omk-ai 0.96.2 → 0.97.0

package/dist/models.generated.js

@@ -797,7 +797,7 @@ export const MODELS = {
                 cacheRead: 0.022,
                 cacheWrite: 0.275,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "global.openai.gpt-5.6-sol": {
@@ -815,7 +815,7 @@ export const MODELS = {
                 cacheRead: 0.55,
                 cacheWrite: 6.875,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "global.openai.gpt-5.6-terra": {
@@ -833,7 +833,7 @@ export const MODELS = {
                 cacheRead: 0.22,
                 cacheWrite: 2.75,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "google.gemma-3-27b-it": {
@@ -1434,7 +1434,7 @@ export const MODELS = {
                 cacheRead: 0.022,
                 cacheWrite: 0.275,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai.gpt-5.6-sol": {
@@ -1452,7 +1452,7 @@ export const MODELS = {
                 cacheRead: 0.55,
                 cacheWrite: 6.875,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai.gpt-5.6-terra": {
@@ -1470,7 +1470,7 @@ export const MODELS = {
                 cacheRead: 0.22,
                 cacheWrite: 2.75,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai.gpt-oss-120b": {
@@ -2894,7 +2894,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-luna": {
@@ -2912,7 +2912,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -2930,7 +2930,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -2948,7 +2948,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-realtime-2.1": {
@@ -3727,7 +3727,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-luna": {
@@ -3745,7 +3745,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -3763,7 +3763,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -3781,7 +3781,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "o1": {
@@ -5354,7 +5354,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -5368,12 +5368,12 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -5392,7 +5392,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "grok-4.5": {
@@ -8550,6 +8550,26 @@ export const MODELS = {
         },
     },
     "nvidia": {
+        "deepseek-ai/deepseek-v4-flash-0731": {
+            id: "deepseek-ai/deepseek-v4-flash-0731",
+            name: "DeepSeek V4 Flash 0731",
+            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, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Gemma 3 12B IT",
@@ -8759,6 +8779,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "moonshotai/kimi-k3": {
+            id: "moonshotai/kimi-k3",
+            name: "Kimi K3",
+            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: 1048576,
+            maxTokens: 131072,
+        },
         "nvidia/cosmos-reason2-8b": {
             id: "nvidia/cosmos-reason2-8b",
             name: "Cosmos Reason2 8B",
@@ -9667,7 +9706,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-luna": {
@@ -9685,7 +9724,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -9703,7 +9742,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -9721,7 +9760,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-realtime-2.1": {
@@ -9932,7 +9971,7 @@ export const MODELS = {
                 cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 372000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-moa": {
@@ -9950,7 +9989,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 300000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -9986,7 +10025,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 372000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
     },
@@ -10705,7 +10744,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-sol": {
@@ -10718,12 +10757,12 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "gpt-5.6-terra": {
@@ -10741,7 +10780,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 3.125,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "grok-4.5": {
@@ -11093,6 +11132,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4-flash-vision-exp": {
+            id: "deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "deepseek-v4-pro": {
             id: "deepseek-v4-pro",
             name: "DeepSeek V4 Pro (New)",
@@ -11180,7 +11238,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "grok-4.5": {
@@ -11270,6 +11328,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "longcat-2.0": {
+            id: "longcat-2.0",
+            name: "LongCat-2.0",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "mimo-v2.5": {
             id: "mimo-v2.5",
             name: "MiMo V2.5",
@@ -12316,13 +12391,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.95,
-                cacheRead: 0.13,
+                input: 0.55,
+                output: 1.6500000000000001,
+                cacheRead: 0.55,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 32768,
+            maxTokens: 161000,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -12384,13 +12459,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26899999999999996,
-                output: 0.39999999999999997,
-                cacheRead: 0.13449999999999998,
+                input: 0.26,
+                output: 0.38,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -12420,9 +12495,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.08259999999999999,
-                output: 0.16519999999999999,
-                cacheRead: 0.01652,
+                input: 0.056,
+                output: 0.112,
+                cacheRead: 0.0112,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12439,12 +12514,31 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.0658,
+                output: 0.1316,
+                cacheRead: 0.01316,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
+            maxTokens: 131072,
+        },
+        "deepseek/deepseek-v4-flash-vision-exp": {
+            id: "deepseek/deepseek-v4-flash-vision-exp",
+            name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
             maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro": {
@@ -12458,13 +12552,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.5999999999999999,
-                output: 3.1999999999999997,
-                cacheRead: 0.135,
+                input: 0.522,
+                output: 1.044,
+                cacheRead: 0.0435,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -12477,9 +12571,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.1880000000000002,
-                output: 3.564,
-                cacheRead: 0.039599999999999996,
+                input: 1.122,
+                output: 3.366,
+                cacheRead: 0.037399999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -13064,40 +13158,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
-        "inclusionai/ling-2.6-1t": {
-            id: "inclusionai/ling-2.6-1t",
-            name: "inclusionAI: Ling-2.6-1T",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "inclusionai/ling-2.6-flash": {
-            id: "inclusionai/ling-2.6-flash",
-            name: "inclusionAI: Ling-2.6-flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.01,
-                output: 0.03,
-                cacheRead: 0.002,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
             name: "Ling-3.0-flash",
@@ -13115,23 +13175,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ring-2.6-1t": {
-            id: "inclusionai/ring-2.6-1t",
-            name: "inclusionAI: Ring-2.6-1T",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "kwaipilot/kat-coder-air-v2.5": {
             id: "kwaipilot/kat-coder-air-v2.5",
             name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -13311,13 +13354,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.1,
+                input: 0.35,
+                output: 1.5,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "meta/muse-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -13353,6 +13396,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 4096,
         },
+        "meta/muse-spark-1.2-contributor": {
+            id: "meta/muse-spark-1.2-contributor",
+            name: "Meta: Muse Spark 1.2 Contributor",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
             name: "MiniMax: MiniMax M1",
@@ -13414,12 +13474,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.03,
+                output: 1.08,
+                cacheRead: 0.027,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 32768,
+            maxTokens: 128000,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -13436,7 +13496,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -13489,6 +13549,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
+        "mistralai/devstral-2512": {
+            id: "mistralai/devstral-2512",
+            name: "Mistral: Devstral 2 2512",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.44,
+                output: 2.2,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -13702,12 +13779,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09375,
-                output: 0.25,
-                cacheRead: 0,
+                input: 0.075,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
@@ -13828,7 +13905,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -13841,7 +13918,7 @@ export const MODELS = {
             cost: {
                 input: 0.67,
                 output: 3.4,
-                cacheRead: 0.16999999999999998,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13879,7 +13956,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 1048576,
         },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
@@ -13932,23 +14009,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "nvidia/nemotron-3-nano-30b-a3b:free": {
-            id: "nvidia/nemotron-3-nano-30b-a3b:free",
-            name: "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 4096,
-        },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
             name: "NVIDIA: Nemotron 3 Nano Omni (free)",
@@ -14085,40 +14145,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "nvidia/nemotron-nano-12b-v2-vl:free": {
-            id: "nvidia/nemotron-nano-12b-v2-vl:free",
-            name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 128000,
-        },
-        "nvidia/nemotron-nano-9b-v2:free": {
-            id: "nvidia/nemotron-nano-9b-v2:free",
-            name: "NVIDIA: Nemotron Nano 9B V2 (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-3.5-turbo": {
             id: "openai/gpt-3.5-turbo",
             name: "OpenAI: GPT-3.5 Turbo",
@@ -15071,7 +15097,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-luna-pro": {
@@ -15089,7 +15115,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-luna-pro:batch": {
@@ -15107,7 +15133,7 @@ export const MODELS = {
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-luna:batch": {
@@ -15125,7 +15151,7 @@ export const MODELS = {
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol": {
@@ -15138,12 +15164,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol-pro": {
@@ -15156,12 +15182,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol-pro:batch": {
@@ -15174,12 +15200,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol:batch": {
@@ -15192,12 +15218,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra": {
@@ -15215,7 +15241,7 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra-pro": {
@@ -15233,7 +15259,7 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra-pro:batch": {
@@ -15251,7 +15277,7 @@ export const MODELS = {
                 cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra:batch": {
@@ -15269,7 +15295,7 @@ export const MODELS = {
                 cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5:batch": {
@@ -15349,9 +15375,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.037,
                 output: 0.16999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -15374,23 +15400,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/gpt-oss-20b:free": {
-            id: "openai/gpt-oss-20b:free",
-            name: "OpenAI: gpt-oss-20b (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
             name: "OpenAI: gpt-oss-safeguard-20b",
@@ -15919,7 +15928,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -15932,13 +15941,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -16140,13 +16149,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -16304,7 +16313,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -16352,13 +16361,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.39,
-                output: 2.34,
-                cacheRead: 0,
+                input: 0.5,
+                output: 3.5999999999999996,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -16442,13 +16451,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.12,
+                input: 0.32,
+                output: 3.1999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 81920,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -16592,7 +16601,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "qwen/qwen3.8-27b": {
             id: "qwen/qwen3.8-27b",
@@ -16604,8 +16613,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.44999999999999996,
-                output: 3.1999999999999997,
+                input: 0.39999999999999997,
+                output: 3,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
@@ -16816,7 +16825,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 1024000,
+            maxTokens: 32768,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -16827,13 +16836,13 @@ 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: 4096,
         },
         "thinkingmachines/inkling-small": {
             id: "thinkingmachines/inkling-small",
@@ -16852,6 +16861,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "thinkingmachines/inkling-small:free": {
+            id: "thinkingmachines/inkling-small:free",
+            name: "Thinking Machines: Inkling Small (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "thinkingmachines/inkling:batch": {
             id: "thinkingmachines/inkling:batch",
             name: "Thinking Machines: Inkling (batch)",
@@ -16869,6 +16895,23 @@ export const MODELS = {
             contextWindow: 524288,
             maxTokens: 4096,
         },
+        "thinkingmachines/inkling:free": {
+            id: "thinkingmachines/inkling:free",
+            name: "Thinking Machines: Inkling (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -17361,9 +17404,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.065,
-                output: 0.18,
-                cacheRead: 0.02,
+                input: 0.04,
+                output: 0.08,
+                cacheRead: 0.008,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -17429,10 +17472,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18893,9 +18936,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.26,
-                cacheRead: 0.028,
+                input: 0.07600000000000001,
+                output: 0.153,
+                cacheRead: 0.014,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-flash-vision-exp": {
+            id: "deepseek/deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -19998,13 +20058,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.01,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 32768,
+        },
+        "nvidia/nemotron-3.5-lightning-free": {
+            id: "nvidia/nemotron-3.5-lightning-free",
+            name: "Nemotron 3.5 Lightning 30B (Free)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 32768,
         },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
@@ -20733,7 +20810,7 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-luna-fast": {
@@ -20751,7 +20828,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0.25,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol": {
@@ -20764,12 +20841,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-sol-fast": {
@@ -20782,12 +20859,12 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 3.125,
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra": {
@@ -20805,7 +20882,7 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-5.6-terra-fast": {
@@ -20823,7 +20900,7 @@ export const MODELS = {
                 cacheRead: 0.39999999999999997,
                 cacheWrite: 2.5,
             },
-            contextWindow: 1050000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "openai/gpt-oss-120b": {