@caupulican/pi-ai 0.95.0 → 0.96.1

package/dist/models.generated.js

@@ -815,6 +815,63 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.openai.gpt-5.6-luna": {
+            id: "global.openai.gpt-5.6-luna",
+            name: "GPT-5.6 Luna (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            supportedImageMimeTypes: ["image/jpeg", "image/jpg", "image/png", "image/gif", "image/webp"],
+            cost: {
+                input: 0.22,
+                output: 1.32,
+                cacheRead: 0.022,
+                cacheWrite: 0.275,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "global.openai.gpt-5.6-sol": {
+            id: "global.openai.gpt-5.6-sol",
+            name: "GPT-5.6 Sol (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            supportedImageMimeTypes: ["image/jpeg", "image/jpg", "image/png", "image/gif", "image/webp"],
+            cost: {
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "global.openai.gpt-5.6-terra": {
+            id: "global.openai.gpt-5.6-terra",
+            name: "GPT-5.6 Terra (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            supportedImageMimeTypes: ["image/jpeg", "image/jpg", "image/png", "image/gif", "image/webp"],
+            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",
@@ -2008,6 +2065,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "xai.grok-4.6": {
+            id: "xai.grok-4.6",
+            name: "Grok 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            supportedImageMimeTypes: ["image/jpeg", "image/jpg", "image/png", "image/gif", "image/webp"],
+            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",
@@ -2983,127 +3058,8 @@ 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-3-5-haiku": {
-            id: "claude-3-5-haiku",
-            name: "Claude Haiku 3.5 (latest)",
-            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: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "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-haiku": {
-            id: "claude-3.5-haiku",
-            name: "Claude Haiku 3.5 (latest)",
-            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: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "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",
@@ -3140,40 +3096,6 @@ 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",
             name: "Claude Opus 4.5 (latest)",
@@ -3193,7 +3115,7 @@ export const MODELS = {
         },
         "claude-opus-4-6": {
             id: "claude-opus-4-6",
-            name: "Claude Opus 4.6 (latest)",
+            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",
@@ -3267,23 +3189,6 @@ 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",
             name: "Claude Sonnet 4.5 (latest)",
@@ -3298,7 +3203,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "claude-sonnet-4-6": {
@@ -3318,7 +3223,7 @@ export const MODELS = {
                 cacheWrite: 3.75,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "claude-sonnet-5": {
             id: "claude-sonnet-5",
@@ -3373,61 +3278,166 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "gpt-4o": {
-            id: "gpt-4o",
-            name: "GPT-4o",
+        "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", "image"],
             cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 1.25,
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 1047576,
+            maxTokens: 32768,
         },
-        "gpt-4o-mini": {
-            id: "gpt-4o-mini",
-            name: "GPT-4o mini",
+        "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: 0.15,
-                output: 0.6,
-                cacheRead: 0.08,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 1047576,
+            maxTokens: 32768,
         },
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
+        "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: true,
-            thinkingLevelMap: { "off": null },
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.13,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 1047576,
+            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-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",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
             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: 400000,
+            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: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5-pro": {
+            id: "gpt-5-pro",
+            name: "GPT-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 },
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 120,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 272000,
+        },
+        "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",
@@ -3461,9 +3471,9 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.2-codex": {
-            id: "gpt-5.2-codex",
-            name: "GPT-5.2 Codex",
+        "gpt-5.2-chat-latest": {
+            id: "gpt-5.2-chat-latest",
+            name: "GPT-5.2 Chat",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3476,9 +3486,45 @@ export const MODELS = {
                 cacheRead: 0.175,
                 cacheWrite: 0,
             },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5.2-pro": {
+            id: "gpt-5.2-pro",
+            name: "GPT-5.2 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: 21,
+                output: 168,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: false,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -3497,6 +3543,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-codex-spark": {
+            id: "gpt-5.3-codex-spark",
+            name: "GPT-5.3 Codex Spark",
+            api: "openai-responses",
+            provider: "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: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 32000,
+        },
         "gpt-5.4": {
             id: "gpt-5.4",
             name: "GPT-5.4",
@@ -3515,6 +3579,60 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "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",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "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: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-pro": {
+            id: "gpt-5.4-pro",
+            name: "GPT-5.4 Pro",
+            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: 1050000,
+            maxTokens: 128000,
+        },
         "gpt-5.5": {
             id: "gpt-5.5",
             name: "GPT-5.5",
@@ -3533,6 +3651,42 @@ export const MODELS = {
             contextWindow: 1050000,
             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", "minimal": null, "low": null },
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.6": {
+            id: "gpt-5.6",
+            name: "GPT-5.6",
+            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", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "gpt-5.6-luna": {
             id: "gpt-5.6-luna",
             name: "GPT-5.6 Luna",
@@ -3543,10 +3697,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             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,
@@ -3564,7 +3718,7 @@ export const MODELS = {
                 input: 5,
                 output: 30,
                 cacheRead: 0.5,
-                cacheWrite: 0,
+                cacheWrite: 6.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3579,10 +3733,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             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,
@@ -3604,6 +3758,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "o1-pro": {
+            id: "o1-pro",
+            name: "o1-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: 150,
+                output: 600,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "o3": {
             id: "o3",
             name: "o3",
@@ -3660,57 +3831,201 @@ export const MODELS = {
             name: "o4-mini",
             api: "openai-responses",
             provider: "cloudflare-ai-gateway",
-            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "workers-ai/@cf/google/gemma-4-26b-a4b-it": {
+            id: "workers-ai/@cf/google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            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: 0.1,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
+        "workers-ai/@cf/ibm-granite/granite-4.0-h-micro": {
+            id: "workers-ai/@cf/ibm-granite/granite-4.0-h-micro",
+            name: "Granite 4.0 H Micro",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0.017,
+                output: 0.112,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 131000,
+        },
+        "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
+            id: "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+            name: "Llama 3.3 70B Instruct fp8 Fast",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0.293,
+                output: 2.253,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 24000,
+            maxTokens: 24000,
+        },
+        "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct": {
+            id: "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct",
+            name: "Llama 4 Scout 17B 16E Instruct",
+            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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.27,
+                output: 0.85,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 16384,
+        },
+        "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct": {
+            id: "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral Small 3.1 24B Instruct",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0.351,
+                output: 0.555,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
+        "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: 262144,
+            maxTokens: 256000,
+        },
+        "workers-ai/@cf/moonshotai/kimi-k2.7-code": {
+            id: "workers-ai/@cf/moonshotai/kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
+            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: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "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", "image"],
+            input: ["text"],
             cost: {
-                input: 1.1,
-                output: 4.4,
-                cacheRead: 0.28,
+                input: 0.5,
+                output: 1.5,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 100000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
-        "workers-ai/@cf/moonshotai/kimi-k2.5": {
-            id: "workers-ai/@cf/moonshotai/kimi-k2.5",
-            name: "Kimi K2.5",
+        "workers-ai/@cf/openai/gpt-oss-120b": {
+            id: "workers-ai/@cf/openai/gpt-oss-120b",
+            name: "GPT OSS 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", "image"],
+            input: ["text"],
             cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.35,
+                output: 0.75,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 128000,
+            maxTokens: 16384,
         },
-        "workers-ai/@cf/moonshotai/kimi-k2.6": {
-            id: "workers-ai/@cf/moonshotai/kimi-k2.6",
-            name: "Kimi K2.6",
+        "workers-ai/@cf/openai/gpt-oss-20b": {
+            id: "workers-ai/@cf/openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
             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"],
+            input: ["text"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.16,
+                input: 0.2,
+                output: 0.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 128000,
+            maxTokens: 16384,
         },
-        "workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
-            id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
-            name: "Nemotron 3 Super 120B",
+        "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8": {
+            id: "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8",
+            name: "Qwen3 30B A3b fp8",
             api: "openai-completions",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
@@ -3718,13 +4033,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 1.5,
+                input: 0.0509,
+                output: 0.335,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 32768,
+            maxTokens: 32768,
         },
         "workers-ai/@cf/zai-org/glm-4.7-flash": {
             id: "workers-ai/@cf/zai-org/glm-4.7-flash",
@@ -3736,7 +4051,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -3760,10 +4075,48 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 256000,
         },
     },
     "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-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0.44,
+                output: 1.32,
+                cacheRead: 0.014,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 1048576,
+        },
+        "@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-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "@cf/google/gemma-4-26b-a4b-it": {
             id: "@cf/google/gemma-4-26b-a4b-it",
             name: "Gemma 4 26B A4B IT",
@@ -3962,6 +4315,24 @@ 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",
@@ -4094,6 +4465,24 @@ 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",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            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",
@@ -4752,6 +5141,25 @@ 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",
@@ -4953,10 +5361,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4999,6 +5407,25 @@ 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",
@@ -5366,9 +5793,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5401,9 +5828,9 @@ 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,
@@ -5418,9 +5845,9 @@ 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,
@@ -5903,6 +6330,24 @@ 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",
@@ -5957,6 +6402,24 @@ 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",
@@ -6065,6 +6528,42 @@ 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",
@@ -6183,13 +6682,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.95,
+                input: 0.15,
+                output: 0.95,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            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: 65536,
+            maxTokens: 131072,
         },
         "XiaomiMiMo/MiMo-V2-Flash": {
             id: "XiaomiMiMo/MiMo-V2-Flash",
@@ -6407,6 +6924,24 @@ 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",
@@ -6443,6 +6978,24 @@ 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",
@@ -6785,6 +7338,24 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "zai-org/GLM-4.6V-Flash": {
+            id: "zai-org/GLM-4.6V-Flash",
+            name: "GLM-4.6V-Flash",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 0.9,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
         "zai-org/GLM-4.7": {
             id: "zai-org/GLM-4.7",
             name: "GLM-4.7",
@@ -9077,24 +9648,6 @@ 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",
-            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",
@@ -9597,7 +10150,7 @@ 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",
@@ -9606,10 +10159,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             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,
@@ -9774,23 +10327,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "laguna-s-2.1-free": {
-            id: "laguna-s-2.1-free",
-            name: "Laguna S 2.1 Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 32000,
-        },
         "mimo-v2.5-free": {
             id: "mimo-v2.5-free",
             name: "MiMo V2.5 Free",
@@ -9859,6 +10395,42 @@ 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",
+            compat: { "sessionAffinityFormat": "openai-nosession" },
+            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",
+            compat: { "sessionAffinityFormat": "openai-nosession" },
+            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",
@@ -9927,11 +10499,28 @@ 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",
@@ -9939,9 +10528,27 @@ 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",
+            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,
@@ -9957,9 +10564,9 @@ 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,
@@ -9999,9 +10606,26 @@ 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",
@@ -10010,10 +10634,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -10038,16 +10662,16 @@ 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,
@@ -10174,6 +10798,41 @@ 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",
+            compat: { "sessionAffinityFormat": "openai-nosession" },
+            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",
@@ -10195,9 +10854,9 @@ 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: {
@@ -10212,9 +10871,9 @@ 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: {
@@ -10229,9 +10888,9 @@ 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: {
@@ -10245,23 +10904,6 @@ 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",
@@ -11149,13 +11791,13 @@ 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",
@@ -11166,13 +11808,13 @@ 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",
@@ -11218,8 +11860,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.13,
+                output: 1,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -11234,13 +11876,13 @@ 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",
@@ -11270,13 +11912,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.05866,
+                output: 0.11732,
+                cacheRead: 0.011732000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-flash-0731": {
             id: "deepseek/deepseek-v4-flash-0731",
@@ -11289,17 +11931,36 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.08,
+                output: 0.18,
+                cacheRead: 0.016,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 384000,
+        },
+        "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 },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
-            name: "DeepSeek: DeepSeek V4 Pro",
+            name: "DeepSeek: DeepSeek V4 Pro 0423",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -11308,13 +11969,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.1680000000000001,
-                output: 2.3360000000000003,
-                cacheRead: 0.09855000000000001,
+                input: 0.413772,
+                output: 0.827544,
+                cacheRead: 0.034481000000000005,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -11327,13 +11988,30 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.003625,
+                input: 1.122,
+                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",
@@ -11803,13 +12481,13 @@ 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",
@@ -12030,7 +12708,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 65536,
             maxTokens: 8192,
         },
         "meituan/longcat-2.0": {
@@ -12111,12 +12789,12 @@ 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",
@@ -12186,6 +12864,23 @@ 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",
@@ -12246,13 +12941,13 @@ 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",
@@ -12297,9 +12992,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 524288,
@@ -12535,12 +13230,12 @@ 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": {
@@ -12655,9 +13350,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.16,
+                input: 0.5415,
+                output: 2.2800000000000002,
+                cacheRead: 0.09119999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12674,7 +13369,7 @@ export const MODELS = {
             cost: {
                 input: 0.67,
                 output: 3.4,
-                cacheRead: 0.15,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12689,9 +13384,9 @@ 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,
@@ -12759,11 +13454,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
+            maxTokens: 262144,
         },
         "nvidia/nemotron-3-nano-30b-a3b:free": {
             id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -12859,9 +13554,9 @@ 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,
@@ -12893,13 +13588,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.25,
-                cacheRead: 0.049999999999999996,
+                input: 0.08,
+                output: 0.19999999999999998,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 262144,
+            contextWindow: 262144,
+            maxTokens: 131072,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -13899,10 +14594,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13917,10 +14612,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0.125,
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13971,10 +14666,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -13989,10 +14684,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14007,10 +14702,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             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,
@@ -14025,10 +14720,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             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,
@@ -14043,10 +14738,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14061,10 +14756,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14182,9 +14877,9 @@ 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,
@@ -14207,23 +14902,6 @@ 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",
@@ -14692,10 +15370,10 @@ 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,
@@ -14777,13 +15455,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.5,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -15015,9 +15693,9 @@ 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,
@@ -15134,13 +15812,13 @@ 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: 65536,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -15185,13 +15863,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3.5999999999999996,
-                cacheRead: 0.3,
+                input: 0.39,
+                output: 2.34,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -15287,7 +15965,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
@@ -15411,8 +16089,25 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1010000,
-            maxTokens: 262144,
+            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: 0.39999999999999997,
+                output: 3,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
         "qwen/qwen3.8-max": {
             id: "qwen/qwen3.8-max",
@@ -15516,6 +16211,23 @@ 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",
@@ -15576,9 +16288,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.063,
-                output: 0.21,
-                cacheRead: 0.020999999999999998,
+                input: 0.18,
+                output: 0.6,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -15632,7 +16344,24 @@ 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: 262144,
             maxTokens: 262144,
         },
         "thinkingmachines/inkling:batch": {
@@ -15644,14 +16373,31 @@ 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: 262144,
+            maxTokens: 262144,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -15939,7 +16685,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -15967,13 +16713,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1794,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -15984,13 +16730,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.63,
-                output: 1.9800000000000002,
-                cacheRead: 0.0945,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1932,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -16001,14 +16747,48 @@ 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",
@@ -16109,13 +16889,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.079996,
-                output: 0.252,
-                cacheRead: 0.0252,
+                input: 0.065,
+                output: 0.18,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 4096,
+            contextWindow: 1310720,
+            maxTokens: 1048576,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -16160,13 +16940,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.8,
-                output: 14,
+                input: 2.6,
+                output: 13,
                 cacheRead: 0.29,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 1048576,
+            maxTokens: 974842,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -16177,10 +16957,10 @@ 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,
@@ -16219,6 +16999,23 @@ 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,
+        },
     },
     "qwen-token-plan": {
         "MiniMax-M2.5": {
@@ -16314,6 +17111,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4-pro-0813": {
+            id: "deepseek-v4-pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "openai-completions",
+            provider: "qwen-token-plan",
+            baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
+            compat: { "thinkingFormat": "qwen", "supportsDeveloperRole": false, "supportsStore": false },
+            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: 1000000,
+            maxTokens: 384000,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -16625,6 +17441,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4-pro-0813": {
+            id: "deepseek-v4-pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "openai-completions",
+            provider: "qwen-token-plan-cn",
+            baseUrl: "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
+            compat: { "thinkingFormat": "qwen", "supportsDeveloperRole": false, "supportsStore": false },
+            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: 1000000,
+            maxTokens: 384000,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -16993,6 +17828,25 @@ 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",
@@ -17616,16 +18470,33 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.25,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "alibaba/qwen3.8-27b": {
+            id: "alibaba/qwen3.8-27b",
+            name: "Qwen3.8 27B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            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",
@@ -18180,9 +19051,9 @@ 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,
@@ -18197,9 +19068,26 @@ 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,
@@ -18231,9 +19119,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.0036,
+                input: 1.32,
+                output: 3.9600000000000004,
+                cacheRead: 0.13199999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -18384,9 +19272,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -19273,25 +20161,59 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 32000,
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            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,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 32768,
         },
-        "nvidia/nemotron-3-ultra-550b-a55b": {
-            id: "nvidia/nemotron-3-ultra-550b-a55b",
-            name: "Nemotron 3 Ultra",
+        "nvidia/nemotron-3.5-lightning-free": {
+            id: "nvidia/nemotron-3.5-lightning-free",
+            name: "Nemotron 3.5 Lightning 30B (Free)",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.12,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 65000,
+            maxTokens: 32768,
         },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
@@ -19378,6 +20300,23 @@ 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",
@@ -19395,6 +20334,23 @@ 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",
@@ -19412,6 +20368,23 @@ 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",
@@ -19429,6 +20402,23 @@ 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",
@@ -19446,6 +20436,23 @@ 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",
@@ -19480,6 +20487,23 @@ 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",
@@ -19497,6 +20521,23 @@ 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",
@@ -19599,6 +20640,23 @@ 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",
@@ -19635,6 +20693,24 @@ 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 ",
@@ -19671,6 +20747,24 @@ 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",
@@ -19689,6 +20783,24 @@ 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",
@@ -19707,6 +20819,24 @@ 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",
@@ -19761,6 +20891,24 @@ 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",
@@ -19797,6 +20945,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-luna-fast": {
+            id: "openai/gpt-5.6-luna-fast",
+            name: "GPT 5.6 Luna (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2.4,
+                cacheRead: 0.04,
+                cacheWrite: 0.25,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.6-sol": {
             id: "openai/gpt-5.6-sol",
             name: "GPT 5.6 Sol",
@@ -19807,10 +20973,28 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             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,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -19833,6 +21017,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-terra-fast": {
+            id: "openai/gpt-5.6-terra-fast",
+            name: "GPT 5.6 Terra (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 4,
+                output: 24,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -19918,18 +21120,35 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o3-deep-research": {
-            id: "openai/o3-deep-research",
-            name: "o3-deep-research",
+        "openai/o3-deep-research": {
+            id: "openai/o3-deep-research",
+            name: "o3-deep-research",
+            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,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "openai/o3-fast": {
+            id: "openai/o3-fast",
+            name: "o3 (Fast)",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 10,
-                output: 40,
-                cacheRead: 2.5,
+                input: 3.5,
+                output: 14,
+                cacheRead: 0.875,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -19986,6 +21205,23 @@ 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",
@@ -20054,93 +21290,8 @@ 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",
@@ -20156,8 +21307,8 @@ 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",
@@ -20173,8 +21324,8 @@ 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",
@@ -20190,8 +21341,8 @@ 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",
@@ -20207,8 +21358,8 @@ 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",
@@ -20224,8 +21375,8 @@ 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",
@@ -20241,8 +21392,8 @@ 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",
@@ -20258,8 +21409,8 @@ 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",
@@ -20275,8 +21426,8 @@ 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",
@@ -20292,8 +21443,8 @@ 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",
@@ -20309,14 +21460,14 @@ 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,
@@ -20326,8 +21477,8 @@ 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",
@@ -20343,6 +21494,91 @@ 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",
@@ -20445,40 +21681,6 @@ 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",
@@ -20590,9 +21792,9 @@ 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,
@@ -20615,6 +21817,23 @@ 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",
@@ -21134,6 +22353,24 @@ 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