@earendil-works/pi-ai 0.78.0 → 0.79.0

package/dist/models.generated.js

@@ -391,8 +391,8 @@ 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,
             },
@@ -409,10 +409,10 @@ 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,
@@ -427,10 +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,
@@ -444,10 +444,10 @@ 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,
@@ -461,10 +461,10 @@ 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,
@@ -1086,6 +1086,59 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "openai.gpt-5.4": {
+            id: "openai.gpt-5.4",
+            name: "GPT-5.4",
+            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: 2.75,
+                output: 16.5,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.5": {
+            id: "openai.gpt-5.5",
+            name: "GPT-5.5",
+            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: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-oss-120b": {
+            id: "openai.gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1103,6 +1156,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai.gpt-oss-20b": {
+            id: "openai.gpt-oss-20b",
+            name: "gpt-oss-20b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-20b-1:0": {
             id: "openai.gpt-oss-20b-1:0",
             name: "gpt-oss-20b",
@@ -1549,6 +1619,63 @@ export const MODELS = {
             maxTokens: 101376,
         },
     },
+    "ant-ling": {
+        "Ling-2.6-1T": {
+            id: "Ling-2.6-1T",
+            name: "Ling 2.6 1T",
+            api: "openai-completions",
+            provider: "ant-ling",
+            baseUrl: "https://api.ant-ling.com/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "Ling-2.6-flash": {
+            id: "Ling-2.6-flash",
+            name: "Ling 2.6 Flash",
+            api: "openai-completions",
+            provider: "ant-ling",
+            baseUrl: "https://api.ant-ling.com/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.01,
+                output: 0.02,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "Ring-2.6-1T": {
+            id: "Ring-2.6-1T",
+            name: "Ring 2.6 1T",
+            api: "openai-completions",
+            provider: "ant-ling",
+            baseUrl: "https://api.ant-ling.com/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "thinkingFormat": "ant-ling" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+    },
     "anthropic": {
         "claude-3-5-haiku-20241022": {
             id: "claude-3-5-haiku-20241022",
@@ -1847,7 +1974,7 @@ 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"],
@@ -1866,7 +1993,7 @@ 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"],
@@ -2955,7 +3082,26 @@ 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"],
@@ -3463,24 +3609,6 @@ 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",
@@ -3808,8 +3936,8 @@ export const MODELS = {
                 cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "accounts/fireworks/routers/glm-5p1-fast": {
             id: "accounts/fireworks/routers/glm-5p1-fast",
@@ -3829,6 +3957,24 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131072,
         },
+        "accounts/fireworks/routers/kimi-k2p6-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p6-fast",
+            name: "Kimi K2.6 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
         "accounts/fireworks/routers/kimi-k2p6-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p6-turbo",
             name: "Kimi K2.6 Turbo",
@@ -3851,7 +3997,7 @@ 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",
@@ -3860,17 +4006,17 @@ 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: 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",
@@ -3878,10 +4024,10 @@ 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: 200000,
             maxTokens: 32000,
@@ -3898,10 +4044,10 @@ 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: 32000,
@@ -3913,15 +4059,15 @@ 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: 200000,
             maxTokens: 32000,
@@ -3933,22 +4079,41 @@ 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: 200000,
             maxTokens: 64000,
         },
+        "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: { "supportsEagerToolInputStreaming": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                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",
+            name: "Claude Sonnet 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3957,10 +4122,10 @@ export const MODELS = {
             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: 200000,
             maxTokens: 32000,
@@ -3976,10 +4141,10 @@ export const MODELS = {
             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: 1000000,
             maxTokens: 32000,
@@ -3992,12 +4157,12 @@ 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,
@@ -4005,7 +4170,7 @@ 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",
@@ -4014,9 +4179,9 @@ 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,
@@ -4033,9 +4198,9 @@ 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: 200000,
@@ -4052,9 +4217,9 @@ 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: 200000,
@@ -4071,36 +4236,17 @@ 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",
@@ -4109,9 +4255,9 @@ 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,
@@ -4128,9 +4274,9 @@ 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,
@@ -4138,7 +4284,7 @@ export const MODELS = {
         },
         "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",
@@ -4147,9 +4293,9 @@ 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,
@@ -4157,7 +4303,7 @@ 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",
@@ -4166,9 +4312,9 @@ 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,
@@ -4185,9 +4331,9 @@ 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,
@@ -4195,7 +4341,7 @@ 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",
@@ -4204,9 +4350,28 @@ 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,
@@ -4223,32 +4388,32 @@ 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": {
@@ -5541,6 +5706,23 @@ 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": {
@@ -5577,6 +5759,23 @@ 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": {
@@ -5613,6 +5812,23 @@ 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",
@@ -5891,11 +6107,11 @@ export const MODELS = {
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
+                input: 0.4,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -5987,6 +6203,23 @@ 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",
@@ -6312,56 +6545,457 @@ export const MODELS = {
             maxTokens: 262144,
         },
     },
-    "openai": {
-        "gpt-4": {
-            id: "gpt-4",
-            name: "GPT-4",
-            api: "openai-responses",
-            provider: "openai",
-            baseUrl: "https://api.openai.com/v1",
+    "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: 30,
-                output: 60,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 128000,
+            maxTokens: 4096,
         },
-        "gpt-4-turbo": {
-            id: "gpt-4-turbo",
-            name: "GPT-4 Turbo",
-            api: "openai-responses",
-            provider: "openai",
-            baseUrl: "https://api.openai.com/v1",
+        "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: 10,
-                output: 30,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "gpt-4.1": {
-            id: "gpt-4.1",
-            name: "GPT-4.1",
-            api: "openai-responses",
-            provider: "openai",
-            baseUrl: "https://api.openai.com/v1",
+        "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: 2,
-                output: 8,
-                cacheRead: 0.5,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1047576,
+            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/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
+            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: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "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,
+            input: ["text"],
+            cost: {
+                input: 30,
+                output: 60,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "gpt-4-turbo": {
+            id: "gpt-4-turbo",
+            name: "GPT-4 Turbo",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 30,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "gpt-4.1": {
+            id: "gpt-4.1",
+            name: "GPT-4.1",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
             maxTokens: 32768,
         },
         "gpt-4.1-mini": {
@@ -6886,7 +7520,7 @@ 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,
@@ -7033,62 +7667,26 @@ export const MODELS = {
             },
             contextWindow: 200000,
             maxTokens: 100000,
-        },
-        "o4-mini-deep-research": {
-            id: "o4-mini-deep-research",
-            name: "o4-mini-deep-research",
-            api: "openai-responses",
-            provider: "openai",
-            baseUrl: "https://api.openai.com/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-    },
-    "openai-codex": {
-        "gpt-5.2": {
-            id: "gpt-5.2",
-            name: "GPT-5.2",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
-            input: ["text", "image"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.3-codex": {
-            id: "gpt-5.3-codex",
-            name: "GPT-5.3 Codex",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
+        },
+        "o4-mini-deep-research": {
+            id: "o4-mini-deep-research",
+            name: "o4-mini-deep-research",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
-            maxTokens: 128000,
+            contextWindow: 200000,
+            maxTokens: 100000,
         },
+    },
+    "openai-codex": {
         "gpt-5.3-codex-spark": {
             id: "gpt-5.3-codex-spark",
             name: "GPT-5.3 Codex Spark",
@@ -7256,7 +7854,7 @@ export const MODELS = {
             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"],
@@ -7275,7 +7873,7 @@ export const MODELS = {
             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"],
@@ -7340,6 +7938,25 @@ 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",
@@ -7803,8 +8420,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 200000,
+            maxTokens: 32000,
         },
         "minimax-m2.5": {
             id: "minimax-m2.5",
@@ -7840,9 +8457,9 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "nemotron-3-super-free": {
-            id: "nemotron-3-super-free",
-            name: "Nemotron 3 Super Free",
+        "nemotron-3-ultra-free": {
+            id: "nemotron-3-ultra-free",
+            name: "Nemotron 3 Ultra Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -7854,7 +8471,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "qwen3.5-plus": {
@@ -8069,6 +8686,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "minimax-m3": {
+            id: "minimax-m3",
+            name: "MiniMax M3",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 131072,
+        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -8084,7 +8718,7 @@ export const MODELS = {
                 cacheRead: 0.05,
                 cacheWrite: 0.625,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
         "qwen3.7-max": {
@@ -8104,6 +8738,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen3.7-plus": {
+            id: "qwen3.7-plus",
+            name: "Qwen3.7 Plus",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.04,
+                cacheWrite: 0.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -8537,40 +9188,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.14,
-                output: 0.56,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8000,
-        },
         "bytedance-seed/seed-1.6": {
             id: "bytedance-seed/seed-1.6",
             name: "ByteDance Seed: Seed 1.6",
@@ -8682,8 +9299,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2288,
-                output: 0.9144,
+                input: 0.20020000000000002,
+                output: 0.8000999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -8784,13 +9401,13 @@ 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",
@@ -8828,25 +9445,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "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 },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 384000,
-        },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
             name: "DeepSeek: DeepSeek V4 Pro",
@@ -8883,40 +9481,6 @@ 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: 1048576,
-            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",
@@ -9130,8 +9694,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
-                output: 0.13,
+                input: 0.049999999999999996,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9199,12 +9763,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.37,
-                cacheRead: 0,
+                output: 0.36,
+                cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9353,7 +9917,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.049999999999999996,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9394,6 +9958,23 @@ 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",
@@ -9403,7 +9984,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
+                input: 0.09999999999999999,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9479,39 +10060,39 @@ 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: 196608,
         },
-        "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",
@@ -9547,40 +10128,6 @@ 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",
@@ -9666,23 +10213,6 @@ 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",
@@ -9816,41 +10346,24 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
-        "mistralai/mixtral-8x22b-instruct": {
-            id: "mistralai/mixtral-8x22b-instruct",
-            name: "Mistral: Mixtral 8x22B Instruct",
-            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: 65536,
-            maxTokens: 4096,
+            contextWindow: 128000,
+            maxTokens: 16384,
         },
-        "mistralai/pixtral-large-2411": {
-            id: "mistralai/pixtral-large-2411",
-            name: "Mistral: Pixtral Large 2411",
+        "mistralai/mixtral-8x22b-instruct": {
+            id: "mistralai/mixtral-8x22b-instruct",
+            name: "Mistral: Mixtral 8x22B Instruct",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 2,
                 output: 6,
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 65536,
             maxTokens: 4096,
         },
         "mistralai/voxtral-small-24b-2507": {
@@ -9944,17 +10457,17 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "supportsDeveloperRole": false },
+            compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.6799999999999999,
+                output: 3.41,
+                cacheRead: 0.33999999999999997,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "moonshotai/kimi-k2.6:free": {
             id: "moonshotai/kimi-k2.6:free",
@@ -9962,7 +10475,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "supportsDeveloperRole": false },
+            compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -9974,23 +10487,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "nex-agi/deepseek-v3.1-nex-n1": {
-            id: "nex-agi/deepseek-v3.1-nex-n1",
-            name: "Nex AGI: DeepSeek V3.1 Nex N1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.135,
-                output: 0.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 163840,
-        },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
             name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -10000,7 +10496,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.39999999999999997,
                 output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10093,6 +10589,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 262144,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "NVIDIA: Nemotron 3 Ultra",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 16384,
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b:free": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b:free",
+            name: "NVIDIA: Nemotron 3 Ultra (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: 1000000,
+            maxTokens: 65536,
+        },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
             id: "nvidia/nemotron-nano-12b-v2-vl:free",
             name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -10212,40 +10742,6 @@ export const MODELS = {
             contextWindow: 8191,
             maxTokens: 4096,
         },
-        "openai/gpt-4-0314": {
-            id: "openai/gpt-4-0314",
-            name: "OpenAI: GPT-4 (older v0314)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 30,
-                output: 60,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8191,
-            maxTokens: 4096,
-        },
-        "openai/gpt-4-1106-preview": {
-            id: "openai/gpt-4-1106-preview",
-            name: "OpenAI: GPT-4 Turbo (older v1106)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 10,
-                output: 30,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-4-turbo": {
             id: "openai/gpt-4-turbo",
             name: "OpenAI: GPT-4 Turbo",
@@ -10913,13 +11409,13 @@ 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",
@@ -11227,23 +11723,6 @@ 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",
@@ -11338,7 +11817,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
+                input: 0.09,
                 output: 0.09999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11355,13 +11834,13 @@ 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",
@@ -11372,13 +11851,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 20000,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -11389,13 +11868,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.3,
+                input: 0.04815,
+                output: 0.19305,
                 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",
@@ -11797,13 +12276,13 @@ 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",
@@ -11831,13 +12310,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
+                input: 0.09999999999999999,
                 output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -11899,13 +12378,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.29,
-                output: 3.1999999999999997,
+                input: 0.28900000000000003,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262140,
+            maxTokens: 131072,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11992,6 +12471,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.7-plus": {
+            id: "qwen/qwen3.7-plus",
+            name: "Qwen: Qwen3.7 Plus",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 1.5999999999999999,
+                cacheRead: 0.08,
+                cacheWrite: 0.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -12026,23 +12522,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 128000,
         },
-        "sao10k/l3-euryale-70b": {
-            id: "sao10k/l3-euryale-70b",
-            name: "Sao10k: Llama 3 Euryale 70B v2.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.48,
-                output: 1.48,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
         "sao10k/l3.1-euryale-70b": {
             id: "sao10k/l3.1-euryale-70b",
             name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -12230,40 +12709,6 @@ 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",
@@ -12613,13 +13058,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.6799999999999999,
+                output: 3.41,
+                cacheRead: 0.33999999999999997,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12810,7 +13255,7 @@ export const MODELS = {
         },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
-            name: "DeepSeek V3",
+            name: "DeepSeek-V3",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -12958,6 +13403,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512300,
+            maxTokens: 512300,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -13021,7 +13485,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.22,
@@ -13073,7 +13537,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.3,
                 output: 7.8,
@@ -13106,7 +13570,7 @@ 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,
@@ -13140,7 +13604,7 @@ 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,
@@ -13219,6 +13683,40 @@ 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",
@@ -13311,14 +13809,31 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.25,
                 output: 3.75,
                 cacheRead: 0.25,
                 cacheWrite: 1.5625,
             },
-            contextWindow: 991000,
+            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": {
@@ -13448,7 +13963,7 @@ 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"],
@@ -13467,7 +13982,7 @@ 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"],
@@ -13626,17 +14141,17 @@ 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",
@@ -13674,8 +14189,8 @@ 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,
@@ -13691,8 +14206,8 @@ 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,
@@ -13709,7 +14224,7 @@ 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,
@@ -13736,40 +14251,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "google/gemini-2.0-flash": {
-            id: "google/gemini-2.0-flash",
-            name: "Gemini 2.0 Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
-        "google/gemini-2.0-flash-lite": {
-            id: "google/gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Gemini 2.5 Flash",
@@ -13929,12 +14410,12 @@ 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,
@@ -14236,7 +14717,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.3,
                 output: 1.2,
@@ -14253,7 +14734,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.6,
                 output: 2.4,
@@ -14263,6 +14744,23 @@ 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",
@@ -14399,6 +14897,23 @@ 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",
@@ -14552,6 +15067,40 @@ 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-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -14729,7 +15278,7 @@ 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,
@@ -15091,6 +15640,23 @@ 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",
@@ -15261,6 +15827,40 @@ 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",
@@ -15539,7 +16139,7 @@ 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,
@@ -15693,7 +16293,7 @@ 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,
@@ -16248,5 +16848,97 @@ export const MODELS = {
             maxTokens: 131072,
         },
     },
+    "zai-coding-cn": {
+        "glm-4.5-air": {
+            id: "glm-4.5-air",
+            name: "GLM-4.5-Air",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 98304,
+        },
+        "glm-4.7": {
+            id: "glm-4.7",
+            name: "GLM-4.7",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "glm-5-turbo": {
+            id: "glm-5-turbo",
+            name: "GLM-5-Turbo",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
+        "glm-5v-turbo": {
+            id: "glm-5v-turbo",
+            name: "GLM-5V-Turbo",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
+    },
 };
 //# sourceMappingURL=models.generated.js.map