@mariozechner/pi-ai 0.70.6 → 0.71.1

package/dist/models.generated.js

@@ -2539,6 +2539,23 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -2703,47 +2720,648 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.1,
-                output: 0.1,
-                cacheRead: 0,
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32000,
+            maxTokens: 8000,
+        },
+        "qwen-3-235b-a22b-instruct-2507": {
+            id: "qwen-3-235b-a22b-instruct-2507",
+            name: "Qwen 3 235B Instruct",
+            api: "openai-completions",
+            provider: "cerebras",
+            baseUrl: "https://api.cerebras.ai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 32000,
+        },
+        "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: false,
+            input: ["text"],
+            cost: {
+                input: 2.25,
+                output: 2.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 40000,
+        },
+    },
+    "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-haiku-4-5": {
+            id: "claude-haiku-4-5",
+            name: "Claude Haiku 4.5 (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: 1,
+                output: 5,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
+            },
+            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)",
+            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: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
+        "claude-opus-4-6": {
+            id: "claude-opus-4-6",
+            name: "Claude Opus 4.6 (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: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "claude-opus-4-7": {
+            id: "claude-opus-4-7",
+            name: "Claude Opus 4.7",
+            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: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            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)",
+            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-4-6": {
+            id: "claude-sonnet-4-6",
+            name: "Claude Sonnet 4.6",
+            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: 1000000,
+            maxTokens: 64000,
+        },
+        "gpt-4": {
+            id: "gpt-4",
+            name: "GPT-4",
+            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"],
+            cost: {
+                input: 30,
+                output: 60,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "gpt-4-turbo": {
+            id: "gpt-4-turbo",
+            name: "GPT-4 Turbo",
+            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: 10,
+                output: 30,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "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: 2.5,
+                output: 10,
+                cacheRead: 1.25,
+                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: 0.15,
+                output: 0.6,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "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",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.13,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.1-codex": {
+            id: "gpt-5.1-codex",
+            name: "GPT-5.1 Codex",
+            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: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.2": {
+            id: "gpt-5.2",
+            name: "GPT-5.2",
+            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: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.2-codex": {
+            id: "gpt-5.2-codex",
+            name: "GPT-5.2 Codex",
+            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: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.3-codex": {
+            id: "gpt-5.3-codex",
+            name: "GPT-5.3 Codex",
+            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: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4": {
+            id: "gpt-5.4",
+            name: "GPT-5.4",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            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: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "o1": {
+            id: "o1",
+            name: "o1",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 60,
+                cacheRead: 7.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3": {
+            id: "o3",
+            name: "o3",
+            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: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3-mini": {
+            id: "o3-mini",
+            name: "o3-mini",
+            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"],
+            cost: {
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3-pro": {
+            id: "o3-pro",
+            name: "o3-pro",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 20,
+                output: 80,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o4-mini": {
+            id: "o4-mini",
+            name: "o4-mini",
+            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: 1.1,
+                output: 4.4,
+                cacheRead: 0.28,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "workers-ai/@cf/moonshotai/kimi-k2.5": {
+            id: "workers-ai/@cf/moonshotai/kimi-k2.5",
+            name: "Kimi K2.5",
+            api: "openai-completions",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "workers-ai/@cf/moonshotai/kimi-k2.6": {
+            id: "workers-ai/@cf/moonshotai/kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "openai-completions",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
-            maxTokens: 8000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
+        "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: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.2,
+                input: 0.5,
+                output: 1.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 32000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
-        "zai-glm-4.7": {
-            id: "zai-glm-4.7",
-            name: "Z.AI GLM-4.7",
+        "workers-ai/@cf/zai-org/glm-4.7-flash": {
+            id: "workers-ai/@cf/zai-org/glm-4.7-flash",
+            name: "GLM-4.7-Flash",
             api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.25,
-                output: 2.75,
+                input: 0.06,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 40000,
+            maxTokens: 131072,
         },
     },
     "cloudflare-workers-ai": {
@@ -2905,7 +3523,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -2921,9 +3539,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -3239,7 +3857,7 @@ export const MODELS = {
         },
         "accounts/fireworks/routers/kimi-k2p5-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p5-turbo",
-            name: "Kimi K2.5 Turbo (firepass)",
+            name: "Kimi K2.5 Turbo",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4161,288 +4779,12 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
-        "gemma-4-26b-a4b-it": {
-            id: "gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 8192,
-        },
-        "gemma-4-31b-it": {
-            id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 8192,
-        },
-    },
-    "google-antigravity": {
-        "claude-opus-4-5-thinking": {
-            id: "claude-opus-4-5-thinking",
-            name: "Claude Opus 4.5 Thinking (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-opus-4-6-thinking": {
-            id: "claude-opus-4-6-thinking",
-            name: "Claude Opus 4.6 Thinking (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
-            contextWindow: 200000,
-            maxTokens: 128000,
-        },
-        "claude-sonnet-4-5": {
-            id: "claude-sonnet-4-5",
-            name: "Claude Sonnet 4.5 (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-sonnet-4-5-thinking": {
-            id: "claude-sonnet-4-5-thinking",
-            name: "Claude Sonnet 4.5 Thinking (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "claude-sonnet-4-6": {
-            id: "claude-sonnet-4-6",
-            name: "Claude Sonnet 4.6 (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "gemini-3-flash": {
-            id: "gemini-3-flash",
-            name: "Gemini 3 Flash (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-3.1-pro-high": {
-            id: "gemini-3.1-pro-high",
-            name: "Gemini 3.1 Pro High (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 2.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-3.1-pro-low": {
-            id: "gemini-3.1-pro-low",
-            name: "Gemini 3.1 Pro Low (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 2.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gpt-oss-120b-medium": {
-            id: "gpt-oss-120b-medium",
-            name: "GPT-OSS 120B Medium (Antigravity)",
-            api: "google-gemini-cli",
-            provider: "google-antigravity",
-            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09,
-                output: 0.36,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-    },
-    "google-gemini-cli": {
-        "gemini-2.0-flash": {
-            id: "gemini-2.0-flash",
-            name: "Gemini 2.0 Flash (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
-        "gemini-2.5-flash": {
-            id: "gemini-2.5-flash",
-            name: "Gemini 2.5 Flash (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-2.5-pro": {
-            id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "gemini-3.1-flash-lite-preview": {
-            id: "gemini-3.1-flash-lite-preview",
-            name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
+        "gemma-4-26b-a4b-it": {
+            id: "gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -4451,15 +4793,15 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65535,
+            contextWindow: 256000,
+            maxTokens: 8192,
         },
-        "gemini-3.1-pro-preview": {
-            id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
-            api: "google-gemini-cli",
-            provider: "google-gemini-cli",
-            baseUrl: "https://cloudcode-pa.googleapis.com",
+        "gemma-4-31b-it": {
+            id: "gemma-4-31b-it",
+            name: "Gemma 4 31B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -4468,8 +4810,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65535,
+            contextWindow: 256000,
+            maxTokens: 8192,
         },
     },
     "google-vertex": {
@@ -5802,22 +6144,56 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "mistral-medium-2604": {
+            id: "mistral-medium-2604",
+            name: "Mistral Medium 3.5",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "mistral-medium-3.5": {
+            id: "mistral-medium-3.5",
+            name: "Mistral Medium 3.5",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "mistral-medium-latest": {
             id: "mistral-medium-latest",
             name: "Mistral Medium (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
+                input: 1.5,
+                output: 7.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "mistral-nemo": {
             id: "mistral-nemo",
@@ -5964,13 +6340,269 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0,
+                input: 2,
+                output: 6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
+    },
+    "moonshotai": {
+        "kimi-k2-0711-preview": {
+            id: "kimi-k2-0711-preview",
+            name: "Kimi K2 0711",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+        "kimi-k2-0905-preview": {
+            id: "kimi-k2-0905-preview",
+            name: "Kimi K2 0905",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-thinking": {
+            id: "kimi-k2-thinking",
+            name: "Kimi K2 Thinking",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-thinking-turbo": {
+            id: "kimi-k2-thinking-turbo",
+            name: "Kimi K2 Thinking Turbo",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-turbo-preview": {
+            id: "kimi-k2-turbo-preview",
+            name: "Kimi K2 Turbo",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2.4,
+                output: 10,
+                cacheRead: 0.6,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2.5": {
+            id: "kimi-k2.5",
+            name: "Kimi K2.5",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2.6": {
+            id: "kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+    },
+    "moonshotai-cn": {
+        "kimi-k2-0711-preview": {
+            id: "kimi-k2-0711-preview",
+            name: "Kimi K2 0711",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+        "kimi-k2-0905-preview": {
+            id: "kimi-k2-0905-preview",
+            name: "Kimi K2 0905",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-thinking": {
+            id: "kimi-k2-thinking",
+            name: "Kimi K2 Thinking",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-thinking-turbo": {
+            id: "kimi-k2-thinking-turbo",
+            name: "Kimi K2 Thinking Turbo",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2-turbo-preview": {
+            id: "kimi-k2-turbo-preview",
+            name: "Kimi K2 Turbo",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2.4,
+                output: 10,
+                cacheRead: 0.6,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2.5": {
+            id: "kimi-k2.5",
+            name: "Kimi K2.5",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2.6": {
+            id: "kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 128000,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
     },
     "openai": {
@@ -6535,6 +7167,23 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -7389,23 +8038,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "ling-2.6-flash-free": {
-            id: "ling-2.6-flash-free",
-            name: "Ling 2.6 Flash Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262100,
-            maxTokens: 32800,
-        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -7516,7 +8148,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -7534,7 +8166,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8489,7 +9121,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8507,7 +9139,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8842,6 +9474,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "ibm-granite/granite-4.1-8b": {
+            id: "ibm-granite/granite-4.1-8b",
+            name: "IBM: Granite 4.1 8B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.09999999999999999,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Inception: Mercury 2",
@@ -8876,18 +9525,18 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ling-2.6-flash:free": {
-            id: "inclusionai/ling-2.6-flash:free",
-            name: "inclusionAI: Ling-2.6-flash (free)",
+        "inclusionai/ling-2.6-flash": {
+            id: "inclusionai/ling-2.6-flash",
+            name: "inclusionAI: Ling-2.6-flash",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.24,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9345,12 +9994,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.04,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -9403,23 +10052,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "mistralai/mistral-small-creative": {
-            id: "mistralai/mistral-small-creative",
-            name: "Mistral: Mistral Small Creative",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 4096,
-        },
         "mistralai/mixtral-8x22b-instruct": {
             id: "mistralai/mixtral-8x22b-instruct",
             name: "Mistral: Mixtral 8x22B Instruct",
@@ -9565,13 +10197,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.7448,
-                output: 4.655,
-                cacheRead: 0.1463,
+                input: 0.74,
+                output: 3.49,
+                cacheRead: 0.14,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 65536,
+            contextWindow: 262142,
+            maxTokens: 262142,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10484,12 +11116,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.039,
-                output: 0.19,
+                output: 0.18,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "openai/gpt-oss-120b:free": {
             id: "openai/gpt-oss-120b:free",
@@ -10746,6 +11378,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
+        "openrouter/owl-alpha": {
+            id: "openrouter/owl-alpha",
+            name: "Owl Alpha",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048756,
+            maxTokens: 262144,
+        },
         "poolside/laguna-m.1:free": {
             id: "poolside/laguna-m.1:free",
             name: "Poolside: Laguna M.1 (free)",
@@ -11146,9 +11795,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.14,
+                input: 0.12,
                 output: 0.7999999999999999,
-                cacheRead: 0.09,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11596,23 +12245,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwq-32b": {
-            id: "qwen/qwq-32b",
-            name: "Qwen: QwQ 32B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.58,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -11911,14 +12543,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
             maxTokens: 4096,
         },
+        "x-ai/grok-4.3": {
+            id: "x-ai/grok-4.3",
+            name: "xAI: Grok 4.3",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 4096,
+        },
         "x-ai/grok-code-fast-1": {
             id: "x-ai/grok-code-fast-1",
             name: "xAI: Grok Code Fast 1",
@@ -12336,13 +12985,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.7448,
-                output: 4.655,
-                cacheRead: 0.1463,
+                input: 0.74,
+                output: 3.49,
+                cacheRead: 0.14,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 65536,
+            contextWindow: 262142,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12467,20 +13116,20 @@ export const MODELS = {
         },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
-            name: "Qwen3 235B A22B Thinking 2507",
+            name: "Qwen3 VL 235B A22B Thinking",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22999999999999998,
-                output: 2.3,
-                cacheRead: 0.19999999999999998,
+                input: 0.39999999999999997,
+                output: 4,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262114,
-            maxTokens: 262114,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "alibaba/qwen3-coder": {
             id: "alibaba/qwen3-coder",
@@ -12652,6 +13301,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.6-27b": {
+            id: "alibaba/qwen3.6-27b",
+            name: "Qwen 3.6 27B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "alibaba/qwen3.6-plus": {
             id: "alibaba/qwen3.6-plus",
             name: "Qwen 3.6 Plus",
@@ -13032,16 +13698,16 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.28,
-                output: 0.42,
-                cacheRead: 0.028,
+                input: 0.62,
+                output: 1.85,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 64000,
+            maxTokens: 8000,
         },
         "deepseek/deepseek-v4-flash": {
             id: "deepseek/deepseek-v4-flash",
@@ -14556,23 +15222,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
-        "prime-intellect/intellect-3": {
-            id: "prime-intellect/intellect-3",
-            name: "INTELLECT 3",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 1.1,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "xai/grok-3": {
             id: "xai/grok-3",
             name: "Grok 3 Beta",
@@ -14828,6 +15477,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
+        "xai/grok-4.3": {
+            id: "xai/grok-4.3",
+            name: "Grok 4.3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "xai/grok-code-fast-1": {
             id: "xai/grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -14879,6 +15545,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "xiaomi/mimo-v2.5": {
+            id: "xiaomi/mimo-v2.5",
+            name: "MiMo M2.5",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 131100,
+        },
+        "xiaomi/mimo-v2.5-pro": {
+            id: "xiaomi/mimo-v2.5-pro",
+            name: "MiMo V2.5 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 131000,
+        },
         "zai/glm-4.5": {
             id: "zai/glm-4.5",
             name: "GLM-4.5",
@@ -15459,6 +16159,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "grok-4.3": {
+            id: "grok-4.3",
+            name: "Grok 4.3",
+            api: "openai-completions",
+            provider: "xai",
+            baseUrl: "https://api.x.ai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 30000,
+        },
         "grok-beta": {
             id: "grok-beta",
             name: "Grok Beta",
@@ -15584,6 +16301,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5v-turbo": {
+            id: "glm-5v-turbo",
+            name: "glm-5v-turbo",
+            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", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
     },
 };
 //# sourceMappingURL=models.generated.js.map