@code-yeongyu/senpi 2026.5.29 → 2026.6.3

package/node_modules/@earendil-works/pi-ai/dist/models.generated.js

@@ -175,6 +175,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-opus-4-8": {
+            id: "anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5",
@@ -244,6 +262,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "au.anthropic.claude-opus-4-8": {
+            id: "au.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (AU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (AU)",
@@ -373,8 +409,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
+                input: 5.5,
+                output: 27.5,
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
@@ -391,10 +427,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -417,6 +453,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "eu.anthropic.claude-opus-4-8": {
+            id: "eu.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (EU)",
@@ -426,10 +480,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -443,10 +497,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 1000000,
             maxTokens: 64000,
@@ -539,6 +593,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-opus-4-8": {
+            id: "global.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (Global)",
@@ -625,6 +697,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "jp.anthropic.claude-opus-4-8": {
+            id: "jp.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (JP)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (JP)",
@@ -1342,6 +1432,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-opus-4-8": {
+            id: "us.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (US)",
@@ -1811,7 +1919,26 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
-            compat: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -1991,7 +2118,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2076,7 +2203,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2202,7 +2329,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2503,7 +2630,7 @@ export const MODELS = {
             provider: "azure-openai-responses",
             baseUrl: "",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -2627,7 +2754,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2686,23 +2813,6 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 8000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 32000,
-        },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
             name: "Z.AI GLM-4.7",
@@ -2917,7 +3027,26 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
-            compat: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -3425,24 +3554,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
-        "@cf/moonshotai/kimi-k2.5": {
-            id: "@cf/moonshotai/kimi-k2.5",
-            name: "Kimi K2.5",
-            api: "openai-completions",
-            provider: "cloudflare-workers-ai",
-            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
-            compat: { "sendSessionAffinityHeaders": true },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
         "@cf/moonshotai/kimi-k2.6": {
             id: "@cf/moonshotai/kimi-k2.6",
             name: "Kimi K2.6",
@@ -3813,7 +3924,7 @@ export const MODELS = {
     "github-copilot": {
         "claude-haiku-4.5": {
             id: "claude-haiku-4.5",
-            name: "Claude Haiku 4.5",
+            name: "Claude Haiku 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3822,17 +3933,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
             },
-            contextWindow: 144000,
-            maxTokens: 32000,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
         "claude-opus-4.5": {
             id: "claude-opus-4.5",
-            name: "Claude Opus 4.5",
+            name: "Claude Opus 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3840,12 +3951,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
-            contextWindow: 160000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-opus-4.6": {
@@ -3860,13 +3971,13 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 32000,
         },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
@@ -3875,54 +3986,93 @@ export const MODELS = {
             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: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 32000,
         },
-        "claude-sonnet-4.5": {
-            id: "claude-sonnet-4.5",
-            name: "Claude Sonnet 4.5",
+        "claude-opus-4.8": {
+            id: "claude-opus-4.8",
+            name: "Claude Opus 4.8",
             api: "anthropic-messages",
             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: { "supportsEagerToolInputStreaming": false },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
-            contextWindow: 144000,
-            maxTokens: 32000,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
-        "claude-sonnet-4.6": {
-            id: "claude-sonnet-4.6",
-            name: "Claude Sonnet 4.6",
+        "claude-sonnet-4": {
+            id: "claude-sonnet-4",
+            name: "Claude Sonnet 4 (latest)",
             api: "anthropic-messages",
             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: { "forceAdaptiveThinking": true },
+            compat: { "supportsEagerToolInputStreaming": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 216000,
+            maxTokens: 16000,
+        },
+        "claude-sonnet-4.5": {
+            id: "claude-sonnet-4.5",
+            name: "Claude Sonnet 4.5 (latest)",
+            api: "anthropic-messages",
+            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: { "supportsEagerToolInputStreaming": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-sonnet-4.6": {
+            id: "claude-sonnet-4.6",
+            name: "Claude Sonnet 4.6",
+            api: "anthropic-messages",
+            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: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
             contextWindow: 1000000,
             maxTokens: 32000,
         },
@@ -3934,12 +4084,12 @@ export const MODELS = {
             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: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -3947,7 +4097,7 @@ export const MODELS = {
         },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash",
+            name: "Gemini 3 Flash Preview",
             api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3956,9 +4106,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -3975,12 +4125,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gemini-3.5-flash": {
@@ -3994,12 +4144,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gpt-4.1": {
@@ -4013,36 +4163,17 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "gpt-4o": {
-            id: "gpt-4o",
-            name: "GPT-4o",
-            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: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "gpt-5-mini": {
             id: "gpt-5-mini",
-            name: "GPT-5-mini",
+            name: "GPT-5 Mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4051,9 +4182,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 264000,
@@ -4070,17 +4201,17 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
         "gpt-5.2-codex": {
             id: "gpt-5.2-codex",
-            name: "GPT-5.2-Codex",
+            name: "GPT-5.2 Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4089,9 +4220,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4099,7 +4230,7 @@ export const MODELS = {
         },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
-            name: "GPT-5.3-Codex",
+            name: "GPT-5.3 Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4108,9 +4239,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4127,9 +4258,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4137,7 +4268,7 @@ export const MODELS = {
         },
         "gpt-5.4-mini": {
             id: "gpt-5.4-mini",
-            name: "GPT-5.4 Mini",
+            name: "GPT-5.4 mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4146,9 +4277,28 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "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" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4165,32 +4315,32 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "grok-code-fast-1": {
-            id: "grok-code-fast-1",
-            name: "Grok Code Fast 1",
+        "raptor-mini": {
+            id: "raptor-mini",
+            name: "Raptor mini",
             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"],
+            input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
     },
     "google": {
@@ -4919,7 +5069,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4936,7 +5086,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4953,7 +5103,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5239,9 +5389,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5483,6 +5633,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "MiniMax-M3": {
+            id: "MiniMax-M3",
+            name: "MiniMax-M3",
+            api: "anthropic-messages",
+            provider: "minimax",
+            baseUrl: "https://api.minimax.io/anthropic",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 128000,
+        },
     },
     "minimax-cn": {
         "MiniMax-M2.7": {
@@ -5519,6 +5686,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "MiniMax-M3": {
+            id: "MiniMax-M3",
+            name: "MiniMax-M3",
+            api: "anthropic-messages",
+            provider: "minimax-cn",
+            baseUrl: "https://api.minimaxi.com/anthropic",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 128000,
+        },
     },
     "mistral": {
         "codestral-latest": {
@@ -5555,6 +5739,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "devstral-latest": {
+            id: "devstral-latest",
+            name: "Devstral 2",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "devstral-medium-2507": {
             id: "devstral-medium-2507",
             name: "Devstral Medium",
@@ -5929,6 +6130,23 @@ export const MODELS = {
             contextWindow: 8000,
             maxTokens: 8000,
         },
+        "open-mistral-nemo": {
+            id: "open-mistral-nemo",
+            name: "Open Mistral Nemo",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
         "open-mixtral-8x22b": {
             id: "open-mixtral-8x22b",
             name: "Mixtral 8x22B",
@@ -6254,11 +6472,393 @@ export const MODELS = {
             maxTokens: 262144,
         },
     },
-    "openai": {
-        "gpt-4": {
-            id: "gpt-4",
-            name: "GPT-4",
-            api: "openai-responses",
+    "nvidia": {
+        "meta/llama-3.1-70b-instruct": {
+            id: "meta/llama-3.1-70b-instruct",
+            name: "Llama 3.1 70b Instruct",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "meta/llama-3.1-8b-instruct": {
+            id: "meta/llama-3.1-8b-instruct",
+            name: "Llama 3.1 8B Instruct",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 16000,
+            maxTokens: 4096,
+        },
+        "meta/llama-3.2-11b-vision-instruct": {
+            id: "meta/llama-3.2-11b-vision-instruct",
+            name: "Llama 3.2 11b Vision Instruct",
+            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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "meta/llama-3.2-90b-vision-instruct": {
+            id: "meta/llama-3.2-90b-vision-instruct",
+            name: "Llama-3.2-90B-Vision-Instruct",
+            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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "meta/llama-3.3-70b-instruct": {
+            id: "meta/llama-3.3-70b-instruct",
+            name: "Llama 3.3 70b Instruct",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "mistralai/mistral-large-3-675b-instruct-2512": {
+            id: "mistralai/mistral-large-3-675b-instruct-2512",
+            name: "Mistral Large 3 675B Instruct 2512",
+            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: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "mistralai/mistral-small-4-119b-2603": {
+            id: "mistralai/mistral-small-4-119b-2603",
+            name: "mistral-small-4-119b-2603",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "moonshotai/kimi-k2.6": {
+            id: "moonshotai/kimi-k2.6",
+            name: "Kimi K2.6",
+            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: 262144,
+            maxTokens: 262144,
+        },
+        "nvidia/llama-3.3-nemotron-super-49b-v1": {
+            id: "nvidia/llama-3.3-nemotron-super-49b-v1",
+            name: "Llama 3.3 Nemotron Super 49B v1",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
+            id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+            name: "Llama 3.3 Nemotron Super 49B v1.5",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "nvidia/nemotron-3-nano-30b-a3b": {
+            id: "nvidia/nemotron-3-nano-30b-a3b",
+            name: "nemotron-3-nano-30b-a3b",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
+            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+            name: "Nemotron 3 Nano Omni",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "Nemotron 3 Super",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.2,
+                output: 0.8,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "nvidia/nvidia-nemotron-nano-9b-v2": {
+            id: "nvidia/nvidia-nemotron-nano-9b-v2",
+            name: "nvidia-nemotron-nano-9b-v2",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "openai/gpt-oss-20b": {
+            id: "openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "qwen/qwen3-coder-480b-a35b-instruct": {
+            id: "qwen/qwen3-coder-480b-a35b-instruct",
+            name: "Qwen3 Coder 480B A35B Instruct",
+            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: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 66536,
+        },
+        "qwen/qwen3.5-122b-a10b": {
+            id: "qwen/qwen3.5-122b-a10b",
+            name: "Qwen3.5 122B-A10B",
+            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: 262144,
+            maxTokens: 65536,
+        },
+        "stepfun-ai/step-3.5-flash": {
+            id: "stepfun-ai/step-3.5-flash",
+            name: "Step 3.5 Flash",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
+        "stepfun-ai/step-3.7-flash": {
+            id: "stepfun-ai/step-3.7-flash",
+            name: "Step 3.7 Flash",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
+        "z-ai/glm-5.1": {
+            id: "z-ai/glm-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+    },
+    "openai": {
+        "gpt-4": {
+            id: "gpt-4",
+            name: "GPT-4",
+            api: "openai-responses",
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: false,
@@ -6334,7 +6934,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -6419,7 +7019,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -6545,7 +7145,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -6828,7 +7428,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh", "minimal": null },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -6846,7 +7446,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -6970,7 +7570,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -7120,7 +7720,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 200000,
-            maxTokens: 128000,
+            maxTokens: 32000,
         },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
@@ -7179,9 +7779,28 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
-            compat: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "claude-opus-4-7": {
+            id: "claude-opus-4-7",
+            name: "Claude Opus 4.7",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "max" },
+            thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -7192,13 +7811,13 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-opus-4-7": {
-            id: "claude-opus-4-7",
-            name: "Claude Opus 4.7",
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
-            compat: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -7263,6 +7882,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "deepseek-v4-flash": {
+            id: "deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "deepseek-v4-flash-free": {
             id: "deepseek-v4-flash-free",
             name: "DeepSeek V4 Flash Free",
@@ -7647,7 +8285,7 @@ export const MODELS = {
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -7664,7 +8302,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 1,
@@ -7698,6 +8338,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7709,6 +8350,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -7891,7 +8549,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -7911,9 +8571,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7928,9 +8588,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.2,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -7970,23 +8630,22 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "qwen3.5-plus": {
-            id: "qwen3.5-plus",
-            name: "Qwen3.5 Plus",
-            api: "openai-completions",
+        "minimax-m3": {
+            id: "minimax-m3",
+            name: "MiniMax M3",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "qwen" },
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.2,
-                output: 1.2,
-                cacheRead: 0.02,
-                cacheWrite: 0.25,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 65536,
+            contextWindow: 512000,
+            maxTokens: 131072,
         },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
@@ -8006,6 +8665,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -8025,23 +8701,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "alibaba/tongyi-deepresearch-30b-a3b": {
-            id: "alibaba/tongyi-deepresearch-30b-a3b",
-            name: "Tongyi DeepResearch 30B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
-                cacheRead: 0.09,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
             name: "Amazon: Nova 2 Lite",
@@ -8301,6 +8960,42 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Anthropic: Claude Opus 4.8",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-opus-4.8-fast": {
+            id: "anthropic/claude-opus-4.8-fast",
+            name: "Anthropic: Claude Opus 4.8 (Fast)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Anthropic: Claude Sonnet 4",
@@ -8369,23 +9064,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (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: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -8437,40 +9115,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/cobuddy:free": {
-            id: "baidu/cobuddy:free",
-            name: "Baidu Qianfan: CoBuddy (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: 65536,
-        },
-        "baidu/ernie-4.5-21b-a3b": {
-            id: "baidu/ernie-4.5-21b-a3b",
-            name: "Baidu: ERNIE 4.5 21B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.07,
-                output: 0.28,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8000,
-        },
         "baidu/ernie-4.5-vl-28b-a3b": {
             id: "baidu/ernie-4.5-vl-28b-a3b",
             name: "Baidu: ERNIE 4.5 VL 28B A3B",
@@ -8599,13 +9243,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.32,
-                output: 0.8899999999999999,
+                input: 0.20020000000000002,
+                output: 0.8000999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 16000,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -8701,13 +9345,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.252,
-                output: 0.378,
-                cacheRead: 0.0252,
+                input: 0.2288,
+                output: 0.3432,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 65536,
+            maxTokens: 64000,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -8732,37 +9376,18 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.19999999999999998,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 16384,
-        },
-        "deepseek/deepseek-v4-flash:free": {
-            id: "deepseek/deepseek-v4-flash:free",
-            name: "DeepSeek: DeepSeek V4 Flash (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.0983,
+                output: 0.1966,
+                cacheRead: 0.019700000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 131072,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -8770,9 +9395,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
                 input: 0.435,
@@ -8800,40 +9425,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 4096,
         },
-        "google/gemini-2.0-flash-001": {
-            id: "google/gemini-2.0-flash-001",
-            name: "Google: Gemini 2.0 Flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "google/gemini-2.0-flash-lite-001": {
-            id: "google/gemini-2.0-flash-lite-001",
-            name: "Google: Gemini 2.0 Flash Lite",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Google: Gemini 2.5 Flash",
@@ -9311,6 +9902,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
+        "meta-llama/llama-4-maverick": {
+            id: "meta-llama/llama-4-maverick",
+            name: "Meta: Llama 4 Maverick",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 16384,
+        },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
             name: "Meta: Llama 4 Scout",
@@ -9396,39 +10004,39 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 196608,
         },
-        "minimax/minimax-m2.5:free": {
-            id: "minimax/minimax-m2.5:free",
-            name: "MiniMax: MiniMax M2.5 (free)",
+        "minimax/minimax-m2.7": {
+            id: "minimax/minimax-m2.7",
+            name: "MiniMax: MiniMax M2.7",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.27899999999999997,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 8192,
+            maxTokens: 131072,
         },
-        "minimax/minimax-m2.7": {
-            id: "minimax/minimax-m2.7",
-            name: "MiniMax: MiniMax M2.7",
+        "minimax/minimax-m3": {
+            id: "minimax/minimax-m3",
+            name: "MiniMax: MiniMax M3",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.27899999999999997,
+                input: 0.3,
                 output: 1.2,
-                cacheRead: 0,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 1048576,
+            maxTokens: 512000,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -9464,40 +10072,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "mistralai/devstral-medium": {
-            id: "mistralai/devstral-medium",
-            name: "Mistral: Devstral Medium",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "mistralai/devstral-small": {
-            id: "mistralai/devstral-small",
-            name: "Mistral: Devstral Small 1.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -9583,23 +10157,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
-        "mistralai/mistral-large-2411": {
-            id: "mistralai/mistral-large-2411",
-            name: "Mistral Large 2411",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/mistral-large-2512": {
             id: "mistralai/mistral-large-2512",
             name: "Mistral: Mistral Large 3 2512",
@@ -9753,23 +10310,6 @@ export const MODELS = {
             contextWindow: 65536,
             maxTokens: 4096,
         },
-        "mistralai/pixtral-large-2411": {
-            id: "mistralai/pixtral-large-2411",
-            name: "Mistral: Pixtral Large 2411",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/voxtral-small-24b-2507": {
             id: "mistralai/voxtral-small-24b-2507",
             name: "Mistral: Voxtral Small 24B 2507",
@@ -9861,16 +10401,35 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 4096,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10297,23 +10856,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o-audio-preview": {
-            id: "openai/gpt-4o-audio-preview",
-            name: "OpenAI: GPT-4o Audio",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-4o-mini": {
             id: "openai/gpt-4o-mini",
             name: "OpenAI: GPT-4o-mini",
@@ -10461,11 +11003,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -10478,7 +11020,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -10512,11 +11054,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -10552,7 +11094,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -10723,7 +11265,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -10828,13 +11370,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.029,
                 output: 0.14,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -11088,8 +11630,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
@@ -11105,8 +11647,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -11142,23 +11684,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
-        "qwen/qwen-2.5-7b-instruct": {
-            id: "qwen/qwen-2.5-7b-instruct",
-            name: "Qwen: Qwen2.5 7B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.04,
-                output: 0.09999999999999999,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
             name: "Qwen: Qwen-Plus",
@@ -11188,7 +11713,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -11270,13 +11795,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14950000000000002,
-                output: 1.495,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -11304,13 +11829,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.3,
+                input: 0.0428,
+                output: 0.1716,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 32000,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -11712,13 +12237,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13899999999999998,
+                input: 0.14,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -11766,7 +12291,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11783,7 +12308,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11800,7 +12325,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11814,13 +12339,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
+                input: 0.29,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11831,7 +12356,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11899,10 +12424,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
-                cacheRead: 0,
-                cacheWrite: 3.125,
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11992,6 +12517,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "StepFun: Step 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
             name: "Tencent: Hy3 preview",
@@ -12001,13 +12543,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06599999999999999,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.020999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -12128,40 +12670,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "xiaomi/mimo-v2-omni": {
-            id: "xiaomi/mimo-v2-omni",
-            name: "Xiaomi: MiMo-V2-Omni",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "xiaomi/mimo-v2-pro": {
-            id: "xiaomi/mimo-v2-pro",
-            name: "Xiaomi: MiMo-V2-Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
             name: "Xiaomi: MiMo-V2.5",
@@ -12171,9 +12679,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12188,13 +12696,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12239,13 +12747,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
+                input: 0.125,
                 output: 0.85,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -12364,7 +12872,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -12398,7 +12906,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
@@ -12511,13 +13019,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 262144,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12915,20 +13423,20 @@ export const MODELS = {
         },
         "alibaba/qwen-3-235b": {
             id: "alibaba/qwen-3-235b",
-            name: "Qwen3 235B A22b Instruct 2507",
+            name: "Qwen3 235B A22B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0.6,
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 40000,
+            contextWindow: 262144,
+            maxTokens: 16384,
         },
         "alibaba/qwen-3-30b": {
             id: "alibaba/qwen-3-30b",
@@ -13004,7 +13512,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.5,
@@ -13038,7 +13546,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.5,
@@ -13117,6 +13625,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 65536,
         },
+        "alibaba/qwen3-next-80b-a3b-instruct": {
+            id: "alibaba/qwen3-next-80b-a3b-instruct",
+            name: "Qwen3 Next 80B A3B Instruct",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "alibaba/qwen3-next-80b-a3b-thinking": {
+            id: "alibaba/qwen3-next-80b-a3b-thinking",
+            name: "Qwen3 Next 80B A3B Thinking",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
         "alibaba/qwen3-vl-thinking": {
             id: "alibaba/qwen3-vl-thinking",
             name: "Qwen3 VL 235B A22B Thinking",
@@ -13219,6 +13761,23 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-plus": {
+            id: "alibaba/qwen3.7-plus",
+            name: "Qwen 3.7 Plus",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 1.5999999999999999,
+                cacheRead: 0.08,
+                cacheWrite: 0.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -13346,7 +13905,26 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            compat: { "forceAdaptiveThinking": true },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -13505,17 +14083,17 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.77,
-                output: 0.77,
-                cacheRead: 0,
+                input: 0.27,
+                output: 1.12,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-v3.1": {
             id: "deepseek/deepseek-v3.1",
-            name: "DeepSeek-V3.1",
+            name: "DeepSeek V3.1",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -13553,8 +14131,8 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0.28,
                 output: 0.42,
@@ -13570,8 +14148,8 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0.62,
                 output: 1.85,
@@ -13588,7 +14166,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.14,
                 output: 0.28,
@@ -13605,7 +14183,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.435,
                 output: 0.87,
@@ -13808,12 +14386,12 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.39999999999999997,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14098,7 +14676,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.6,
                 output: 2.4,
@@ -14142,6 +14720,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131100,
         },
+        "minimax/minimax-m3": {
+            id: "minimax/minimax-m3",
+            name: "MiniMax M3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -14278,6 +14873,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "mistral/mistral-nemo": {
+            id: "mistral/mistral-nemo",
+            name: "Mistral Nemo 12B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.02,
+                output: 0.04,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
             name: "Mistral Small",
@@ -14431,6 +15043,23 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "NVIDIA Nemotron 3 Super 120B A12B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.65,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -14608,7 +15237,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 1.25,
                 output: 10,
@@ -14959,7 +15588,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -14970,6 +15599,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.35,
+                output: 0.75,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131000,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "GPT OSS 20B",
@@ -15140,6 +15786,40 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
+        "stepfun/step-3.5-flash": {
+            id: "stepfun/step-3.5-flash",
+            name: "StepFun 3.5 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0.02,
+            },
+            contextWindow: 262114,
+            maxTokens: 262114,
+        },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "Step 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -15353,9 +16033,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15370,9 +16050,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15418,7 +16098,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 0.6,
@@ -15572,7 +16252,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 1.4,
                 output: 4.4,
@@ -15814,24 +16494,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-ams": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-ams",
-            baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "supportsDisabledThinking": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15906,24 +16568,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-cn": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-cn",
-            baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "supportsDisabledThinking": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15998,24 +16642,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-sgp": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-sgp",
-            baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "supportsDisabledThinking": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",