npm - omk-ai - Versions diffs - 1.3.0 → 1.3.2 - Mend

omk-ai 1.3.0 → 1.3.2

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

Files changed (18) hide show

package/CHANGELOG.md +17 -1
package/dist/image-models.generated.d.ts +60 -0
package/dist/image-models.generated.d.ts.map +1 -1
package/dist/image-models.generated.js +60 -0
package/dist/image-models.generated.js.map +1 -1
package/dist/models.generated.d.ts +869 -278
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +888 -414
package/dist/models.generated.js.map +1 -1
package/dist/providers/mistral-reasoning.d.ts +6 -0
package/dist/providers/mistral-reasoning.d.ts.map +1 -0
package/dist/providers/mistral-reasoning.js +16 -0
package/dist/providers/mistral-reasoning.js.map +1 -0
package/dist/providers/mistral.d.ts +1 -2
package/dist/providers/mistral.d.ts.map +1 -1
package/dist/providers/mistral.js +1 -9
package/dist/providers/mistral.js.map +1 -1
package/package.json +1 -1

package/dist/models.generated.js CHANGED Viewed

@@ -1224,6 +1224,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "global.openai.gpt-6.1-sol": {
+            id: "global.openai.gpt-6.1-sol",
+            name: "GPT-6.1 Sol (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.1,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "global.xai.grok-4.6": {
             id: "global.xai.grok-4.6",
             name: "Grok 4.6 (Global)",
@@ -1260,6 +1277,24 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
+        "global.zai.glm-5.3": {
+            id: "global.zai.glm-5.3",
+            name: "GLM-5.3 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.68,
+                output: 5.28,
+                cacheRead: 0.312,
+                cacheWrite: 2.1,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "google.gemma-4-26b-a4b": {
             id: "google.gemma-4-26b-a4b",
             name: "Gemma 4 26B A4B IT",
@@ -1311,6 +1346,58 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
+        "in.anthropic.claude-haiku-4-5-20251001-v1:0": {
+            id: "in.anthropic.claude-haiku-4-5-20251001-v1:0",
+            name: "Claude Haiku 4.5 (India)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.1,
+                output: 5.5,
+                cacheRead: 0.11,
+                cacheWrite: 1.375,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
+        "in.anthropic.claude-opus-5": {
+            id: "in.anthropic.claude-opus-5",
+            name: "Claude Opus 5 (India)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "in.anthropic.claude-sonnet-5": {
+            id: "in.anthropic.claude-sonnet-5",
+            name: "Claude Sonnet 5 (India)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "in.openai.gpt-5.6-luna": {
             id: "in.openai.gpt-5.6-luna",
             name: "GPT-5.6 Luna (India)",
@@ -2037,6 +2124,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai.gpt-6.1-sol": {
+            id: "openai.gpt-6.1-sol",
+            name: "GPT-6.1 Sol",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.11,
+                cacheWrite: 2.75,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai.gpt-oss-120b": {
             id: "openai.gpt-oss-120b",
             name: "gpt-oss-120b",
@@ -2831,6 +2935,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "us.openai.gpt-6.1-sol": {
+            id: "us.openai.gpt-6.1-sol",
+            name: "GPT-6.1 Sol (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.11,
+                cacheWrite: 2.75,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "us.writer.palmyra-x4-v1:0": {
             id: "us.writer.palmyra-x4-v1:0",
             name: "Palmyra X4 (US)",
@@ -2901,6 +3022,24 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
+        "us.zai.glm-5.3": {
+            id: "us.zai.glm-5.3",
+            name: "GLM-5.3 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.848,
+                output: 5.808,
+                cacheRead: 0.3432,
+                cacheWrite: 2.31,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "writer.palmyra-x4-v1:0": {
             id: "writer.palmyra-x4-v1:0",
             name: "Palmyra X4",
@@ -3295,7 +3434,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "claude-sonnet-4-5-20250929": {
@@ -3312,7 +3451,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "claude-sonnet-4-6": {
@@ -4212,7 +4351,7 @@ export const MODELS = {
             cost: {
                 input: 0.99,
                 output: 1.49,
-                cacheRead: 0,
+                cacheRead: 0.99,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4814,6 +4953,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6.1-sol": {
+            id: "gpt-6.1-sol",
+            name: "GPT-6.1 Sol",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.1,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o3": {
             id: "o3",
             name: "o3",
@@ -4917,7 +5074,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -4985,7 +5142,7 @@ export const MODELS = {
             baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
             compat: { "sendSessionAffinityHeaders": true },
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.351,
                 output: 0.555,
@@ -12924,9 +13081,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.66,
-                cacheRead: 0.007,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -13144,9 +13301,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.66,
-                cacheRead: 0.007,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -13377,6 +13534,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
+        "claude-haiku-5.5": {
+            id: "claude-haiku-5.5",
+            name: "Claude Haiku 5.5",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.5,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
             name: "Claude Opus 4.7",
@@ -13496,6 +13672,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-sonnet-5.5": {
+            id: "claude-sonnet-5.5",
+            name: "Claude Sonnet 5.5",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.1,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "gemini-3.5-flash": {
             id: "gemini-3.5-flash",
             name: "Gemini 3.5 Flash",
@@ -14553,9 +14748,9 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3.1-flash-lite-preview": {
-            id: "gemini-3.1-flash-lite-preview",
-            name: "Gemini 3.1 Flash Lite Preview",
+        "gemini-3.1-flash-lite-image": {
+            id: "gemini-3.1-flash-lite-image",
+            name: "Nano Banana 2 Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -14564,12 +14759,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.25,
-                output: 1.5,
+                output: 30,
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            contextWindow: 65536,
+            maxTokens: 4096,
         },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
@@ -14697,40 +14892,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-flash-latest": {
-            id: "gemini-flash-latest",
-            name: "Gemini Flash Latest",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.5,
-                output: 9,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-flash-lite-latest": {
-            id: "gemini-flash-lite-latest",
-            name: "Gemini Flash-Lite Latest",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1.5,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
     },
     "groq": {
         "llama-3.1-8b-instant": {
@@ -16524,6 +16685,23 @@ export const MODELS = {
         },
     },
     "mistral": {
+        "codestral-2508": {
+            id: "codestral-2508",
+            name: "Codestral 25.08",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 0.9,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
         "codestral-latest": {
             id: "codestral-latest",
             name: "Codestral (latest)",
@@ -16643,23 +16821,58 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
-        "labs-devstral-small-2512": {
-            id: "labs-devstral-small-2512",
-            name: "Devstral Small 2",
+        "glm-5-2": {
+            id: "glm-5-2",
+            name: "GLM-5.2",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: false,
-            input: ["text", "image"],
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "labs-devstral-small-2512": {
+            id: "labs-devstral-small-2512",
+            name: "Devstral Small 2",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "labs-leanstral-1-5-1": {
+            id: "labs-leanstral-1-5-1",
+            name: "Leanstral 1.5",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 128000,
+        },
         "magistral-medium-latest": {
             id: "magistral-medium-latest",
             name: "Magistral Medium (latest)",
@@ -16667,16 +16880,50 @@ export const MODELS = {
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 262144,
             maxTokens: 16384,
         },
+        "ministral-14b-2512": {
+            id: "ministral-14b-2512",
+            name: "Ministral 3 14B",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 0.2,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "ministral-3b-2512": {
+            id: "ministral-3b-2512",
+            name: "Ministral 3 3B",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 262144,
+        },
         "ministral-3b-latest": {
             id: "ministral-3b-latest",
             name: "Ministral 3B (latest)",
@@ -16684,16 +16931,33 @@ export const MODELS = {
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.04,
                 output: 0.04,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131072,
             maxTokens: 128000,
         },
+        "ministral-8b-2512": {
+            id: "ministral-8b-2512",
+            name: "Ministral 3 8B",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "ministral-8b-latest": {
             id: "ministral-8b-latest",
             name: "Ministral 8B (latest)",
@@ -16701,14 +16965,14 @@ export const MODELS = {
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.1,
                 output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 262144,
             maxTokens: 128000,
         },
         "mistral-large-2411": {
@@ -16745,6 +17009,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "mistral-large-4": {
+            id: "mistral-large-4",
+            name: "Mistral Large 4",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.68,
+                output: 2.09,
+                cacheRead: 0.07,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
         "mistral-large-latest": {
             id: "mistral-large-latest",
             name: "Mistral Large (latest)",
@@ -16895,7 +17177,7 @@ export const MODELS = {
                 cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "mistral-small-latest": {
@@ -16912,7 +17194,7 @@ export const MODELS = {
                 cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "open-mistral-7b": {
@@ -17017,6 +17299,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
+        "voxtral-small-2507": {
+            id: "voxtral-small-2507",
+            name: "Voxtral Small",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32000,
+        },
         "voxtral-small-latest": {
             id: "voxtral-small-latest",
             name: "Voxtral Small (latest)",
@@ -17031,7 +17330,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
+            contextWindow: 32768,
             maxTokens: 32000,
         },
         "zai-glm-5-2": {
@@ -17049,7 +17348,7 @@ export const MODELS = {
                 cacheRead: 0.14,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 1048576,
             maxTokens: 131072,
         },
         "zai-glm-5-3": {
@@ -17067,7 +17366,7 @@ export const MODELS = {
                 cacheRead: 0.14,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 1048576,
             maxTokens: 131072,
         },
     },
@@ -17139,7 +17438,7 @@ export const MODELS = {
                 input: 3,
                 output: 15,
                 cacheRead: 0.3,
-                cacheWrite: 0,
+                cacheWrite: 3,
             },
             contextWindow: 1048576,
             maxTokens: 1048576,
@@ -17213,13 +17512,52 @@ export const MODELS = {
                 input: 3,
                 output: 15,
                 cacheRead: 0.3,
-                cacheWrite: 0,
+                cacheWrite: 3,
             },
             contextWindow: 1048576,
             maxTokens: 1048576,
         },
     },
     "nvidia": {
+        "deepseek-ai/deepseek-v4.1-flash": {
+            id: "deepseek-ai/deepseek-v4.1-flash",
+            name: "DeepSeek V4.1 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, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "google/diffusiongemma-26b-a4b-it": {
+            id: "google/diffusiongemma-26b-a4b-it",
+            name: "DiffusionGemma 26B A4B IT",
+            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: 250000,
+            maxTokens: 32768,
+        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Gemma 3 12B IT",
@@ -18963,6 +19301,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "exo-free": {
+            id: "exo-free",
+            name: "Exo 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: 1048576,
+            maxTokens: 131072,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -19748,6 +20103,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "ling-3.1-flash-free": {
+            id: "ling-3.1-flash-free",
+            name: "Ling 3.1 Flash Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "longcat-2.5-preview-free": {
             id: "longcat-2.5-preview-free",
             name: "LongCat 2.5 Preview Free",
@@ -19833,6 +20205,24 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 128000,
         },
+        "mistral-large-4": {
+            id: "mistral-large-4",
+            name: "Mistral Large 4",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.68,
+                output: 2.09,
+                cacheRead: 0.07,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 262144,
+        },
         "muse-spark-1.2": {
             id: "muse-spark-1.2",
             name: "Muse Spark 1.2",
@@ -20010,6 +20400,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 524288,
         },
+        "step-5-preview-free": {
+            id: "step-5-preview-free",
+            name: "Step 5 Preview 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: 1000000,
+            maxTokens: 65536,
+        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -20457,9 +20864,9 @@ export const MODELS = {
         "qwen3.7-plus": {
             id: "qwen3.7-plus",
             name: "Qwen3.7 Plus",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
@@ -20493,9 +20900,9 @@ export const MODELS = {
         "qwen3.8-max": {
             id: "qwen3.8-max",
             name: "Qwen3.8 Max",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
@@ -20508,9 +20915,26 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "space-bunny-free": {
-            id: "space-bunny-free",
-            name: "Space Bunny Free",
+        "space-bunny": {
+            id: "space-bunny",
+            name: "Space Bunny",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 524288,
+        },
+        "step-5-preview-free": {
+            id: "step-5-preview-free",
+            name: "Step 5 Preview Free",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -20522,8 +20946,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 524288,
+            contextWindow: 1000000,
+            maxTokens: 65536,
         },
     },
     "openrouter": {
@@ -20808,6 +21232,42 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
+        "anthropic/claude-haiku-5.5": {
+            id: "anthropic/claude-haiku-5.5",
+            name: "Anthropic: Claude Haiku 5.5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.5,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-haiku-5.5:batch": {
+            id: "anthropic/claude-haiku-5.5:batch",
+            name: "Anthropic: Claude Haiku 5.5 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.25,
+                cacheRead: 0.005,
+                cacheWrite: 0.0625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-opus-4.1": {
             id: "anthropic/claude-opus-4.1",
             name: "Anthropic: Claude Opus 4.1",
@@ -21143,20 +21603,56 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-sonnet-5": {
-            id: "anthropic/claude-sonnet-5",
-            name: "Anthropic: Claude Sonnet 5",
+        "anthropic/claude-sonnet-5": {
+            id: "anthropic/claude-sonnet-5",
+            name: "Anthropic: Claude Sonnet 5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-sonnet-5.5": {
+            id: "anthropic/claude-sonnet-5.5",
+            name: "Anthropic: Claude Sonnet 5.5",
+            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", "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-sonnet-5.5:batch": {
+            id: "anthropic/claude-sonnet-5.5:batch",
+            name: "Anthropic: Claude Sonnet 5.5 (batch)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
+                input: 1,
+                output: 5,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 1.25,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -21179,6 +21675,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "apodex/apodex-1.1-mini:free": {
+            id: "apodex/apodex-1.1-mini:free",
+            name: "Apodex: Apodex 1.1 Mini (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
+        },
         "arcee-ai/trinity-large-thinking": {
             id: "arcee-ai/trinity-large-thinking",
             name: "Arcee AI: Trinity Large Thinking",
@@ -21396,13 +21909,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2574,
-                output: 1.0287,
+                input: 0.32,
+                output: 0.8899999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -21419,7 +21932,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 147456,
+            maxTokens: 115200,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -21483,13 +21996,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
+                input: 0.27,
                 output: 1,
-                cacheRead: 0.135,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 147456,
         },
         "deepseek/deepseek-v3.2": {
             id: "deepseek/deepseek-v3.2",
@@ -21500,13 +22013,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.28,
+                input: 0.25899999999999995,
                 output: 0.42,
-                cacheRead: 0.028,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 147456,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -21536,13 +22049,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "off": "none", "max": null, "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.0075,
+                output: 1.28,
+                cacheRead: 0.0075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 943718,
         },
         "deepseek/deepseek-v4-flash-0731": {
             id: "deepseek/deepseek-v4-flash-0731",
@@ -21555,9 +22068,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.018,
-                output: 0.32,
-                cacheRead: 0.018,
+                input: 0.0046,
+                output: 1.28,
+                cacheRead: 0.0046,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -21612,9 +22125,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 1.32,
-                output: 3.9600000000000004,
-                cacheRead: 0.044,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -22157,6 +22670,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "google/gemini-nano-banana-2.1": {
+            id: "google/gemini-nano-banana-2.1",
+            name: "Google: Nano Banana 2.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": "minimal", "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 65536,
+            maxTokens: 58982,
+        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Google: Gemma 3 12B",
@@ -22200,9 +22731,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.0765,
-                output: 0.255,
-                cacheRead: 0.042499999999999996,
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -22339,26 +22870,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.18,
-                cacheRead: 0.012,
+                input: 0.041999999999999996,
+                output: 0.12319999999999999,
+                cacheRead: 0.008400000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32768,
         },
-        "inclusionai/ling-3.0-flash-sante:free": {
-            id: "inclusionai/ling-3.0-flash-sante:free",
-            name: "inclusionAI: Ling 3.0 Flash Sante (free)",
+        "inclusionai/ling-3.0-flash-sante": {
+            id: "inclusionai/ling-3.0-flash-sante",
+            name: "inclusionAI: Ling 3.0 Flash Sante",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.041999999999999996,
+                output: 0.12319999999999999,
+                cacheRead: 0.008400000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -22381,22 +22912,22 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kwaipilot/kat-coder-pro-v2.5": {
-            id: "kwaipilot/kat-coder-pro-v2.5",
-            name: "Kwaipilot: KAT-Coder-Pro V2.5",
+        "inclusionai/ling-3.1-flash": {
+            id: "inclusionai/ling-3.1-flash",
+            name: "inclusionAI: Ling 3.1 Flash",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.74,
-                output: 2.96,
-                cacheRead: 0.15,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32768,
         },
         "liquid/lfm-2.5-2.6b:free": {
             id: "liquid/lfm-2.5-2.6b:free",
@@ -22476,9 +23007,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.32,
-                cacheRead: 0,
+                input: 0.22,
+                output: 0.5,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -22495,7 +23026,7 @@ export const MODELS = {
             cost: {
                 input: 0.1875,
                 output: 0.6525,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -22528,13 +23059,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
             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-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -22635,7 +23166,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.55,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -22919,6 +23450,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
+        "mistralai/mistral-large-4-0": {
+            id: "mistralai/mistral-large-4-0",
+            name: "Mistral: Mistral Large 4",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.6799999999999999,
+                output: 2.09,
+                cacheRead: 0.07,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
         "mistralai/mistral-medium-3": {
             id: "mistralai/mistral-medium-3",
             name: "Mistral: Mistral Medium 3",
@@ -23015,7 +23564,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.019000000000000003,
+                input: 0.029,
                 output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -23190,11 +23739,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 98304,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -23223,9 +23772,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.65,
-                output: 3.41,
-                cacheRead: 0.15,
+                input: 0.46499999999999997,
+                output: 2.4499999999999997,
+                cacheRead: 0.0975,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -23241,8 +23790,8 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.6562,
-                output: 3.3000000000000003,
+                input: 0.6712,
+                output: 3.35,
                 cacheRead: 0.18,
                 cacheWrite: 0,
             },
@@ -23259,8 +23808,8 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
+                input: 0.5,
+                output: 12,
                 cacheRead: 0.3,
                 cacheWrite: 0,
             },
@@ -23312,9 +23861,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.03,
+                input: 0.06,
+                output: 0.24,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -23383,13 +23932,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.12,
+                input: 0.5,
+                output: 2.2,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 182520,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -23418,13 +23967,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.16,
-                cacheRead: 0.03,
+                input: 0.046900000000000004,
+                output: 0.134,
+                cacheRead: 0.023450000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 131072,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -24458,10 +25007,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": "max", "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 4,
-                output: 20,
-                cacheRead: 0.39999999999999997,
-                cacheWrite: 5,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -25461,13 +26010,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.0875,
-                output: 0.35,
-                cacheRead: 0.0175,
+                input: 0.09,
+                output: 0.55,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -25497,13 +26046,13 @@ 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",
@@ -25514,13 +26063,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04815,
-                output: 0.19305,
+                input: 0.09999999999999999,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32000,
+            maxTokens: 235929,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -25729,7 +26278,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -25881,13 +26430,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.195,
-                output: 1.56,
+                input: 0.26,
+                output: 2.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-35b-a3b": {
             id: "qwen/qwen3.5-35b-a3b",
@@ -25899,13 +26448,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.1625,
-                output: 1.3,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.75,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -26007,13 +26556,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "high", "max": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0.32,
-                output: 3.1999999999999997,
+                input: 0.44999999999999996,
+                output: 2.7,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 65536,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -26169,32 +26718,14 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 0.42,
-                output: 3,
+                input: 0.425,
+                output: 2.5500000000000003,
                 cacheRead: 0.08499999999999999,
-                cacheWrite: 0,
+                cacheWrite: 0.53125,
             },
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "qwen/qwen3.8-27b:free": {
-            id: "qwen/qwen3.8-27b:free",
-            name: "Qwen: Qwen3.8 27B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
-        },
         "qwen/qwen3.8-flash": {
             id: "qwen/qwen3.8-flash",
             name: "Qwen: Qwen3.8 Flash",
@@ -26373,41 +26904,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "sao10k/l3.1-euryale-70b": {
-            id: "sao10k/l3.1-euryale-70b",
-            name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.85,
-                output: 0.85,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
-        "stealth/space-bunny-alpha": {
-            id: "stealth/space-bunny-alpha",
-            name: "Space Bunny Alpha",
-            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", "ultra": null },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 524288,
-        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -26436,13 +26932,31 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.15,
-                cacheRead: 0.04,
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 230400,
+        },
+        "stepfun/step-5-preview": {
+            id: "stepfun/step-5-preview",
+            name: "StepFun: Step 5 Preview",
+            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": null, "max": null, "ultra": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2.7,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 230400,
+            contextWindow: 1000000,
+            maxTokens: 64000,
         },
         "tencent/hy3": {
             id: "tencent/hy3",
@@ -26570,6 +27084,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "typesafe/jev-router": {
+            id: "typesafe/jev-router",
+            name: "TypeSafe: Jev Router",
+            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: 1000000,
+            maxTokens: 4096,
+        },
         "unbiased/pareto": {
             id: "unbiased/pareto",
             name: "Pareto",
@@ -26587,6 +27118,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "unbiased/pareto-26.10-preview": {
+            id: "unbiased/pareto-26.10-preview",
+            name: "Pareto 26.10 Preview",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.7999999999999999,
+                output: 3.1999999999999997,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "upstage/solar-mini4": {
             id: "upstage/solar-mini4",
             name: "Upstage: Solar Mini 4",
@@ -26814,7 +27362,7 @@ export const MODELS = {
                 cacheRead: 0.0028,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1050000,
             maxTokens: 131072,
         },
         "xiaomi/mimo-v2.6-pro": {
@@ -27013,13 +27561,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1794,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -27031,9 +27579,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.2087,
-                output: 3.9899999999999998,
-                cacheRead: 0.167,
+                input: 0.06,
+                output: 6,
+                cacheRead: 0.059,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27049,13 +27597,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.039,
+                output: 4.8,
+                cacheRead: 0.038000000000000006,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 943717,
+            maxTokens: 943718,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -27189,15 +27737,16 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 0.09999999999999999,
+                output: 0.5,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
             },
-            contextWindow: 200000,
-            maxTokens: 64000,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
         "~anthropic/claude-opus-latest": {
             id: "~anthropic/claude-opus-latest",
@@ -27229,7 +27778,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 10,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 2.5,
             },
             contextWindow: 1000000,
@@ -27245,9 +27794,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 0.02,
-                output: 0.6,
-                cacheRead: 0.02,
+                input: 0.016,
+                output: 1.2,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27263,9 +27812,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.198,
+                output: 8,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27282,9 +27831,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.012,
-                output: 1.25,
-                cacheRead: 0.01,
+                input: 0.00368,
+                output: 0.064127,
+                cacheRead: 0.00368,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27336,9 +27885,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 9,
-                cacheRead: 0.39999999999999997,
+                input: 0.49,
+                output: 13,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27462,9 +28011,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text", "image"],
             cost: {
-                input: 0.02,
-                output: 0.3,
-                cacheRead: 0.01,
+                input: 0.032,
+                output: 0.683284,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27480,9 +28029,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 1.5,
-                cacheRead: 0.12,
+                input: 0.031200000000000002,
+                output: 4.4,
+                cacheRead: 0.029,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -27621,34 +28170,15 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
-        "deepseek-ai/DeepSeek-V4-Pro": {
-            id: "deepseek-ai/DeepSeek-V4-Pro",
-            name: "DeepSeek V4 Pro",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
-            input: ["text"],
-            cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 512000,
-            maxTokens: 384000,
-        },
         "deepseek-ai/DeepSeek-V4-Pro-0813": {
             id: "deepseek-ai/DeepSeek-V4-Pro-0813",
             name: "DeepSeek V4 Pro 0813",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
             input: ["text"],
             cost: {
                 input: 1.32,
@@ -27678,25 +28208,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
-        "google/gemma-4-31B-it": {
-            id: "google/gemma-4-31B-it",
-            name: "Gemma 4 31B Instruct",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text", "image"],
-            cost: {
-                input: 0.39,
-                output: 0.97,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
         "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
             id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
             name: "Llama 3.3 70B",
@@ -27772,25 +28283,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/gpt-oss-20b": {
-            id: "openai/gpt-oss-20b",
-            name: "GPT OSS 20B",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null },
-            input: ["text"],
-            cost: {
-                input: 0.05,
-                output: 0.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "thinkingmachines/Inkling": {
             id: "thinkingmachines/Inkling",
             name: "Inkling",
@@ -27893,8 +28385,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "high", "max": "max" },
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.22,
@@ -28843,7 +29334,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.25,
-                output: 0.8999999999999999,
+                output: 0.7999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -28901,6 +29392,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "callstack/apex": {
+            id: "callstack/apex",
+            name: "Apex",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "cohere/command-a": {
             id: "cohere/command-a",
             name: "Command A",
@@ -28952,23 +29460,6 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 128000,
         },
-        "deepseek/deepseek-v3.1-terminus": {
-            id: "deepseek/deepseek-v3.1-terminus",
-            name: "DeepSeek V3.1 Terminus",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.27,
-                output: 1,
-                cacheRead: 0.135,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
         "deepseek/deepseek-v3.2": {
             id: "deepseek/deepseek-v3.2",
             name: "DeepSeek V3.2",
@@ -29439,26 +29930,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 32000,
-        },
-        "inclusionai/ling-3.0-flash-sante-free": {
-            id: "inclusionai/ling-3.0-flash-sante-free",
-            name: "Ling 3.0 Flash Sante (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,
+                input: 0.075,
+                output: 0.22,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -29957,6 +30431,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 256000,
         },
+        "mistral/mistral-large-4": {
+            id: "mistral/mistral-large-4",
+            name: "Mistral Large 4",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6799999999999999,
+                output: 2.09,
+                cacheRead: 0.07,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 262144,
+        },
         "mistral/mistral-medium-3.5": {
             id: "mistral/mistral-medium-3.5",
             name: "Mistral Medium Latest",
@@ -29983,13 +30474,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.16999999999999998,
+                input: 0.019000000000000003,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 60288,
-            maxTokens: 16000,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
@@ -30042,23 +30533,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "moonshotai/kimi-k2-thinking": {
-            id: "moonshotai/kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.47,
-                output: 2,
-                cacheRead: 0.14100000000000001,
-                cacheWrite: 0,
-            },
-            contextWindow: 216144,
-            maxTokens: 216144,
-        },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -31381,9 +31855,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.19999999999999998,
-                cacheRead: 0.01,
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.009,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -31732,22 +32206,22 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
-        "stepfun/step-3.5-flash": {
-            id: "stepfun/step-3.5-flash",
-            name: "StepFun 3.5 Flash",
+        "stealth/glyph-cluster": {
+            id: "stealth/glyph-cluster",
+            name: "Glyph Cluster",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.3,
-                cacheRead: 0.02,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262114,
-            maxTokens: 262114,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "stepfun/step-3.7-flash": {
             id: "stepfun/step-3.7-flash",