npm - @elyracode/ai - Versions diffs - 0.9.30 → 0.9.32 - Mend

@elyracode/ai 0.9.30 → 0.9.32

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (9) hide show

package/dist/image-models.generated.d.ts +30 -0
package/dist/image-models.generated.d.ts.map +1 -1
package/dist/image-models.generated.js +30 -0
package/dist/image-models.generated.js.map +1 -1
package/dist/models.generated.d.ts +1534 -562
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +1909 -1031
package/dist/models.generated.js.map +1 -1
package/package.json +1 -1

package/dist/models.generated.js CHANGED Viewed

@@ -819,6 +819,57 @@ 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,
+            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,
+            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,
+            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",
@@ -1984,6 +2035,23 @@ 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,
+            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",
@@ -2749,10 +2817,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2785,10 +2853,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2966,93 +3034,8 @@ 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-3-haiku": {
-            id: "claude-3-haiku",
-            name: "Claude Haiku 3",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1.25,
-                cacheRead: 0.03,
-                cacheWrite: 0.3,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
-        "claude-3-opus": {
-            id: "claude-3-opus",
-            name: "Claude Opus 3",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
-        "claude-3-sonnet": {
-            id: "claude-3-sonnet",
-            name: "Claude Sonnet 3",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 0.3,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
-        "claude-3.5-sonnet": {
-            id: "claude-3.5-sonnet",
-            name: "Claude Sonnet 3.5 v2",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "claude-fable-5": {
             id: "claude-fable-5",
             name: "Claude Fable 5",
@@ -3071,8 +3054,8 @@ 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",
@@ -3088,42 +3071,8 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-opus-4": {
-            id: "claude-opus-4",
-            name: "Claude Opus 4 (latest)",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "claude-opus-4-1": {
-            id: "claude-opus-4-1",
-            name: "Claude Opus 4.1 (latest)",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "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",
@@ -3139,9 +3088,9 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-opus-4-6": {
-            id: "claude-opus-4-6",
-            name: "Claude Opus 4.6 (latest)",
+        "claude-opus-4.6": {
+            id: "claude-opus-4.6",
+            name: "Claude Opus 4.6",
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
@@ -3157,8 +3106,8 @@ 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",
@@ -3175,8 +3124,8 @@ 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",
@@ -3210,25 +3159,8 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-sonnet-4": {
-            id: "claude-sonnet-4",
-            name: "Claude Sonnet 4 (latest)",
-            api: "anthropic-messages",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "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",
@@ -3241,11 +3173,11 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            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",
@@ -3259,7 +3191,7 @@ export const MODELS = {
                 cacheWrite: 3.75,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "claude-sonnet-5": {
             id: "claude-sonnet-5",
@@ -3278,60 +3210,94 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "gpt-4": {
-            id: "gpt-4",
-            name: "GPT-4",
+        "gpt-4.1": {
+            id: "gpt-4.1",
+            name: "GPT-4.1",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 30,
-                output: 60,
-                cacheRead: 0,
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 1047576,
+            maxTokens: 32768,
         },
-        "gpt-4o": {
-            id: "gpt-4o",
-            name: "GPT-4o",
+        "gpt-4.1-mini": {
+            id: "gpt-4.1-mini",
+            name: "GPT-4.1 mini",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 1.25,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 1047576,
+            maxTokens: 32768,
         },
-        "gpt-4o-mini": {
-            id: "gpt-4o-mini",
-            name: "GPT-4o mini",
+        "gpt-4.1-nano": {
+            id: "gpt-4.1-nano",
+            name: "GPT-4.1 nano",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.08,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 32768,
+        },
+        "gpt-4o": {
+            id: "gpt-4o",
+            name: "GPT-4o",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 5,
+                cacheRead: 0.625,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
+        "gpt-4o-mini": {
+            id: "gpt-4o-mini",
+            name: "GPT-4o mini",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.0375,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5": {
+            id: "gpt-5",
+            name: "GPT-5",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3341,15 +3307,51 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
-        "gpt-5.1-codex": {
-            id: "gpt-5.1-codex",
-            name: "GPT-5.1 Codex",
+        "gpt-5-mini": {
+            id: "gpt-5-mini",
+            name: "GPT-5 Mini",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
+        "gpt-5-nano": {
+            id: "gpt-5-nano",
+            name: "GPT-5 Nano",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.05,
+                output: 0.4,
+                cacheRead: 0.005,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
+        "gpt-5.1": {
+            id: "gpt-5.1",
+            name: "GPT-5.1",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3362,12 +3364,12 @@ export const MODELS = {
                 cacheRead: 0.125,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
-        "gpt-5.2": {
-            id: "gpt-5.2",
-            name: "GPT-5.2",
+        "gpt-5.4": {
+            id: "gpt-5.4",
+            name: "GPT-5.4",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3375,17 +3377,17 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "gpt-5.2-codex": {
-            id: "gpt-5.2-codex",
-            name: "GPT-5.2 Codex",
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3393,17 +3395,17 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
-        "gpt-5.3-codex": {
-            id: "gpt-5.3-codex",
-            name: "GPT-5.3 Codex",
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3411,17 +3413,17 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
-        "gpt-5.4": {
-            id: "gpt-5.4",
-            name: "GPT-5.4",
+        "gpt-5.4-pro": {
+            id: "gpt-5.4-pro",
+            name: "GPT-5.4 Pro",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3429,12 +3431,12 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
+                input: 30,
+                output: 180,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.5": {
@@ -3449,10 +3451,28 @@ export const MODELS = {
             cost: {
                 input: 5,
                 output: 30,
-                cacheRead: 0.5,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-luna": {
@@ -3465,10 +3485,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 0,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3483,10 +3503,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 0,
+                input: 2,
+                output: 10,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3501,31 +3521,14 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "o1": {
-            id: "o1",
-            name: "o1",
-            api: "openai-responses",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 60,
-                cacheRead: 7.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "o3": {
             id: "o3",
             name: "o3",
@@ -3560,23 +3563,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "o3-pro": {
-            id: "o3-pro",
-            name: "o3-pro",
-            api: "openai-responses",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 20,
-                output: 80,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "o4-mini": {
             id: "o4-mini",
             name: "o4-mini",
@@ -3588,104 +3574,52 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "workers-ai/@cf/moonshotai/kimi-k2.5": {
-            id: "workers-ai/@cf/moonshotai/kimi-k2.5",
-            name: "Kimi K2.5",
-            api: "openai-completions",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
-            compat: { "sendSessionAffinityHeaders": true },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "workers-ai/@cf/moonshotai/kimi-k2.6": {
-            id: "workers-ai/@cf/moonshotai/kimi-k2.6",
-            name: "Kimi K2.6",
-            api: "openai-completions",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
-            compat: { "sendSessionAffinityHeaders": true },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.16,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
-            id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
-            name: "Nemotron 3 Super 120B",
-            api: "openai-completions",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
-            compat: { "sendSessionAffinityHeaders": true },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "workers-ai/@cf/zai-org/glm-4.7-flash": {
-            id: "workers-ai/@cf/zai-org/glm-4.7-flash",
-            name: "GLM-4.7-Flash",
+    },
+    "cloudflare-workers-ai": {
+        "@cf/deepseek-ai/deepseek-v4-flash-0731": {
+            id: "@cf/deepseek-ai/deepseek-v4-flash-0731",
+            name: "DeepSeek V4 Flash 0731",
             api: "openai-completions",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
-            compat: { "sendSessionAffinityHeaders": true },
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.4,
-                cacheRead: 0,
+                input: 0.44,
+                output: 1.32,
+                cacheRead: 0.014,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 1310720,
+            maxTokens: 1048576,
         },
-        "workers-ai/@cf/zai-org/glm-5.2": {
-            id: "workers-ai/@cf/zai-org/glm-5.2",
-            name: "Glm 5.2",
+        "@cf/deepseek-ai/deepseek-v4-pro-0813": {
+            id: "@cf/deepseek-ai/deepseek-v4-pro-0813",
+            name: "DeepSeek V4 Pro 0813",
             api: "openai-completions",
-            provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
-            compat: { "sendSessionAffinityHeaders": true },
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0.044,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 1048576,
+            maxTokens: 1048576,
         },
-    },
-    "cloudflare-workers-ai": {
         "@cf/google/gemma-4-26b-a4b-it": {
             id: "@cf/google/gemma-4-26b-a4b-it",
             name: "Gemma 4 26B A4B IT",
@@ -3884,6 +3818,24 @@ 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,
+            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",
@@ -4013,6 +3965,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "accounts/fireworks/models/deepseek-v4-pro-0813": {
+            id: "accounts/fireworks/models/deepseek-v4-pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/glm-5p2": {
             id: "accounts/fireworks/models/glm-5p2",
             name: "GLM 5.2",
@@ -4064,6 +4033,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
+        "accounts/fireworks/models/inkling": {
+            id: "accounts/fireworks/models/inkling",
+            name: "Inkling",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.17,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "accounts/fireworks/models/kimi-k2p6": {
             id: "accounts/fireworks/models/kimi-k2p6",
             name: "Kimi K2.6",
@@ -4112,42 +4098,93 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/minimax-m2p7": {
+            id: "accounts/fireworks/models/minimax-m2p7",
+            name: "MiniMax-M2.7",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
+        "accounts/fireworks/models/minimax-m3": {
+            id: "accounts/fireworks/models/minimax-m3",
+            name: "MiniMax-M3",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 512000,
+        },
+        "accounts/fireworks/models/muse-glimmer-30b": {
+            id: "accounts/fireworks/models/muse-glimmer-30b",
+            name: "Muse Glimmer 30B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.35,
+                output: 1.5,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
             maxTokens: 131072,
         },
-        "accounts/fireworks/models/minimax-m2p7": {
-            id: "accounts/fireworks/models/minimax-m2p7",
-            name: "MiniMax-M2.7",
+        "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
+            id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
+            name: "Nemotron 3 Ultra 550B A55B",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.119,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
-            maxTokens: 196608,
+            contextWindow: 262144,
+            maxTokens: 128000,
         },
-        "accounts/fireworks/models/minimax-m3": {
-            id: "accounts/fireworks/models/minimax-m3",
-            name: "MiniMax-M3",
+        "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
+            id: "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
+            name: "Nemotron 3.5 Lightning 30B A3B",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0.05,
+                output: 0.2,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 512000,
-            maxTokens: 512000,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "accounts/fireworks/models/qwen3p7-plus": {
             id: "accounts/fireworks/models/qwen3p7-plus",
@@ -4166,6 +4203,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "accounts/fireworks/models/qwen3p8-max": {
+            id: "accounts/fireworks/models/qwen3p8-max",
+            name: "Qwen3.8 Max",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/routers/glm-5p2-fast": {
             id: "accounts/fireworks/routers/glm-5p2-fast",
             name: "GLM 5.2 Fast",
@@ -4518,6 +4572,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "gpt-4.1": {
             id: "gpt-4.1",
             name: "GPT-4.1",
@@ -4719,10 +4792,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             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,
@@ -4765,6 +4838,25 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 128000,
         },
+        "grok-4.6": {
+            id: "grok-4.6",
+            name: "Grok 4.6",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 128000,
+        },
         "kimi-k2.7-code": {
             id: "kimi-k2.7-code",
             name: "Kimi K2.7 Code",
@@ -5117,9 +5209,27 @@ 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,
+            maxTokens: 65536,
+        },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5134,9 +5244,9 @@ 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,
@@ -5151,9 +5261,9 @@ 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,
@@ -5635,6 +5745,24 @@ export const MODELS = {
             contextWindow: 524288,
             maxTokens: 128000,
         },
+        "Qwen/Qwen2.5-Coder-32B-Instruct": {
+            id: "Qwen/Qwen2.5-Coder-32B-Instruct",
+            name: "Qwen2.5-Coder-32B-Instruct",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "Qwen/Qwen3-235B-A22B": {
             id: "Qwen/Qwen3-235B-A22B",
             name: "Qwen3 235B-A22B",
@@ -5689,6 +5817,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "Qwen/Qwen3-30B-A3B": {
+            id: "Qwen/Qwen3-30B-A3B",
+            name: "Qwen3 30B A3B",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.12,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 40960,
+            maxTokens: 16384,
+        },
         "Qwen/Qwen3-32B": {
             id: "Qwen/Qwen3-32B",
             name: "Qwen3 32B",
@@ -5797,6 +5943,42 @@ 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,
+            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",
@@ -5923,6 +6105,24 @@ 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,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 6.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "XiaomiMiMo/MiMo-V2.5": {
             id: "XiaomiMiMo/MiMo-V2.5",
             name: "MiMo-V2.5",
@@ -6013,6 +6213,24 @@ export const MODELS = {
             contextWindow: 64000,
             maxTokens: 8192,
         },
+        "deepseek-ai/DeepSeek-V3-0324": {
+            id: "deepseek-ai/DeepSeek-V3-0324",
+            name: "DeepSeek V3 0324",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.27,
+                output: 1.12,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 163840,
+            maxTokens: 163840,
+        },
         "deepseek-ai/DeepSeek-V3.1": {
             id: "deepseek-ai/DeepSeek-V3.1",
             name: "DeepSeek-V3.1",
@@ -6103,6 +6321,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 393216,
         },
+        "deepseek-ai/DeepSeek-V4-Pro-0813": {
+            id: "deepseek-ai/DeepSeek-V4-Pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "google/gemma-4-26B-A4B-it": {
             id: "google/gemma-4-26B-A4B-it",
             name: "Gemma 4 26B A4B IT",
@@ -6139,6 +6375,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "meta-llama/Llama-3.1-8B-Instruct": {
+            id: "meta-llama/Llama-3.1-8B-Instruct",
+            name: "Llama-3.1-8B-Instruct",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.06,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 4096,
+        },
         "meta-llama/Llama-3.3-70B-Instruct": {
             id: "meta-llama/Llama-3.3-70B-Instruct",
             name: "Llama-3.3-70B-Instruct",
@@ -6478,8 +6732,26 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            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",
@@ -8118,10 +8390,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8154,10 +8426,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8708,25 +8980,6 @@ 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",
@@ -8836,6 +9089,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -9195,7 +9466,7 @@ 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",
@@ -9203,10 +9474,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -9365,40 +9636,6 @@ 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,
-        },
-        "ling-3.0-tiny-free": {
-            id: "ling-3.0-tiny-free",
-            name: "Ling-3.0-tiny 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: 32768,
-        },
         "mimo-v2.5-free": {
             id: "mimo-v2.5-free",
             name: "MiMo V2.5 Free",
@@ -9467,6 +9704,40 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 128000,
         },
+        "muse-spark-1.2": {
+            id: "muse-spark-1.2",
+            name: "Muse Spark 1.2",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            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",
@@ -9535,11 +9806,28 @@ 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": {
             id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash (2x usage)",
+            name: "DeepSeek V4 Flash",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9548,9 +9836,28 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.14,
-                cacheRead: 0.0014,
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek-v4-flash-vision-exp": {
+            id: "deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -9567,9 +9874,9 @@ 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,
@@ -9609,9 +9916,26 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3": {
+            id: "glm-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "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",
@@ -9619,10 +9943,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             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,
@@ -9646,16 +9970,16 @@ 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,
@@ -9712,6 +10036,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "longcat-2.0": {
+            id: "longcat-2.0",
+            name: "LongCat-2.0",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "mimo-v2.5": {
             id: "mimo-v2.5",
             name: "MiMo V2.5",
@@ -9780,6 +10121,40 @@ 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",
@@ -9801,9 +10176,9 @@ export const MODELS = {
         "qwen3.7-max": {
             id: "qwen3.7-max",
             name: "Qwen3.7 Max",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -9818,9 +10193,9 @@ export const MODELS = {
         "qwen3.7-plus": {
             id: "qwen3.7-plus",
             name: "Qwen3.7 Plus",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -9835,9 +10210,9 @@ export const MODELS = {
         "qwen3.8-max": {
             id: "qwen3.8-max",
             name: "Qwen3.8 Max",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -9851,23 +10226,6 @@ 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",
@@ -10720,13 +11078,13 @@ 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",
@@ -10737,13 +11095,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.95,
-                cacheRead: 0.13,
+                input: 0.55,
+                output: 1.6500000000000001,
+                cacheRead: 0.55,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 32768,
+            maxTokens: 161000,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -10759,7 +11117,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
+            contextWindow: 64000,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -10789,8 +11147,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.13,
+                output: 1,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -10805,13 +11163,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26899999999999996,
-                output: 0.39999999999999997,
-                cacheRead: 0.13449999999999998,
+                input: 0.26,
+                output: 0.38,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -10841,13 +11199,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.0854,
+                output: 0.1708,
+                cacheRead: 0.01708,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-flash-0731": {
             id: "deepseek/deepseek-v4-flash-0731",
@@ -10860,9 +11218,28 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 131072,
+        },
+        "deepseek/deepseek-v4-flash-vision-exp": {
+            id: "deepseek/deepseek-v4-flash-vision-exp",
+            name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10870,7 +11247,7 @@ export const MODELS = {
         },
         "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",
@@ -10879,13 +11256,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 1.1680000000000001,
-                output: 2.3360000000000003,
-                cacheRead: 0.09855000000000001,
+                input: 0.5790719999999999,
+                output: 1.1581439999999998,
+                cacheRead: 0.048256,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -10898,13 +11275,30 @@ 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: 1.122,
+                output: 3.366,
+                cacheRead: 0.037399999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 4096,
+        },
+        "dots-studio/dots-3-note-preview:free": {
+            id: "dots-studio/dots-3-note-preview:free",
+            name: "Dots Studio: Dots3-Note Preview (free)",
+            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: 512000,
+            maxTokens: 512000,
         },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
@@ -11272,10 +11666,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -11289,10 +11683,44 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.75,
-                cacheRead: 0.075,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Google: Gemini 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash:batch": {
+            id: "google/gemini-3.7-flash:batch",
+            name: "Google: Gemini 3.7 Flash (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1875,
+                output: 0.9375,
+                cacheRead: 0.01875,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -11340,13 +11768,13 @@ 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",
@@ -11433,40 +11861,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
-        "inclusionai/ling-2.6-1t": {
-            id: "inclusionai/ling-2.6-1t",
-            name: "inclusionAI: Ling-2.6-1T",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "inclusionai/ling-2.6-flash": {
-            id: "inclusionai/ling-2.6-flash",
-            name: "inclusionAI: Ling-2.6-flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.01,
-                output: 0.03,
-                cacheRead: 0.002,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
             name: "Ling-3.0-flash",
@@ -11484,40 +11878,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ling-3.0-tiny:free": {
-            id: "inclusionai/ling-3.0-tiny:free",
-            name: "inclusionAI: Ling 3.0 Tiny (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: 32768,
-        },
-        "inclusionai/ring-2.6-1t": {
-            id: "inclusionai/ring-2.6-1t",
-            name: "inclusionAI: Ring-2.6-1T",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "kwaipilot/kat-coder-air-v2.5": {
             id: "kwaipilot/kat-coder-air-v2.5",
             name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -11583,8 +11943,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 32768,
+            contextWindow: 65536,
+            maxTokens: 8192,
         },
         "meituan/longcat-2.0": {
             id: "meituan/longcat-2.0",
@@ -11664,12 +12024,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
-                output: 0.696,
+                output: 0.7999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
@@ -11739,6 +12099,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 4096,
         },
+        "meta/muse-spark-1.2-contributor": {
+            id: "meta/muse-spark-1.2-contributor",
+            name: "Meta: Muse Spark 1.2 Contributor",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
             name: "MiniMax: MiniMax M1",
@@ -11799,13 +12176,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                input: 0.27,
+                output: 1.08,
+                cacheRead: 0.027,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 196608,
+            maxTokens: 128000,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -11822,7 +12199,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 4096,
+        },
+        "minimax/minimax-m2.7:free": {
+            id: "minimax/minimax-m2.7:free",
+            name: "MiniMax: MiniMax M2.7 (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: 196608,
+            maxTokens: 4096,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -11850,14 +12244,31 @@ 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,
             maxTokens: 4096,
         },
+        "minimax/minimax-m3:free": {
+            id: "minimax/minimax-m3:free",
+            name: "MiniMax: MiniMax M3 (free)",
+            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: 1048576,
+            maxTokens: 4096,
+        },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
             name: "Mistral: Codestral 2508",
@@ -11875,6 +12286,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
+        "mistralai/devstral-2512": {
+            id: "mistralai/devstral-2512",
+            name: "Mistral: Devstral 2 2512",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.44,
+                output: 2.2,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -12088,12 +12516,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09375,
-                output: 0.25,
+                input: 0.075,
+                output: 0.19999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
@@ -12207,13 +12635,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5795,
-                output: 2.44,
-                cacheRead: 0.0976,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -12226,7 +12654,7 @@ export const MODELS = {
             cost: {
                 input: 0.67,
                 output: 3.4,
-                cacheRead: 0.15,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12241,9 +12669,9 @@ 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,
@@ -12264,7 +12692,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 1048576,
         },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
@@ -12311,28 +12739,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
-        },
-        "nvidia/nemotron-3-nano-30b-a3b:free": {
-            id: "nvidia/nemotron-3-nano-30b-a3b:free",
-            name: "NVIDIA: Nemotron 3 Nano 30B A3B (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: 256000,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12411,9 +12822,9 @@ 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,
@@ -12436,43 +12847,26 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "nvidia/nemotron-3.5-lightning:free": {
-            id: "nvidia/nemotron-3.5-lightning:free",
-            name: "NVIDIA: Nemotron 3.5 Lightning (free)",
+        "nvidia/nemotron-3.5-lightning": {
+            id: "nvidia/nemotron-3.5-lightning",
+            name: "NVIDIA: Nemotron 3.5 Lightning",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 65536,
-        },
-        "nvidia/nemotron-nano-12b-v2-vl:free": {
-            id: "nvidia/nemotron-nano-12b-v2-vl:free",
-            name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.19999999999999998,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 128000,
+            contextWindow: 262144,
+            maxTokens: 131072,
         },
-        "nvidia/nemotron-nano-9b-v2:free": {
-            id: "nvidia/nemotron-nano-9b-v2:free",
-            name: "NVIDIA: Nemotron Nano 9B V2 (free)",
+        "nvidia/nemotron-3.5-lightning:free": {
+            id: "nvidia/nemotron-3.5-lightning:free",
+            name: "NVIDIA: Nemotron 3.5 Lightning (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12484,8 +12878,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 65536,
         },
         "openai/gpt-3.5-turbo": {
             id: "openai/gpt-3.5-turbo",
@@ -13331,10 +13725,10 @@ export const MODELS = {
             reasoning: true,
             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,
@@ -13348,10 +13742,10 @@ export const MODELS = {
             reasoning: true,
             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,
@@ -13399,10 +13793,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13416,10 +13810,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13433,10 +13827,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13450,10 +13844,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13467,10 +13861,10 @@ export const MODELS = {
             reasoning: true,
             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,
@@ -13484,10 +13878,10 @@ export const MODELS = {
             reasoning: true,
             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,
@@ -13603,9 +13997,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.037,
                 output: 0.16999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -13628,23 +14022,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/gpt-oss-20b:free": {
-            id: "openai/gpt-oss-20b:free",
-            name: "OpenAI: gpt-oss-20b (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: 131072,
-            maxTokens: 32768,
-        },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
             name: "OpenAI: gpt-oss-safeguard-20b",
@@ -14096,10 +14473,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.2,
+                input: 0.26,
+                output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.5,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -14169,7 +14546,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -14385,13 +14762,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14408,7 +14785,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -14419,9 +14796,9 @@ 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,
@@ -14453,13 +14830,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14538,13 +14915,13 @@ export const MODELS = {
             reasoning: true,
             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: 262144,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -14572,9 +14949,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
-                output: 1,
-                cacheRead: 0,
+                input: 0.25,
+                output: 1.25,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14674,13 +15051,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.12,
+                input: 0.32,
+                output: 3.1999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 81920,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -14691,7 +15068,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
@@ -14812,11 +15189,28 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 52429,
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "qwen/qwen3.8-27b": {
+            id: "qwen/qwen3.8-27b",
+            name: "Qwen: Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.425,
+                output: 2.5500000000000003,
+                cacheRead: 0.08499999999999999,
+                cacheWrite: 0.53125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
         "qwen/qwen3.8-max": {
             id: "qwen/qwen3.8-max",
@@ -14920,6 +15314,23 @@ 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,
+            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",
@@ -14986,7 +15397,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 1024000,
+            maxTokens: 32768,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -15019,7 +15430,24 @@ export const MODELS = {
                 cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 524288,
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
+        "thinkingmachines/inkling-small:free": {
+            id: "thinkingmachines/inkling-small:free",
+            name: "Thinking Machines: Inkling Small (free)",
+            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: 1048576,
             maxTokens: 262144,
         },
         "thinkingmachines/inkling:batch": {
@@ -15031,14 +15459,31 @@ 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,
             maxTokens: 4096,
         },
+        "thinkingmachines/inkling:free": {
+            id: "thinkingmachines/inkling:free",
+            name: "Thinking Machines: Inkling (free)",
+            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: 1048576,
+            maxTokens: 262144,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -15252,9 +15697,9 @@ 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,
@@ -15326,7 +15771,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -15354,13 +15799,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.26,
+                output: 3.9600000000000004,
+                cacheRead: 0.234,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 202752,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -15371,13 +15816,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.49,
-                output: 1.54,
-                cacheRead: 0.091,
+                input: 1.19,
+                output: 3.74,
+                cacheRead: 0.221,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 262144,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -15388,14 +15833,48 @@ export const MODELS = {
             reasoning: true,
             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,
+            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,
+            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",
@@ -15493,13 +15972,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.079996,
-                output: 0.252,
-                cacheRead: 0.0252,
+                input: 0.035,
+                output: 0.09999999999999999,
+                cacheRead: 0.008,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 4096,
+            contextWindow: 1310720,
+            maxTokens: 1048576,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -15510,10 +15989,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -15561,10 +16040,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -15603,6 +16082,23 @@ 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": {
@@ -15755,6 +16251,25 @@ 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",
@@ -16371,6 +16886,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.8-2.4t-a95b": {
+            id: "alibaba/qwen3.8-2.4t-a95b",
+            name: "Qwen3.8 2.4T A95B",
+            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: 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,
+            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",
@@ -16733,23 +17282,6 @@ export const MODELS = {
             contextWindow: 262100,
             maxTokens: 80000,
         },
-        "arcee-ai/trinity-mini": {
-            id: "arcee-ai/trinity-mini",
-            name: "Trinity Mini",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.045,
-                output: 0.15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "bytedance/seed-1.6": {
             id: "bytedance/seed-1.6",
             name: "Seed 1.6",
@@ -16912,9 +17444,9 @@ 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,
@@ -16929,9 +17461,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.39999999999999997,
-                cacheRead: 0.04,
+                input: 0.07600000000000001,
+                output: 0.153,
+                cacheRead: 0.014,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-flash-vision-exp": {
+            id: "deepseek/deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16963,9 +17512,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.0036,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.06599999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -17116,14 +17665,31 @@ 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,
             maxTokens: 64000,
         },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Google Gemma 4 26B A4B",
@@ -17155,7 +17721,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "inception/mercury-2": {
@@ -17209,23 +17775,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "inclusionai/ling-3.0-tiny-free": {
-            id: "inclusionai/ling-3.0-tiny-free",
-            name: "Ling 3.0 Tiny (Free)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 32000,
-        },
         "interfaze/interfaze-beta": {
             id: "interfaze/interfaze-beta",
             name: "Interfaze Beta",
@@ -17566,6 +18115,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131000,
         },
+        "minimax/minimax-m2.7-free": {
+            id: "minimax/minimax-m2.7-free",
+            name: "Minimax M2.7 (Free)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
         "minimax/minimax-m2.7-highspeed": {
             id: "minimax/minimax-m2.7-highspeed",
             name: "MiniMax M2.7 High Speed",
@@ -17600,6 +18166,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "minimax/minimax-m3-free": {
+            id: "minimax/minimax-m3-free",
+            name: "MiniMax M3 (Free)",
+            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: 1048576,
+            maxTokens: 1048576,
+        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -17648,42 +18231,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "mistral/magistral-medium": {
-            id: "mistral/magistral-medium",
-            name: "Magistral Medium 2509",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "mistral/magistral-small": {
-            id: "mistral/magistral-small",
-            name: "Magistral Small 2509",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "mistral/ministral-14b": {
             id: "mistral/ministral-14b",
@@ -18025,6 +18574,23 @@ 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",
@@ -18093,6 +18659,23 @@ 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",
@@ -18110,6 +18693,23 @@ 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",
@@ -18127,6 +18727,23 @@ 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",
@@ -18144,6 +18761,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "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: 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",
@@ -18161,6 +18795,23 @@ export const MODELS = {
             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",
@@ -18195,6 +18846,23 @@ 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",
@@ -18212,6 +18880,23 @@ 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",
@@ -18314,6 +18999,23 @@ 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",
@@ -18350,6 +19052,24 @@ 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 ",
@@ -18386,6 +19106,24 @@ 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",
@@ -18404,6 +19142,24 @@ 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",
@@ -18422,6 +19178,24 @@ 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",
@@ -18476,6 +19250,24 @@ 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",
@@ -18511,6 +19303,23 @@ 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,
+            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",
@@ -18520,10 +19329,27 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
+            },
+            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,
+            input: ["text", "image"],
+            cost: {
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18545,6 +19371,23 @@ 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,
+            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",
@@ -18579,6 +19422,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
+        "openai/gpt-oss-safeguard-120b": {
+            id: "openai/gpt-oss-safeguard-120b",
+            name: "GPT OSS Safeguard 120B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16000,
+        },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
             name: "GPT OSS Safeguard 20B",
@@ -18588,13 +19448,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.037,
+                input: 0.07,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 65536,
+            contextWindow: 128000,
+            maxTokens: 16000,
         },
         "openai/o1": {
             id: "openai/o1",
@@ -18630,18 +19490,18 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o3-deep-research": {
-            id: "openai/o3-deep-research",
-            name: "o3-deep-research",
+        "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: 10,
-                output: 40,
-                cacheRead: 2.5,
+                input: 3.5,
+                output: 14,
+                cacheRead: 0.875,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -18698,6 +19558,23 @@ 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",
@@ -18766,93 +19643,8 @@ 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",
@@ -18868,8 +19660,8 @@ 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",
@@ -18885,8 +19677,8 @@ 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",
@@ -18902,8 +19694,8 @@ 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",
@@ -18919,8 +19711,8 @@ 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",
@@ -18936,8 +19728,8 @@ 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",
@@ -18953,8 +19745,8 @@ 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",
@@ -18970,8 +19762,8 @@ 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",
@@ -18987,8 +19779,8 @@ 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",
@@ -19004,8 +19796,8 @@ 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",
@@ -19021,14 +19813,14 @@ 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",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
@@ -19038,8 +19830,8 @@ 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",
@@ -19055,6 +19847,91 @@ 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",
@@ -19157,40 +20034,6 @@ 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",
@@ -19302,9 +20145,9 @@ export const MODELS = {
             reasoning: true,
             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,
@@ -19327,6 +20170,23 @@ 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,
+            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",
@@ -19751,6 +20611,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3": {
+            id: "glm-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
     },
 };
 //# sourceMappingURL=models.generated.js.map