omk-ai 0.98.0 → 0.98.2

package/dist/models.generated.js

@@ -77,6 +77,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -87,6 +88,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-fable-5-1": {
+            id: "anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5",
@@ -441,6 +460,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 11,
@@ -615,6 +635,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -625,6 +646,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-fable-5-1": {
+            id: "global.anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (Global)",
@@ -1703,6 +1742,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -1713,6 +1753,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-fable-5-1": {
+            id: "us.anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 11,
+                output: 55,
+                cacheRead: 0.275,
+                cacheWrite: 13.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (US)",
@@ -2123,7 +2181,9 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -2134,6 +2194,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-fable-5-1": {
+            id: "claude-fable-5-1",
+            name: "Claude Fable 5.1",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5 (latest)",
@@ -3114,7 +3193,9 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -3952,6 +4033,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 256000,
         },
+        "@cf/zai-org/glm-5.3": {
+            id: "@cf/zai-org/glm-5.3",
+            name: "Glm 5.3",
+            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: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 1310720,
+        },
         "@cf/zai-org/glm-5.3-flash": {
             id: "@cf/zai-org/glm-5.3-flash",
             name: "Glm 5.3 Flash",
@@ -3969,7 +4069,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 1310720,
+            maxTokens: 1048576,
         },
     },
     "deepseek": {
@@ -4013,24 +4113,6 @@ export const MODELS = {
         },
     },
     "fireworks": {
-        "accounts/fireworks/models/deepseek-v4-flash": {
-            id: "accounts/fireworks/models/deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
-            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: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 384000,
-        },
         "accounts/fireworks/models/deepseek-v4-flash-0731": {
             id: "accounts/fireworks/models/deepseek-v4-flash-0731",
             name: "DeepSeek V4 Flash 0731",
@@ -4041,9 +4123,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -4086,6 +4168,44 @@ export const MODELS = {
             contextWindow: 1048575,
             maxTokens: 131072,
         },
+        "accounts/fireworks/models/glm-5p3": {
+            id: "accounts/fireworks/models/glm-5p3",
+            name: "GLM 5.3",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/glm-5p3-flash": {
+            id: "accounts/fireworks/models/glm-5p3-flash",
+            name: "GLM 5.3 Flash",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.029,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/models/gpt-oss-120b": {
             id: "accounts/fireworks/models/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -4334,6 +4454,7 @@ export const MODELS = {
             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,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -5292,23 +5413,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-robotics-er-1.6-preview": {
-            id: "gemini-robotics-er-1.6-preview",
-            name: "Gemini Robotics-ER 1.6 Preview",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
         "gemma-4-26b-a4b-it": {
             id: "gemma-4-26b-a4b-it",
             name: "Gemma 4 26B A4B IT",
@@ -5695,6 +5799,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "qwen/qwen3.8-27b": {
+            id: "qwen/qwen3.8-27b",
+            name: "Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max", "minimal": null, "low": null, "medium": null, "high": "default" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.8,
+                output: 4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131042,
+            maxTokens: 16384,
+        },
     },
     "huggingface": {
         "MiniMaxAI/MiniMax-M2": {
@@ -6936,6 +7058,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "zai-org/GLM-5.3": {
+            id: "zai-org/GLM-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "zai-org/GLM-5.3-Flash": {
             id: "zai-org/GLM-5.3-Flash",
             name: "GLM-5.3-Flash",
@@ -6945,7 +7086,7 @@ export const MODELS = {
             compat: { "supportsDeveloperRole": false },
             reasoning: true,
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.5,
@@ -8320,25 +8461,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "nvidia/nemotron-3-nano-30b-a3b": {
-            id: "nvidia/nemotron-3-nano-30b-a3b",
-            name: "nemotron-3-nano-30b-a3b",
-            api: "openai-completions",
-            provider: "nvidia",
-            baseUrl: "https://integrate.api.nvidia.com/v1",
-            headers: { "NVCF-POLL-SECONDS": "3600" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
             name: "Nemotron 3 Nano Omni",
@@ -8472,25 +8594,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
-        "stepfun-ai/step-3.7-flash": {
-            id: "stepfun-ai/step-3.7-flash",
-            name: "Step 3.7 Flash",
-            api: "openai-completions",
-            provider: "nvidia",
-            baseUrl: "https://integrate.api.nvidia.com/v1",
-            headers: { "NVCF-POLL-SECONDS": "3600" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 16384,
-        },
     },
     "openai": {
         "gpt-4": {
@@ -9385,7 +9488,9 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -10168,23 +10273,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
-        "hy3-free": {
-            id: "hy3-free",
-            name: "Hy3 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: 190000,
-            maxTokens: 64000,
-        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -10254,27 +10342,44 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "mimo-v2.5-free": {
-            id: "mimo-v2.5-free",
-            name: "MiMo V2.5 Free",
+        "ling-3.0-flash-fin-free": {
+            id: "ling-3.0-flash-fin-free",
+            name: "Ling 3.0 Flash Fin Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0,
                 output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 32000,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
-        "minimax-m2.5": {
-            id: "minimax-m2.5",
-            name: "MiniMax-M2.5",
-            api: "openai-completions",
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
+            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: 200000,
+            maxTokens: 32000,
+        },
+        "minimax-m2.5": {
+            id: "minimax-m2.5",
+            name: "MiniMax-M2.5",
+            api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
@@ -10594,21 +10699,38 @@ export const MODELS = {
         },
         "hy3": {
             id: "hy3",
-            name: "Hy3 (8x usage)",
+            name: "Hy3",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.0175,
-                output: 0.0725,
-                cacheRead: 0.004375,
+                input: 0.14,
+                output: 0.58,
+                cacheRead: 0.035,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
             maxTokens: 64000,
         },
+        "hy4-preview": {
+            id: "hy4-preview",
+            name: "Hy4 preview",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0.042,
+                cacheWrite: 0,
+            },
+            contextWindow: 1024000,
+            maxTokens: 64000,
+        },
         "kimi-k2.6": {
             id: "kimi-k2.6",
             name: "Kimi K2.6",
@@ -11017,6 +11139,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -11027,6 +11150,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-fable-5.1": {
+            id: "anthropic/claude-fable-5.1",
+            name: "Anthropic: Claude Fable 5.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-fable-5:batch": {
             id: "anthropic/claude-fable-5:batch",
             name: "Anthropic: Claude Fable 5 (batch)",
@@ -11034,6 +11175,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -11217,24 +11359,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.7-fast": {
-            id: "anthropic/claude-opus-4.7-fast",
-            name: "Anthropic: Claude Opus 4.7 (Fast)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
-            input: ["text", "image"],
-            cost: {
-                input: 30,
-                output: 150,
-                cacheRead: 3,
-                cacheWrite: 37.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.7:batch": {
             id: "anthropic/claude-opus-4.7:batch",
             name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -11271,24 +11395,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.8-fast": {
-            id: "anthropic/claude-opus-4.8-fast",
-            name: "Anthropic: Claude Opus 4.8 (Fast)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.8:batch": {
             id: "anthropic/claude-opus-4.8:batch",
             name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -11324,23 +11430,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-5-fast": {
-            id: "anthropic/claude-opus-5-fast",
-            name: "Claude Opus 5 (Fast)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-5:batch": {
             id: "anthropic/claude-opus-5:batch",
             name: "Claude Opus 5 (batch)",
@@ -11488,30 +11577,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.85,
+                input: 0.25,
+                output: 0.7999999999999999,
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
-        },
-        "arcee-ai/virtuoso-large": {
-            id: "arcee-ai/virtuoso-large",
-            name: "Arcee AI: Virtuoso Large",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.75,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 64000,
+            maxTokens: 80000,
         },
         "auto": {
             id: "auto",
@@ -11726,13 +11798,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 1.6500000000000001,
-                cacheRead: 0.55,
+                input: 0.25,
+                output: 0.95,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 144900,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -11794,13 +11866,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.26899999999999996,
+                output: 0.39999999999999997,
+                cacheRead: 0.13449999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 147456,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -11849,14 +11921,33 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.14,
-                cacheRead: 0.014,
+                input: 0.065,
+                output: 0.18,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
             maxTokens: 943718,
         },
+        "deepseek/deepseek-v4-flash-0731:batch": {
+            id: "deepseek/deepseek-v4-flash-0731:batch",
+            name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
+            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"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
+        },
         "deepseek/deepseek-v4-flash-vision-exp": {
             id: "deepseek/deepseek-v4-flash-vision-exp",
             name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -11887,9 +11978,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.87,
-                output: 1.74,
-                cacheRead: 0.0725,
+                input: 1.04226,
+                output: 2.08452,
+                cacheRead: 0.086855,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11905,14 +11996,33 @@ export const MODELS = {
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
+            cost: {
+                input: 1.1154,
+                output: 3.3461999999999996,
+                cacheRead: 0.03718,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro-0813:batch": {
+            id: "deepseek/deepseek-v4-pro-0813:batch",
+            name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
+            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"],
             cost: {
                 input: 1.32,
                 output: 3.9600000000000004,
-                cacheRead: 0.044,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 943718,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -12331,10 +12441,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.375,
-                output: 1.875,
-                cacheRead: 0.0375,
-                cacheWrite: 0.0208333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -12387,7 +12497,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 131072,
             maxTokens: 117964,
         },
         "google/gemma-4-26b-a4b-it": {
@@ -12441,6 +12551,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
+        "google/gemma-4-31b-it:batch": {
+            id: "google/gemma-4-31b-it:batch",
+            name: "Google: Gemma 4 31B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39,
+                output: 0.9700000000000001,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
+        },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
             name: "Google: Gemma 4 31B (free)",
@@ -12475,6 +12602,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 117964,
         },
+        "ibm-granite/granite-4.2-8b": {
+            id: "ibm-granite/granite-4.2-8b",
+            name: "IBM: Granite 4.2 8B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.15,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 117964,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Inception: Mercury 2",
@@ -12493,6 +12637,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
+        "inception/mercury-2.5-preview": {
+            id: "inception/mercury-2.5-preview",
+            name: "Inception: Mercury 2.5 Preview",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text"],
+            cost: {
+                input: 0.04,
+                output: 0.15,
+                cacheRead: 0.004,
+                cacheWrite: 0,
+            },
+            contextWindow: 260000,
+            maxTokens: 65536,
+        },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
             name: "Ling-3.0-flash",
@@ -12527,23 +12689,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kwaipilot/kat-coder-air-v2.5": {
-            id: "kwaipilot/kat-coder-air-v2.5",
-            name: "Kwaipilot: KAT-Coder-Air V2.5",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 80000,
-        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -12559,7 +12704,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 80000,
+            maxTokens: 144000,
         },
         "kwaipilot/kat-coder-pro-v2.5": {
             id: "kwaipilot/kat-coder-pro-v2.5",
@@ -12576,7 +12721,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 80000,
+            maxTokens: 235929,
         },
         "liquid/lfm-2.5-2.6b:free": {
             id: "liquid/lfm-2.5-2.6b:free",
@@ -12673,12 +12818,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
-                output: 0.7999999999999999,
+                output: 0.696,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 115200,
         },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
@@ -12689,13 +12834,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.11,
-                output: 0.33999999999999997,
-                cacheRead: 0.055,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "meta/muse-glimmer-30b": {
             id: "meta/muse-glimmer-30b",
@@ -12706,13 +12851,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.35,
-                output: 1.5,
+                input: 0.3,
+                output: 1.2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 117964,
+            maxTokens: 16384,
+        },
+        "meta/muse-glimmer-30b:batch": {
+            id: "meta/muse-glimmer-30b:batch",
+            name: "Meta: Muse Glimmer 30B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.35,
+                output: 1.5,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 117964,
         },
         "meta/muse-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -12944,9 +13106,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.44,
-                output: 2.2,
-                cacheRead: 0.044,
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13088,6 +13250,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
+        "mistralai/mistral-medium-3-5:batch": {
+            id: "mistralai/mistral-medium-3-5:batch",
+            name: "Mistral: Mistral Medium 3.5 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 209715,
+        },
         "mistralai/mistral-medium-3.1": {
             id: "mistralai/mistral-medium-3.1",
             name: "Mistral: Mistral Medium 3.1",
@@ -13204,8 +13383,8 @@ export const MODELS = {
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
-            maxTokens: 25600,
+            contextWindow: 32768,
+            maxTokens: 26214,
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
@@ -13327,6 +13506,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "moonshotai/kimi-k3:batch": {
+            id: "moonshotai/kimi-k3:batch",
+            name: "MoonshotAI: Kimi K3 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
+        },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
             name: "Nex AGI: Nex-N2-Mini",
@@ -13438,13 +13634,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.2,
-                cacheRead: 0.09999999999999999,
+                input: 0.625,
+                output: 3.125,
+                cacheRead: 0.1875,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:batch": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -13489,13 +13685,13 @@ 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: 262144,
-            maxTokens: 235929,
+            maxTokens: 131072,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -13565,6 +13761,23 @@ export const MODELS = {
             contextWindow: 16385,
             maxTokens: 4096,
         },
+        "openai/gpt-3.5-turbo:batch": {
+            id: "openai/gpt-3.5-turbo:batch",
+            name: "OpenAI: GPT-3.5 Turbo (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.25,
+                output: 0.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 16385,
+            maxTokens: 4096,
+        },
         "openai/gpt-4": {
             id: "openai/gpt-4",
             name: "OpenAI: GPT-4",
@@ -13616,6 +13829,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "openai/gpt-4-turbo:batch": {
+            id: "openai/gpt-4-turbo:batch",
+            name: "OpenAI: GPT-4 Turbo (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
         "openai/gpt-4.1": {
             id: "openai/gpt-4.1",
             name: "OpenAI: GPT-4.1",
@@ -13650,6 +13880,23 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
+        "openai/gpt-4.1-mini:batch": {
+            id: "openai/gpt-4.1-mini:batch",
+            name: "OpenAI: GPT-4.1 Mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 0.7999999999999999,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
             name: "OpenAI: GPT-4.1 Nano",
@@ -13667,6 +13914,40 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
+        "openai/gpt-4.1-nano:batch": {
+            id: "openai/gpt-4.1-nano:batch",
+            name: "OpenAI: GPT-4.1 Nano (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.19999999999999998,
+                cacheRead: 0.012499999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
+        "openai/gpt-4.1:batch": {
+            id: "openai/gpt-4.1:batch",
+            name: "OpenAI: GPT-4.1 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
         "openai/gpt-4o": {
             id: "openai/gpt-4o",
             name: "OpenAI: GPT-4o",
@@ -13769,6 +14050,40 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai/gpt-4o-mini:batch": {
+            id: "openai/gpt-4o-mini:batch",
+            name: "OpenAI: GPT-4o-mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.0375,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "openai/gpt-4o:batch": {
+            id: "openai/gpt-4o:batch",
+            name: "OpenAI: GPT-4o (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 5,
+                cacheRead: 0.625,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai/gpt-5": {
             id: "openai/gpt-5",
             name: "OpenAI: GPT-5",
@@ -13803,6 +14118,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5-mini:batch": {
+            id: "openai/gpt-5-mini:batch",
+            name: "OpenAI: GPT-5 Mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.125,
+                output: 1,
+                cacheRead: 0.012499999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
             name: "OpenAI: GPT-5 Nano",
@@ -13820,6 +14152,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5-nano:batch": {
+            id: "openai/gpt-5-nano:batch",
+            name: "OpenAI: GPT-5 Nano (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.024999999999999998,
+                output: 0.19999999999999998,
+                cacheRead: 0.0025,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5-pro": {
             id: "openai/gpt-5-pro",
             name: "OpenAI: GPT-5 Pro",
@@ -13837,6 +14186,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5-pro:batch": {
+            id: "openai/gpt-5-pro:batch",
+            name: "OpenAI: GPT-5 Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 7.5,
+                output: 60,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.1": {
             id: "openai/gpt-5.1",
             name: "OpenAI: GPT-5.1",
@@ -13905,6 +14271,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.1:batch": {
+            id: "openai/gpt-5.1:batch",
+            name: "OpenAI: GPT-5.1 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.625,
+                output: 5,
+                cacheRead: 0.0625,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
             name: "OpenAI: GPT-5.2",
@@ -13977,6 +14360,42 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.2-pro:batch": {
+            id: "openai/gpt-5.2-pro:batch",
+            name: "OpenAI: GPT-5.2 Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10.5,
+                output: 84,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.2:batch": {
+            id: "openai/gpt-5.2:batch",
+            name: "OpenAI: GPT-5.2 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.875,
+                output: 7,
+                cacheRead: 0.0875,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.3-codex": {
             id: "openai/gpt-5.3-codex",
             name: "OpenAI: GPT-5.3-Codex",
@@ -14031,6 +14450,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-mini:batch": {
+            id: "openai/gpt-5.4-mini:batch",
+            name: "OpenAI: GPT-5.4 Mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.375,
+                output: 2.25,
+                cacheRead: 0.0375,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-nano": {
             id: "openai/gpt-5.4-nano",
             name: "OpenAI: GPT-5.4 Nano",
@@ -14049,6 +14486,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-nano:batch": {
+            id: "openai/gpt-5.4-nano:batch",
+            name: "OpenAI: GPT-5.4 Nano (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.625,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "OpenAI: GPT-5.4 Pro",
@@ -14067,6 +14522,42 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-pro:batch": {
+            id: "openai/gpt-5.4-pro:batch",
+            name: "OpenAI: GPT-5.4 Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 90,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.4:batch": {
+            id: "openai/gpt-5.4:batch",
+            name: "OpenAI: GPT-5.4 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 7.5,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.5": {
             id: "openai/gpt-5.5",
             name: "OpenAI: GPT-5.5",
@@ -14103,6 +14594,42 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.5-pro:batch": {
+            id: "openai/gpt-5.5-pro:batch",
+            name: "OpenAI: GPT-5.5 Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 90,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.5:batch": {
+            id: "openai/gpt-5.5:batch",
+            name: "OpenAI: GPT-5.5 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.6-luna": {
             id: "openai/gpt-5.6-luna",
             name: "OpenAI: GPT-5.6 Luna",
@@ -14139,6 +14666,42 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-luna-pro:batch": {
+            id: "openai/gpt-5.6-luna-pro:batch",
+            name: "OpenAI: GPT-5.6 Luna Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.6-luna:batch": {
+            id: "openai/gpt-5.6-luna:batch",
+            name: "OpenAI: GPT-5.6 Luna (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.6-sol": {
             id: "openai/gpt-5.6-sol",
             name: "OpenAI: GPT-5.6 Sol",
@@ -14175,6 +14738,42 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-sol-pro:batch": {
+            id: "openai/gpt-5.6-sol-pro:batch",
+            name: "OpenAI: GPT-5.6 Sol Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.6-sol:batch": {
+            id: "openai/gpt-5.6-sol:batch",
+            name: "OpenAI: GPT-5.6 Sol (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.6-terra": {
             id: "openai/gpt-5.6-terra",
             name: "OpenAI: GPT-5.6 Terra",
@@ -14211,6 +14810,59 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.6-terra-pro:batch": {
+            id: "openai/gpt-5.6-terra-pro:batch",
+            name: "OpenAI: GPT-5.6 Terra Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 6,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.6-terra:batch": {
+            id: "openai/gpt-5.6-terra:batch",
+            name: "OpenAI: GPT-5.6 Terra (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 6,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5:batch": {
+            id: "openai/gpt-5:batch",
+            name: "OpenAI: GPT-5 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.625,
+                output: 5,
+                cacheRead: 0.0625,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-audio": {
             id: "openai/gpt-audio",
             name: "OpenAI: GPT Audio",
@@ -14279,6 +14931,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 117964,
         },
+        "openai/gpt-oss-120b:batch": {
+            id: "openai/gpt-oss-120b:batch",
+            name: "OpenAI: gpt-oss-120b (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 117964,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "OpenAI: gpt-oss-20b",
@@ -14381,6 +15050,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "openai/o3-mini:batch": {
+            id: "openai/o3-mini:batch",
+            name: "OpenAI: o3 Mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.55,
+                output: 2.2,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "openai/o3-pro": {
             id: "openai/o3-pro",
             name: "OpenAI: o3 Pro",
@@ -14398,6 +15084,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "openai/o3:batch": {
+            id: "openai/o3:batch",
+            name: "OpenAI: o3 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "openai/o4-mini": {
             id: "openai/o4-mini",
             name: "OpenAI: o4 Mini",
@@ -14432,6 +15135,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
+        "openai/o4-mini:batch": {
+            id: "openai/o4-mini:batch",
+            name: "OpenAI: o4 Mini (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.55,
+                output: 2.2,
+                cacheRead: 0.1375,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
         "openrouter/auto": {
             id: "openrouter/auto",
             name: "Auto Router",
@@ -14978,13 +15698,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 16384,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -15066,13 +15786,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.26,
-                output: 2.08,
+                input: 0.29,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -15146,6 +15866,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 235929,
         },
+        "qwen/qwen3.5-9b:batch": {
+            id: "qwen/qwen3.5-9b:batch",
+            name: "Qwen: Qwen3.5-9B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.16999999999999998,
+                output: 0.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
+        },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
             name: "Qwen: Qwen3.5-Flash",
@@ -15356,11 +16094,29 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.25,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
+        },
+        "qwen/qwen3.8-2.4t-a95b:batch": {
+            id: "qwen/qwen3.8-2.4t-a95b:batch",
+            name: "Qwen: Qwen3.8 2.4T A95B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1010000,
+            maxTokens: 909000,
         },
         "qwen/qwen3.8-27b": {
             id: "qwen/qwen3.8-27b",
@@ -15612,13 +16368,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
+                input: 1,
                 output: 4.05,
-                cacheRead: 0.16,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 471859,
         },
         "thinkingmachines/inkling-small": {
             id: "thinkingmachines/inkling-small",
@@ -15637,6 +16393,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "thinkingmachines/inkling-small:batch": {
+            id: "thinkingmachines/inkling-small:batch",
+            name: "Thinking Machines: Inkling Small (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 471859,
+        },
         "thinkingmachines/inkling-small:free": {
             id: "thinkingmachines/inkling-small:free",
             name: "Thinking Machines: Inkling Small (free)",
@@ -16004,13 +16777,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.26,
-                output: 3.9600000000000004,
-                cacheRead: 0.234,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1794,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 182476,
+            maxTokens: 128000,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -16022,13 +16795,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
             input: ["text"],
             cost: {
-                input: 1.19,
-                output: 3.74,
-                cacheRead: 0.221,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1932,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.2:free": {
             id: "z-ai/glm-5.2:free",
@@ -16063,7 +16836,7 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1310720,
             maxTokens: 131072,
         },
         "z-ai/glm-5.3-flash": {
@@ -16084,6 +16857,24 @@ export const MODELS = {
             contextWindow: 1310720,
             maxTokens: 131072,
         },
+        "z-ai/glm-5.3-flash:batch": {
+            id: "z-ai/glm-5.3-flash:batch",
+            name: "Z.ai: GLM 5.3 Flash (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048575,
+            maxTokens: 943717,
+        },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
             name: "Z.ai: GLM 5V Turbo",
@@ -16108,11 +16899,12 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
                 output: 50,
-                cacheRead: 1,
+                cacheRead: 0.25,
                 cacheWrite: 12.5,
             },
             contextWindow: 1000000,
@@ -16180,13 +16972,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.03,
-                output: 0.09999999999999999,
-                cacheRead: 0.007,
+                input: 0.049999999999999996,
+                output: 0.16,
+                cacheRead: 0.013000000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 393216,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -16197,10 +16989,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.375,
-                output: 1.875,
-                cacheRead: 0.0375,
-                cacheWrite: 0.0208333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -16291,6 +17083,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 450000,
         },
+        "~z-ai/glm-flash-latest": {
+            id: "~z-ai/glm-flash-latest",
+            name: "Z.ai: GLM Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.25,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 131072,
+        },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
             name: "Z.ai: GLM Latest",
@@ -16300,13 +17109,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.17,
+                output: 3.9600000000000004,
+                cacheRead: 0.234,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 131072,
+            contextWindow: 1310720,
+            maxTokens: 943718,
         },
     },
     "together": {
@@ -16668,6 +17477,25 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 164000,
         },
+        "zai-org/GLM-5.3": {
+            id: "zai-org/GLM-5.3",
+            name: "GLM-5.3",
+            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": "low", "medium": "medium", "off": null, "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
         "zai-org/GLM-5.3-Flash": {
             id: "zai-org/GLM-5.3-Flash",
             name: "GLM-5.3-Flash",
@@ -17142,11 +17970,11 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "alibaba/qwen3.8-27b": {
             id: "alibaba/qwen3.8-27b",
@@ -17158,10 +17986,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.55,
-                output: 3.3000000000000003,
-                cacheRead: 0.11,
-                cacheWrite: 0,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0.625,
             },
             contextWindow: 1000000,
             maxTokens: 131072,
@@ -17184,6 +18012,24 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 128000,
         },
+        "alibaba/qwen3.8-flash-next": {
+            id: "alibaba/qwen3.8-flash-next",
+            name: "Qwen 3.8 Flash Next",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.12,
+                output: 0.39999999999999997,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -17293,7 +18139,9 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -17304,6 +18152,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-fable-5.1": {
+            id: "anthropic/claude-fable-5.1",
+            name: "Claude Fable 5.1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Claude Haiku 4.5",
@@ -17621,23 +18488,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "deepseek/deepseek-v3": {
-            id: "deepseek/deepseek-v3",
-            name: "DeepSeek V3 0324",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.27,
-                output: 1.12,
-                cacheRead: 0.135,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
         "deepseek/deepseek-v3.1": {
             id: "deepseek/deepseek-v3.1",
             name: "DeepSeek V3.1",
@@ -17754,8 +18604,8 @@ export const MODELS = {
                 cacheRead: 0.007,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 1048576,
+            maxTokens: 1048576,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -17766,13 +18616,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.14,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
-            contextWindow: 1048600,
-            maxTokens: 1048600,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -18405,7 +19255,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
-            name: "Minimax M2.7",
+            name: "MiniMax M2.7",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -18422,7 +19272,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7-free": {
             id: "minimax/minimax-m2.7-free",
-            name: "Minimax M2.7 (Free)",
+            name: "MiniMax M2.7 (Free)",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -18468,8 +19318,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 1000000,
+            contextWindow: 512000,
+            maxTokens: 512000,
         },
         "minimax/minimax-m3-free": {
             id: "minimax/minimax-m3-free",
@@ -18771,7 +19621,7 @@ export const MODELS = {
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.19,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -18889,8 +19739,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.049999999999999996,
-                output: 0.15,
-                cacheRead: 0.049999999999999996,
+                output: 0.19999999999999998,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -20220,13 +21070,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13199999999999998,
-                output: 0.5279999999999999,
-                cacheRead: 0.032999999999999995,
+                input: 0.14,
+                output: 0.58,
+                cacheRead: 0.035,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 128000,
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "tencent/hy4-preview": {
+            id: "tencent/hy4-preview",
+            name: "Tencent Hy4 Preview",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0.041999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1024000,
+            maxTokens: 64000,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -20296,6 +21163,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 131000,
         },
+        "xiaomi/mimo-v2.5-pro-ultraspeed": {
+            id: "xiaomi/mimo-v2.5-pro-ultraspeed",
+            name: "MiMo V2.5 Pro UltraSpeed",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "zai/glm-4.5": {
             id: "zai/glm-4.5",
             name: "GLM 4.5",
@@ -20514,11 +21398,11 @@ export const MODELS = {
             cost: {
                 input: 1.4,
                 output: 4.4,
-                cacheRead: 0.26,
+                cacheRead: 0.14,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 12800,
+            maxTokens: 1000000,
         },
         "zai/glm-5.3-flash": {
             id: "zai/glm-5.3-flash",