omk-ai 0.96.0 → 0.96.2

package/dist/models.generated.js

@@ -782,6 +782,60 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.openai.gpt-5.6-luna": {
+            id: "global.openai.gpt-5.6-luna",
+            name: "GPT-5.6 Luna (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 1.32,
+                cacheRead: 0.022,
+                cacheWrite: 0.275,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "global.openai.gpt-5.6-sol": {
+            id: "global.openai.gpt-5.6-sol",
+            name: "GPT-5.6 Sol (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "global.openai.gpt-5.6-terra": {
+            id: "global.openai.gpt-5.6-terra",
+            name: "GPT-5.6 Terra (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 13.2,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "google.gemma-3-27b-it": {
             id: "google.gemma-3-27b-it",
             name: "Google Gemma 3 27B Instruct",
@@ -1935,6 +1989,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "xai.grok-4.6": {
+            id: "xai.grok-4.6",
+            name: "Grok 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 6.6,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "zai.glm-4.7": {
             id: "zai.glm-4.7",
             name: "GLM-4.7",
@@ -3034,23 +3106,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 40960,
         },
-        "zai-glm-4.7": {
-            id: "zai-glm-4.7",
-            name: "Z.AI GLM-4.7",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 2.25,
-                output: 2.75,
-                cacheRead: 2.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 40960,
-        },
     },
     "cloudflare-ai-gateway": {
         "claude-fable-5": {
@@ -3070,8 +3125,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-haiku-4-5": {
-            id: "claude-haiku-4-5",
+        "claude-haiku-4.5": {
+            id: "claude-haiku-4.5",
             name: "Claude Haiku 4.5 (latest)",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3087,8 +3142,8 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-opus-4-5": {
-            id: "claude-opus-4-5",
+        "claude-opus-4.5": {
+            id: "claude-opus-4.5",
             name: "Claude Opus 4.5 (latest)",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3104,8 +3159,8 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-opus-4-6": {
-            id: "claude-opus-4-6",
+        "claude-opus-4.6": {
+            id: "claude-opus-4.6",
             name: "Claude Opus 4.6",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3123,8 +3178,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-opus-4-7": {
-            id: "claude-opus-4-7",
+        "claude-opus-4.7": {
+            id: "claude-opus-4.7",
             name: "Claude Opus 4.7",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3142,8 +3197,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-opus-4-8": {
-            id: "claude-opus-4-8",
+        "claude-opus-4.8": {
+            id: "claude-opus-4.8",
             name: "Claude Opus 4.8",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3178,8 +3233,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-sonnet-4-5": {
-            id: "claude-sonnet-4-5",
+        "claude-sonnet-4.5": {
+            id: "claude-sonnet-4.5",
             name: "Claude Sonnet 4.5 (latest)",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3195,8 +3250,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "claude-sonnet-4-6": {
-            id: "claude-sonnet-4-6",
+        "claude-sonnet-4.6": {
+            id: "claude-sonnet-4.6",
             name: "Claude Sonnet 4.6",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
@@ -3326,9 +3381,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 1.25,
+                input: 1.25,
+                output: 5,
+                cacheRead: 0.625,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -3343,9 +3398,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.075,
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -4085,7 +4140,7 @@ export const MODELS = {
                 cacheRead: 0.014,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1310720,
             maxTokens: 1048576,
         },
         "@cf/deepseek-ai/deepseek-v4-pro-0813": {
@@ -4306,6 +4361,25 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 32768,
         },
+        "@cf/qwen/qwen3.8-27b": {
+            id: "@cf/qwen/qwen3.8-27b",
+            name: "Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.45,
+                output: 3.2,
+                cacheRead: 0.05,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "@cf/zai-org/glm-4.7-flash": {
             id: "@cf/zai-org/glm-4.7-flash",
             name: "GLM-4.7-Flash",
@@ -5712,9 +5786,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5747,9 +5821,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 9,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5764,9 +5838,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.25,
-                output: 1.5,
-                cacheRead: 0.025,
+                input: 0.3,
+                output: 2.5,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -6469,6 +6543,43 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "Qwen/Qwen3-VL-235B-A22B-Instruct": {
+            id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
+            name: "Qwen3 VL 235B A22B Instruct",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "Qwen/Qwen3-VL-235B-A22B-Thinking": {
+            id: "Qwen/Qwen3-VL-235B-A22B-Thinking",
+            name: "Qwen3 VL 235B A22B Thinking",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.98,
+                output: 3.95,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
         "Qwen/Qwen3.5-122B-A10B": {
             id: "Qwen/Qwen3.5-122B-A10B",
             name: "Qwen3.5 122B-A10B",
@@ -6602,6 +6713,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "Qwen/Qwen3.8-2.4T-A95B": {
+            id: "Qwen/Qwen3.8-2.4T-A95B",
+            name: "Qwen3.8 2.4T A95B",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 6.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "XiaomiMiMo/MiMo-V2-Flash": {
             id: "XiaomiMiMo/MiMo-V2-Flash",
             name: "MiMo-V2-Flash",
@@ -7232,6 +7362,24 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "zai-org/GLM-4.6V-Flash": {
+            id: "zai-org/GLM-4.6V-Flash",
+            name: "GLM-4.6V-Flash",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 0.9,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
         "zai-org/GLM-4.7": {
             id: "zai-org/GLM-4.7",
             name: "GLM-4.7",
@@ -8972,26 +9120,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 16384,
         },
-        "z-ai/glm-5.2": {
-            id: "z-ai/glm-5.2",
-            name: "GLM-5.2",
-            api: "openai-completions",
-            provider: "nvidia",
-            baseUrl: "https://integrate.api.nvidia.com/v1",
-            headers: { "NVCF-POLL-SECONDS": "3600" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 131072,
-        },
     },
     "openai": {
         "gpt-4": {
@@ -9840,7 +9968,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 372000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -10095,25 +10223,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "deepseek-v4-flash-free": {
-            id: "deepseek-v4-flash-free",
-            name: "DeepSeek V4 Flash Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 128000,
-        },
         "deepseek-v4-pro": {
             id: "deepseek-v4-pro",
             name: "DeepSeek V4 Pro",
@@ -10601,7 +10710,7 @@ export const MODELS = {
         },
         "gpt-5.6-sol": {
             id: "gpt-5.6-sol",
-            name: "GPT-5.6 Sol",
+            name: "GPT-5.6 Sol (50% Off)",
             api: "openai-responses",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -10609,13 +10718,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
         },
         "gpt-5.6-terra": {
             id: "gpt-5.6-terra",
@@ -10774,23 +10883,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "laguna-s-2.1-free": {
-            id: "laguna-s-2.1-free",
-            name: "Laguna S 2.1 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: 256000,
-            maxTokens: 32000,
-        },
         "mimo-v2.5-free": {
             id: "mimo-v2.5-free",
             name: "MiMo V2.5 Free",
@@ -10876,6 +10968,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "muse-spark-1.2-contributor-free": {
+            id: "muse-spark-1.2-contributor-free",
+            name: "Muse Spark 1.2 Free",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "nemotron-3-ultra-free": {
             id: "nemotron-3-ultra-free",
             name: "Nemotron 3 Ultra Free",
@@ -10946,6 +11055,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "x-preview-f-free": {
+            id: "x-preview-f-free",
+            name: "Ox Alpha Free (Unlimited)",
+            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: 1000000,
+            maxTokens: 131072,
+        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -10959,9 +11085,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.0028,
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -10978,9 +11104,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.003625,
+                input: 0.66,
+                output: 1.98,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -11041,7 +11167,7 @@ export const MODELS = {
         },
         "gpt-5.6-luna": {
             id: "gpt-5.6-luna",
-            name: "GPT-5.6 Luna (2x usage)",
+            name: "GPT-5.6 Luna",
             api: "openai-responses",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -11049,10 +11175,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -11076,16 +11202,16 @@ export const MODELS = {
         },
         "hy3": {
             id: "hy3",
-            name: "Hy3",
+            name: "Hy3 (8x usage)",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.58,
-                cacheRead: 0.035,
+                input: 0.0175,
+                output: 0.0725,
+                cacheRead: 0.004375,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -11212,6 +11338,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "muse-spark-1.2-contributor": {
+            id: "muse-spark-1.2-contributor",
+            name: "Muse Spark 1.2 Contributor",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.2,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "ox-alpha-free": {
+            id: "ox-alpha-free",
+            name: "Ox Alpha Free (Unlimited)",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -11287,23 +11447,6 @@ export const MODELS = {
         },
     },
     "openrouter": {
-        "ai21/jamba-large-1.7": {
-            id: "ai21/jamba-large-1.7",
-            name: "AI21: Jamba Large 1.7",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 4096,
-        },
         "aion-labs/aion-2.0": {
             id: "aion-labs/aion-2.0",
             name: "AionLabs: Aion-2.0",
@@ -12156,13 +12299,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.27,
-                output: 1.12,
-                cacheRead: 0.135,
+                input: 0.25,
+                output: 1,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -12225,8 +12368,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.13,
+                output: 1,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -12277,9 +12420,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.061459999999999994,
-                output: 0.12291999999999999,
-                cacheRead: 0.012292,
+                input: 0.08259999999999999,
+                output: 0.16519999999999999,
+                cacheRead: 0.01652,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12296,17 +12439,17 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.08,
+                output: 0.18,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 393216,
+            contextWindow: 1310720,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
-            name: "DeepSeek: DeepSeek V4 Pro",
+            name: "DeepSeek: DeepSeek V4 Pro 0423",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12315,9 +12458,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.1680000000000001,
-                output: 2.3360000000000003,
-                cacheRead: 0.09855000000000001,
+                input: 1.5999999999999999,
+                output: 3.1999999999999997,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12334,13 +12477,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.003625,
+                input: 1.1880000000000002,
+                output: 3.564,
+                cacheRead: 0.039599999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 4096,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -12827,13 +12970,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.12,
-                output: 0.39999999999999997,
-                cacheRead: 0.049999999999999996,
+                input: 0.07,
+                output: 0.33999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 16384,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -13054,7 +13197,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 65536,
             maxTokens: 8192,
         },
         "meituan/longcat-2.0": {
@@ -13168,13 +13311,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.35,
-                output: 1.5,
+                input: 0.3,
+                output: 1.1,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "meta/muse-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -13270,13 +13413,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                input: 0.27,
+                output: 0.95,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 196608,
+            maxTokens: 32768,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -13321,9 +13464,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 524288,
@@ -13679,9 +13822,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5415,
-                output: 2.2800000000000002,
-                cacheRead: 0.09119999999999999,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13696,9 +13839,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.71,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.67,
+                output: 3.4,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13713,9 +13856,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.475,
-                output: 2,
-                cacheRead: 0.095,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13783,11 +13926,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
+            maxTokens: 262144,
         },
         "nvidia/nemotron-3-nano-30b-a3b:free": {
             id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -13883,9 +14026,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.7999999999999998,
-                cacheRead: 0.09999999999999999,
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 512288,
@@ -13917,13 +14060,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.25,
-                cacheRead: 0.049999999999999996,
+                input: 0.08,
+                output: 0.19999999999999998,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 262144,
+            contextWindow: 262144,
+            maxTokens: 131072,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -14923,10 +15066,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14941,10 +15084,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14995,10 +15138,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -15013,10 +15156,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -15031,9 +15174,9 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
+                input: 1.25,
+                output: 7.5,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15049,9 +15192,9 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
+                input: 1.25,
+                output: 7.5,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15067,10 +15210,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -15085,10 +15228,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -15997,13 +16140,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 1.1,
-                cacheRead: 0.07,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 16384,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -16032,9 +16175,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.26,
-                output: 1.04,
-                cacheRead: 0,
+                input: 0.21,
+                output: 1.9,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -16155,13 +16298,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.29,
-                output: 2.4,
+                input: 0.26,
+                output: 2.08,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -16191,13 +16334,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.22499999999999998,
-                output: 1.7999999999999998,
-                cacheRead: 0.22499999999999998,
+                input: 0.25,
+                output: 1.25,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -16299,13 +16442,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2,
-                cacheRead: 0.03,
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -16317,7 +16460,7 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
@@ -16463,10 +16606,10 @@ export const MODELS = {
             cost: {
                 input: 0.44999999999999996,
                 output: 3.1999999999999997,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 131072,
         },
         "qwen/qwen3.8-max": {
@@ -16572,6 +16715,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "stealth/ox-alpha": {
+            id: "stealth/ox-alpha",
+            name: "Ox Alpha",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max", "ultra": "ultra" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -16688,7 +16849,7 @@ export const MODELS = {
                 cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 524288,
+            contextWindow: 1048576,
             maxTokens: 262144,
         },
         "thinkingmachines/inkling:batch": {
@@ -16700,9 +16861,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2.025,
-                cacheRead: 0.08499999999999999,
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 524288,
@@ -16922,9 +17083,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.11,
+                input: 0.5,
+                output: 2,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -17042,13 +17203,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
             input: ["text"],
             cost: {
-                input: 0.308,
-                output: 0.9680000000000001,
-                cacheRead: 0.0572,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1932,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 128000,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -17060,14 +17221,50 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
             input: ["text"],
             cost: {
-                input: 0.7,
-                output: 2.2,
-                cacheRead: 0.13,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 512000,
+            contextWindow: 1048575,
             maxTokens: 4096,
         },
+        "z-ai/glm-5.2:free": {
+            id: "z-ai/glm-5.2:free",
+            name: "Z.ai: GLM 5.2 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "z-ai/glm-5.3": {
+            id: "z-ai/glm-5.3",
+            name: "Z.ai: GLM 5.3",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
             name: "Z.ai: GLM 5V Turbo",
@@ -17164,13 +17361,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.06426,
-                output: 0.12852,
-                cacheRead: 0.012852,
+                input: 0.065,
+                output: 0.18,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 384000,
+            contextWindow: 1310720,
+            maxTokens: 1048576,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -17215,13 +17412,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.8,
-                output: 14,
+                input: 2.6,
+                output: 13,
                 cacheRead: 0.29,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 1048576,
+            maxTokens: 974842,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -17232,10 +17429,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -17275,6 +17472,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 4096,
         },
+        "~z-ai/glm-latest": {
+            id: "~z-ai/glm-latest",
+            name: "Z.ai: GLM Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "together": {
         "MiniMaxAI/MiniMax-M2.7": {
@@ -17427,6 +17641,25 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 384000,
         },
+        "deepseek-ai/DeepSeek-V4-Pro-0813": {
+            id: "deepseek-ai/DeepSeek-V4-Pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0.13,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "google/gemma-4-31B-it": {
             id: "google/gemma-4-31B-it",
             name: "Gemma 4 31B Instruct",
@@ -18067,16 +18300,34 @@ export const MODELS = {
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.25,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "alibaba/qwen3.8-27b": {
+            id: "alibaba/qwen3.8-27b",
+            name: "Qwen3.8 27B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.55,
+                output: 3.3000000000000003,
+                cacheRead: 0.11,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -18625,9 +18876,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.39999999999999997,
-                cacheRead: 0.04,
+                input: 0.13,
+                output: 0.26,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -18642,9 +18893,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.39999999999999997,
-                cacheRead: 0.04,
+                input: 0.13,
+                output: 0.26,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -18829,9 +19080,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -19738,6 +19989,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65000,
         },
+        "nvidia/nemotron-3.5-lightning": {
+            id: "nvidia/nemotron-3.5-lightning",
+            name: "Nemotron 3.5 Lightning 30B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.19999999999999998,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -19823,6 +20091,23 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
+        "openai/gpt-4.1-fast": {
+            id: "openai/gpt-4.1-fast",
+            name: "GPT-4.1 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 3.5,
+                output: 14,
+                cacheRead: 0.875,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
         "openai/gpt-4.1-mini": {
             id: "openai/gpt-4.1-mini",
             name: "GPT-4.1 mini",
@@ -19840,6 +20125,23 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
+        "openai/gpt-4.1-mini-fast": {
+            id: "openai/gpt-4.1-mini-fast",
+            name: "GPT-4.1 mini (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.7,
+                output: 2.8,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
             name: "GPT-4.1 nano",
@@ -19857,6 +20159,23 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
+        "openai/gpt-4.1-nano-fast": {
+            id: "openai/gpt-4.1-nano-fast",
+            name: "GPT-4.1 nano (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 0.7999999999999999,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
         "openai/gpt-4o": {
             id: "openai/gpt-4o",
             name: "GPT-4o",
@@ -19874,23 +20193,57 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o-mini": {
-            id: "openai/gpt-4o-mini",
-            name: "GPT-4o mini",
+        "openai/gpt-4o-fast": {
+            id: "openai/gpt-4o-fast",
+            name: "GPT-4o (Fast)",
             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,
+                input: 4.25,
+                output: 17,
+                cacheRead: 2.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "openai/gpt-4o-mini": {
+            id: "openai/gpt-4o-mini",
+            name: "GPT-4o mini",
+            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: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai/gpt-4o-mini-fast": {
+            id: "openai/gpt-4o-mini-fast",
+            name: "GPT-4o mini (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai/gpt-5": {
             id: "openai/gpt-5",
             name: "GPT-5",
@@ -19925,6 +20278,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5-fast": {
+            id: "openai/gpt-5-fast",
+            name: "GPT-5 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 20,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5-mini": {
             id: "openai/gpt-5-mini",
             name: "GPT-5 mini",
@@ -19942,6 +20312,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5-mini-fast": {
+            id: "openai/gpt-5-mini-fast",
+            name: "GPT-5 mini (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.44999999999999996,
+                output: 3.5999999999999996,
+                cacheRead: 0.045,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
             name: "GPT-5 nano",
@@ -20044,6 +20431,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.1-thinking-fast": {
+            id: "openai/gpt-5.1-thinking-fast",
+            name: "GPT 5.1 Thinking (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 20,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
             name: "GPT 5.2",
@@ -20080,6 +20484,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.2-fast": {
+            id: "openai/gpt-5.2-fast",
+            name: "GPT 5.2 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 3.5,
+                output: 28,
+                cacheRead: 0.35,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.2-pro": {
             id: "openai/gpt-5.2-pro",
             name: "GPT 5.2 ",
@@ -20116,6 +20538,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.3-codex-fast": {
+            id: "openai/gpt-5.3-codex-fast",
+            name: "GPT 5.3 Codex (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 3.5,
+                output: 28,
+                cacheRead: 0.35,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4": {
             id: "openai/gpt-5.4",
             name: "GPT 5.4",
@@ -20134,6 +20574,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-fast": {
+            id: "openai/gpt-5.4-fast",
+            name: "GPT 5.4 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-mini": {
             id: "openai/gpt-5.4-mini",
             name: "GPT 5.4 Mini",
@@ -20152,6 +20610,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-mini-fast": {
+            id: "openai/gpt-5.4-mini-fast",
+            name: "GPT 5.4 Mini (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-nano": {
             id: "openai/gpt-5.4-nano",
             name: "GPT 5.4 Nano",
@@ -20206,6 +20682,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.5-fast": {
+            id: "openai/gpt-5.5-fast",
+            name: "GPT 5.5 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 12.5,
+                output: 75,
+                cacheRead: 1.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.5-pro": {
             id: "openai/gpt-5.5-pro",
             name: "GPT 5.5 Pro",
@@ -20242,6 +20736,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-luna-fast": {
+            id: "openai/gpt-5.6-luna-fast",
+            name: "GPT 5.6 Luna (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2.4,
+                cacheRead: 0.04,
+                cacheWrite: 0.25,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.6-sol": {
             id: "openai/gpt-5.6-sol",
             name: "GPT 5.6 Sol",
@@ -20251,11 +20763,29 @@ export const MODELS = {
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.6-sol-fast": {
+            id: "openai/gpt-5.6-sol-fast",
+            name: "GPT 5.6 Sol (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
             cost: {
                 input: 5,
                 output: 30,
                 cacheRead: 0.5,
-                cacheWrite: 6.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -20278,6 +20808,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-terra-fast": {
+            id: "openai/gpt-5.6-terra-fast",
+            name: "GPT 5.6 Terra (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 4,
+                output: 24,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -20380,6 +20928,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "openai/o3-fast": {
+            id: "openai/o3-fast",
+            name: "o3 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3.5,
+                output: 14,
+                cacheRead: 0.875,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "openai/o3-mini": {
             id: "openai/o3-mini",
             name: "o3-mini",
@@ -20431,6 +20996,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "openai/o4-mini-fast": {
+            id: "openai/o4-mini-fast",
+            name: "o4-mini (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "poolside/laguna-s-2.1": {
             id: "poolside/laguna-s-2.1",
             name: "Laguna S 2.1",
@@ -20499,93 +21081,8 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
-        "stepfun/step-3.5-flash": {
-            id: "stepfun/step-3.5-flash",
-            name: "StepFun 3.5 Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09,
-                output: 0.3,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 262114,
-            maxTokens: 262114,
-        },
-        "stepfun/step-3.7-flash": {
-            id: "stepfun/step-3.7-flash",
-            name: "Step 3.7 Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 1.15,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "tencent/hy3": {
-            id: "tencent/hy3",
-            name: "Hy3",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.14,
-                output: 0.58,
-                cacheRead: 0.035,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "thinkingmachines/inkling": {
-            id: "thinkingmachines/inkling",
-            name: "Inkling",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 4.05,
-                cacheRead: 0.16999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "thinkingmachines/inkling-small": {
-            id: "thinkingmachines/inkling-small",
-            name: "Inkling Small",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.2,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 1000000,
-        },
-        "xai/grok-4.1-fast-non-reasoning": {
-            id: "xai/grok-4.1-fast-non-reasoning",
+        "spacexai/grok-4.1-fast-non-reasoning": {
+            id: "spacexai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20601,8 +21098,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-4.1-fast-reasoning": {
-            id: "xai/grok-4.1-fast-reasoning",
+        "spacexai/grok-4.1-fast-reasoning": {
+            id: "spacexai/grok-4.1-fast-reasoning",
             name: "Grok 4.1 Fast Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20618,8 +21115,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-4.20-multi-agent": {
-            id: "xai/grok-4.20-multi-agent",
+        "spacexai/grok-4.20-multi-agent": {
+            id: "spacexai/grok-4.20-multi-agent",
             name: "Grok 4.20 Multi-Agent",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20636,14 +21133,13 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.20-multi-agent-beta": {
-            id: "xai/grok-4.20-multi-agent-beta",
+        "spacexai/grok-4.20-multi-agent-beta": {
+            id: "spacexai/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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 1.25,
@@ -20654,8 +21150,8 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.20-non-reasoning": {
-            id: "xai/grok-4.20-non-reasoning",
+        "spacexai/grok-4.20-non-reasoning": {
+            id: "spacexai/grok-4.20-non-reasoning",
             name: "Grok 4.20 Non-Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20671,8 +21167,8 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.20-non-reasoning-beta": {
-            id: "xai/grok-4.20-non-reasoning-beta",
+        "spacexai/grok-4.20-non-reasoning-beta": {
+            id: "spacexai/grok-4.20-non-reasoning-beta",
             name: "Grok 4.20 Beta Non-Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20688,8 +21184,8 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.20-reasoning": {
-            id: "xai/grok-4.20-reasoning",
+        "spacexai/grok-4.20-reasoning": {
+            id: "spacexai/grok-4.20-reasoning",
             name: "Grok 4.20 Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20705,8 +21201,8 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.20-reasoning-beta": {
-            id: "xai/grok-4.20-reasoning-beta",
+        "spacexai/grok-4.20-reasoning-beta": {
+            id: "spacexai/grok-4.20-reasoning-beta",
             name: "Grok 4.20 Beta Reasoning",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20722,8 +21218,8 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
-        "xai/grok-4.3": {
-            id: "xai/grok-4.3",
+        "spacexai/grok-4.3": {
+            id: "spacexai/grok-4.3",
             name: "Grok 4.3",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20739,8 +21235,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-4.5": {
-            id: "xai/grok-4.5",
+        "spacexai/grok-4.5": {
+            id: "spacexai/grok-4.5",
             name: "Grok 4.5",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20756,8 +21252,8 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
-        "xai/grok-4.6": {
-            id: "xai/grok-4.6",
+        "spacexai/grok-4.6": {
+            id: "spacexai/grok-4.6",
             name: "Grok 4.6",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20774,8 +21270,8 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
-        "xai/grok-build-0.1": {
-            id: "xai/grok-build-0.1",
+        "spacexai/grok-build-0.1": {
+            id: "spacexai/grok-build-0.1",
             name: "Grok Build 0.1",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
@@ -20791,6 +21287,91 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "stepfun/step-3.5-flash": {
+            id: "stepfun/step-3.5-flash",
+            name: "StepFun 3.5 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 262114,
+            maxTokens: 262114,
+        },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "Step 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "tencent/hy3": {
+            id: "tencent/hy3",
+            name: "Hy3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.13199999999999998,
+                output: 0.5279999999999999,
+                cacheRead: 0.032999999999999995,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 128000,
+        },
+        "thinkingmachines/inkling": {
+            id: "thinkingmachines/inkling",
+            name: "Inkling",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.16999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "thinkingmachines/inkling-small": {
+            id: "thinkingmachines/inkling-small",
+            name: "Inkling Small",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
             name: "MiMo M2.5",
@@ -20893,40 +21474,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 96000,
         },
-        "zai/glm-4.6v": {
-            id: "zai/glm-4.6v",
-            name: "GLM-4.6V",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 24000,
-        },
-        "zai/glm-4.6v-flash": {
-            id: "zai/glm-4.6v-flash",
-            name: "GLM-4.6V-Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 24000,
-        },
         "zai/glm-4.7": {
             id: "zai/glm-4.7",
             name: "GLM 4.7",
@@ -21039,9 +21586,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
             input: ["text"],
             cost: {
-                input: 1.1,
-                output: 3.851,
-                cacheRead: 0.275,
+                input: 0.7999999999999999,
+                output: 2.5500000000000003,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -21065,6 +21612,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "zai/glm-5.3": {
+            id: "zai/glm-5.3",
+            name: "GLM 5.3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 12800,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",