13 @@ 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",
@@ -7322,9 +7373,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
-                output: 0.15,
-                cacheRead: 0.02,
+                input: 0.03,
+                output: 0.11,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -7449,23 +7500,6 @@ 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",
@@ -7628,13 +7662,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.295,
-                output: 1.2,
-                cacheRead: 0.03,
+                input: 0.27,
+                output: 0.95,
+                cacheRead: 0.0299999997,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 196608,
+            maxTokens: 4096,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -8061,23 +8095,6 @@ 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",
@@ -8104,13 +8121,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.44999999999999996,
-                output: 2.2,
-                cacheRead: 0.22499999999999998,
+                input: 0.41,
+                output: 2.06,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65535,
+            maxTokens: 4096,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -8197,6 +8214,23 @@ export const MODELS = {
             contextWindow: 256000,
             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)",
@@ -8928,23 +8962,6 @@ 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)",
@@ -9200,6 +9217,40 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
+        "openrouter/healer-alpha": {
+            id: "openrouter/healer-alpha",
+            name: "Healer Alpha",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32000,
+        },
+        "openrouter/hunter-alpha": {
+            id: "openrouter/hunter-alpha",
+            name: "Hunter Alpha",
+            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: 1048576,
+            maxTokens: 32000,
+        },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
             name: "Prime Intellect: INTELLECT-3",
@@ -9608,23 +9659,6 @@ 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)",
@@ -9690,7 +9724,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "qwen/qwen3-next-80b-a3b-instruct:free": {
@@ -9719,13 +9753,13 @@ 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",
@@ -9753,8 +9787,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.26,
+                output: 2.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9787,8 +9821,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.13,
+                output: 1.56,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9914,6 +9948,23 @@ 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",
@@ -10008,13 +10059,13 @@ 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",
@@ -10237,6 +10288,23 @@ 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",
@@ -10373,31 +10441,14 @@ 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)",
+        "z-ai/glm-4.6v": {
+            id: "z-ai/glm-4.6v",
+            name: "Z.ai: GLM 4.6V",
             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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
+            input: ["text", "image"],
             cost: {
                 input: 0.3,
                 output: 0.8999999999999999,
@@ -10450,13 +10501,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.7999999999999999,
-                output: 2.56,
-                cacheRead: 0.16,
+                input: 0.6,
+                output: 1.9,
+                cacheRead: 0.119,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
     },
     "vercel-ai-gateway": {
@@ -10520,13 +10571,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
+                input: 0.29,
+                output: 0.59,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 40960,
         },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10571,13 +10622,13 @@ 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",
@@ -10585,7 +10636,7 @@ 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,
@@ -10613,6 +10664,23 @@ 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",
@@ -10760,8 +10828,8 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
             contextWindow: 200000,
             maxTokens: 8192,
@@ -10970,6 +11038,23 @@ 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",
@@ -10996,13 +11081,13 @@ 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",
@@ -11055,6 +11140,40 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 8192,
+        },
+        "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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 8192,
+        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Gemini 2.5 Flash",
@@ -11062,11 +11181,11 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -11130,11 +11249,11 @@ 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,
@@ -11155,7 +11274,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65000,
         },
         "google/gemini-3-pro-preview": {
             id: "google/gemini-3-pro-preview",
@@ -11257,7 +11376,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 100000,
         },
         "meituan/longcat-flash-thinking": {
             id: "meituan/longcat-flash-thinking",
@@ -11285,13 +11404,13 @@ 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",
@@ -11302,12 +11421,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.03,
-                output: 0.049999999999999996,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 128000,
             maxTokens: 16384,
         },
         "meta/llama-3.2-11b": {
@@ -11370,12 +11489,12 @@ 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": {
@@ -11387,12 +11506,12 @@ 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": {
@@ -11423,8 +11542,8 @@ 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,
@@ -11463,6 +11582,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131000,
         },
+        "minimax/minimax-m2.5-highspeed": {
+            id: "minimax/minimax-m2.5-highspeed",
+            name: "MiniMax M2.5 High Speed",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.03,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 4096,
+            maxTokens: 4096,
+        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -11642,14 +11778,31 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2,
+                input: 0.6,
+                output: 2.5,
                 cacheRead: 0,
                 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,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
             name: "Kimi K2 Thinking",
@@ -11659,13 +11812,13 @@ 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",
@@ -11710,13 +11863,13 @@ 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",
@@ -11744,31 +11897,14 @@ 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",
@@ -11831,7 +11967,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -11882,7 +12018,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11912,11 +12048,11 @@ 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,
@@ -11933,7 +12069,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11950,7 +12086,7 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.39999999999999997,
-                cacheRead: 0.01,
+                cacheRead: 0.005,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11984,7 +12120,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12035,7 +12171,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -12052,7 +12188,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12069,7 +12205,7 @@ export const MODELS = {
             cost: {
                 input: 1.75,
                 output: 14,
-                cacheRead: 0.18,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12194,23 +12330,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-oss-120b": {
-            id: "openai/gpt-oss-120b",
-            name: "gpt-oss-120b",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "gpt-oss-20b",
@@ -12528,7 +12647,7 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
+                cacheRead: 0.75,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -12602,6 +12721,57 @@ 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",
@@ -12628,9 +12798,9 @@ 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,
@@ -12647,11 +12817,11 @@ 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",
@@ -12676,16 +12846,16 @@ 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",
@@ -12747,14 +12917,31 @@ 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",
@@ -12774,7 +12961,7 @@ 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",
@@ -12787,7 +12974,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202800,
-            maxTokens: 131072,
+            maxTokens: 131100,
         },
     },
     "xai": {
@@ -13114,6 +13301,57 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "grok-4.20-beta-latest-non-reasoning": {
+            id: "grok-4.20-beta-latest-non-reasoning",
+            name: "Grok 4.20 Beta (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-beta-latest-reasoning": {
+            id: "grok-4.20-beta-latest-reasoning",
+            name: "Grok 4.20 Beta (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-4.20-multi-agent-beta-latest": {
+            id: "grok-4.20-multi-agent-beta-latest",
+            name: "Grok 4.20 Multi-Agent Beta",
+            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",