@elyracode/ai 0.9.24 → 0.9.25

package/dist/models.generated.js

@@ -1417,10 +1417,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.22,
+                output: 1.32,
+                cacheRead: 0.022,
+                cacheWrite: 0.275,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -1434,10 +1434,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 6.88,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -1451,10 +1451,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2.2,
+                output: 13.2,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -2803,10 +2803,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2839,10 +2839,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3229,6 +3229,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-5": {
+            id: "claude-opus-5",
+            name: "Claude Opus 5",
+            api: "anthropic-messages",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4 (latest)",
@@ -3998,39 +4015,39 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "accounts/fireworks/models/deepseek-v4-pro": {
-            id: "accounts/fireworks/models/deepseek-v4-pro",
-            name: "DeepSeek V4 Pro",
+        "accounts/fireworks/models/deepseek-v4-flash-0731": {
+            id: "accounts/fireworks/models/deepseek-v4-flash-0731",
+            name: "DeepSeek V4 Flash 0731",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "accounts/fireworks/models/glm-5p1": {
-            id: "accounts/fireworks/models/glm-5p1",
-            name: "GLM 5.1",
+        "accounts/fireworks/models/deepseek-v4-pro": {
+            id: "accounts/fireworks/models/deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
                 cacheWrite: 0,
             },
-            contextWindow: 202800,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "accounts/fireworks/models/glm-5p2": {
             id: "accounts/fireworks/models/glm-5p2",
@@ -4117,6 +4134,23 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "accounts/fireworks/models/kimi-k3": {
+            id: "accounts/fireworks/models/kimi-k3",
+            name: "Kimi K3",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/models/minimax-m2p7": {
             id: "accounts/fireworks/models/minimax-m2p7",
             name: "MiniMax-M2.7",
@@ -4168,23 +4202,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "accounts/fireworks/routers/glm-5p1-fast": {
-            id: "accounts/fireworks/routers/glm-5p1-fast",
-            name: "GLM 5.1 Fast",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 2.8,
-                output: 8.8,
-                cacheRead: 0.52,
-                cacheWrite: 0,
-            },
-            contextWindow: 202800,
-            maxTokens: 131072,
-        },
         "accounts/fireworks/routers/glm-5p2-fast": {
             id: "accounts/fireworks/routers/glm-5p2-fast",
             name: "GLM 5.2 Fast",
@@ -4253,6 +4270,23 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "accounts/fireworks/routers/kimi-k3-fast": {
+            id: "accounts/fireworks/routers/kimi-k3-fast",
+            name: "Kimi K3 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 4.5,
+                output: 22.5,
+                cacheRead: 0.45,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "github-copilot": {
         "claude-fable-5": {
@@ -4369,6 +4403,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
+        "claude-opus-5": {
+            id: "claude-opus-5",
+            name: "Claude Opus 5",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4 (latest)",
@@ -4444,44 +4497,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "gemini-2.5-pro": {
-            id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
             name: "Gemini 3.1 Pro Preview",
@@ -4520,6 +4535,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
+        "gemini-3.6-flash": {
+            id: "gemini-3.6-flash",
+            name: "Gemini 3.6 Flash",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "gpt-4.1": {
             id: "gpt-4.1",
             name: "GPT-4.1",
@@ -4702,10 +4736,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4740,14 +4774,33 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 0,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "grok-4.5": {
+            id: "grok-4.5",
+            name: "Grok 4.5",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 128000,
+        },
         "kimi-k2.7-code": {
             id: "kimi-k2.7-code",
             name: "Kimi K2.7 Code",
@@ -6028,6 +6081,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
+        "deepseek-ai/DeepSeek-V4-Flash-0731": {
+            id: "deepseek-ai/DeepSeek-V4-Flash-0731",
+            name: "DeepSeek V4 Flash 0731",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "deepseek-ai/DeepSeek-V4-Pro": {
             id: "deepseek-ai/DeepSeek-V4-Pro",
             name: "DeepSeek V4 Pro",
@@ -6208,6 +6279,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "moonshotai/Kimi-K3": {
+            id: "moonshotai/Kimi-K3",
+            name: "Kimi K3",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -6280,8 +6369,62 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 256000,
         },
-        "zai-org/GLM-4.5": {
-            id: "zai-org/GLM-4.5",
+        "tencent/Hy3": {
+            id: "tencent/Hy3",
+            name: "Hy3",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.58,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 64000,
+        },
+        "thinkingmachines/Inkling": {
+            id: "thinkingmachines/Inkling",
+            name: "Inkling",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
+        "thinkingmachines/Inkling-Small": {
+            id: "thinkingmachines/Inkling-Small",
+            name: "Inkling Small",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 1048576,
+        },
+        "zai-org/GLM-4.5": {
+            id: "zai-org/GLM-4.5",
             name: "GLM-4.5",
             api: "openai-completions",
             provider: "huggingface",
@@ -7134,6 +7277,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
+        "voxtral-small-latest": {
+            id: "voxtral-small-latest",
+            name: "Voxtral Small (latest)",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32000,
+            maxTokens: 32000,
+        },
     },
     "moonshotai": {
         "kimi-k2-0711-preview": {
@@ -7990,10 +8150,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8026,10 +8186,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8562,7 +8722,7 @@ export const MODELS = {
         },
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
+            name: "DeepSeek V4 Flash 0731",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -8581,7 +8741,7 @@ export const MODELS = {
         },
         "deepseek-v4-flash-free": {
             id: "deepseek-v4-flash-free",
-            name: "DeepSeek V4 Flash Free",
+            name: "DeepSeek V4 Flash Free (New)",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -9056,10 +9216,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -9185,6 +9345,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k3": {
+            id: "kimi-k3",
+            name: "Kimi K3",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "laguna-s-2.1-free": {
             id: "laguna-s-2.1-free",
             name: "Laguna S 2.1 Free",
@@ -9359,7 +9536,7 @@ export const MODELS = {
     "opencode-go": {
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
+            name: "DeepSeek V4 Flash (New)",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9429,6 +9606,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "gpt-5.6-luna": {
+            id: "gpt-5.6-luna",
+            name: "GPT-5.6 Luna (2x usage)",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
@@ -9499,7 +9694,7 @@ export const MODELS = {
         },
         "kimi-k3": {
             id: "kimi-k3",
-            name: "Kimi K3 (2x usage)",
+            name: "Kimi K3",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9634,6 +9829,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen3.8-max": {
+            id: "qwen3.8-max",
+            name: "Qwen3.8 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -10093,13 +10305,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.7999999999999999,
+                input: 0.22,
+                output: 0.85,
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 80000,
+            maxTokens: 262144,
         },
         "arcee-ai/virtuoso-large": {
             id: "arcee-ai/virtuoso-large",
@@ -10263,8 +10475,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.20020000000000002,
-                output: 0.8000999999999999,
+                input: 0.2574,
+                output: 1.0287,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10392,7 +10604,7 @@ export const MODELS = {
         },
         "deepseek/deepseek-v4-flash": {
             id: "deepseek/deepseek-v4-flash",
-            name: "DeepSeek: DeepSeek V4 Flash",
+            name: "DeepSeek: DeepSeek V4 Flash 0423",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10401,13 +10613,32 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.098,
-                output: 0.196,
-                cacheRead: 0.0196,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 393216,
+        },
+        "deepseek/deepseek-v4-flash-0731": {
+            id: "deepseek/deepseek-v4-flash-0731",
+            name: "DeepSeek: DeepSeek V4 Flash 0731",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.018,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -10440,7 +10671,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 2.5,
                 cacheRead: 0.03,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -10457,7 +10688,7 @@ export const MODELS = {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
                 cacheRead: 0.01,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -10525,7 +10756,7 @@ export const MODELS = {
                 input: 0.5,
                 output: 3,
                 cacheRead: 0.049999999999999996,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -10559,7 +10790,7 @@ export const MODELS = {
                 input: 0.25,
                 output: 1.5,
                 cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10576,7 +10807,7 @@ export const MODELS = {
                 input: 0.25,
                 output: 1.5,
                 cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10627,7 +10858,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 9,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10644,7 +10875,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 2.5,
                 cacheRead: 0.03,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10661,7 +10892,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 7.5,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10709,13 +10940,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.12,
-                output: 0.35,
-                cacheRead: 0.049999999999999996,
+                input: 0.07,
+                output: 0.33999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 16384,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -10743,9 +10974,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
-                output: 0.39999999999999997,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.33999999999999997,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11159,23 +11390,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "mistralai/devstral-2512": {
-            id: "mistralai/devstral-2512",
-            name: "Mistral: Devstral 2 2512",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 4096,
-        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -11389,13 +11603,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
+                input: 0.075,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
             id: "mistralai/mixtral-8x22b-instruct",
@@ -11508,9 +11722,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.6,
+                output: 3.41,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11525,8 +11739,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.82,
-                output: 3.75,
+                input: 0.73,
+                output: 3.5,
                 cacheRead: 0.15,
                 cacheWrite: 0,
             },
@@ -11595,11 +11809,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
+            maxTokens: 262144,
         },
         "nvidia/nemotron-3-nano-30b-a3b:free": {
             id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -11644,13 +11858,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.44999999999999996,
+                input: 0.08499999999999999,
+                output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
             id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -11678,13 +11892,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.2,
-                cacheRead: 0.09999999999999999,
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 512288,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11907,23 +12121,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-codex": {
-            id: "openai/gpt-5-codex",
-            name: "OpenAI: GPT-5 Codex",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-mini": {
             id: "openai/gpt-5-mini",
             name: "OpenAI: GPT-5 Mini",
@@ -11992,23 +12189,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.1-chat": {
-            id: "openai/gpt-5.1-chat",
-            name: "OpenAI: GPT-5.1 Chat",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
             name: "OpenAI: GPT-5.1-Codex",
@@ -12020,7 +12200,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -12054,11 +12234,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 100000,
+            maxTokens: 128000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -12285,10 +12465,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 0.09999999999999999,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12302,10 +12482,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 0.09999999999999999,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12353,10 +12533,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 1,
+                output: 6,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12370,10 +12550,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 1,
+                output: 6,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12455,13 +12635,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.029,
-                output: 0.14,
-                cacheRead: 0,
+                input: 0.03,
+                output: 0.13,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -12531,23 +12711,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o3-deep-research": {
-            id: "openai/o3-deep-research",
-            name: "OpenAI: o3 Deep Research",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 40,
-                cacheRead: 2.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/o3-mini": {
             id: "openai/o3-mini",
             name: "OpenAI: o3 Mini",
@@ -12616,23 +12779,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o4-mini-deep-research": {
-            id: "openai/o4-mini-deep-research",
-            name: "OpenAI: o4 Mini Deep Research",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/o4-mini-high": {
             id: "openai/o4-mini-high",
             name: "OpenAI: o4 Mini High",
@@ -12701,40 +12847,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
-        "poolside/laguna-m.1": {
-            id: "poolside/laguna-m.1",
-            name: "Poolside: Laguna M.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.39999999999999997,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "poolside/laguna-m.1:free": {
-            id: "poolside/laguna-m.1:free",
-            name: "Poolside: Laguna M.1 (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "poolside/laguna-s-2.1": {
             id: "poolside/laguna-s-2.1",
             name: "Poolside: Laguna S 2.1",
@@ -12744,9 +12856,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.19999999999999998,
-                cacheRead: 0.01,
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.009,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12829,8 +12941,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.09999999999999999,
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12880,10 +12992,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.78,
+                input: 0.39999999999999997,
+                output: 1.2,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0.5,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -12931,13 +13043,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.55,
+                input: 0.14950000000000002,
+                output: 0.5980000000000001,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -12948,13 +13060,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 3,
+                input: 0.22999999999999998,
+                output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -12965,13 +13077,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -12982,13 +13094,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
+                input: 0.04815,
+                output: 0.19305,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 32000,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -12999,8 +13111,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 1.56,
+                input: 0.19999999999999998,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13101,7 +13213,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.11,
+                input: 0.12,
                 output: 0.7999999999999999,
                 cacheRead: 0.07,
                 cacheWrite: 0,
@@ -13141,7 +13253,7 @@ export const MODELS = {
                 cacheWrite: 0.975,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 65536,
         },
         "qwen/qwen3-max-thinking": {
             id: "qwen/qwen3-max-thinking",
@@ -13158,7 +13270,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 65536,
         },
         "qwen/qwen3-next-80b-a3b-instruct": {
             id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -13186,8 +13298,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.0975,
-                output: 0.78,
+                input: 0.15,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13220,8 +13332,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.26,
-                output: 2.6,
+                input: 0.98,
+                output: 3.95,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13237,13 +13349,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13254,8 +13366,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 1.56,
+                input: 0.19999999999999998,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13305,8 +13417,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.117,
-                output: 1.365,
+                input: 0.18,
+                output: 2.0999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13458,13 +13570,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.288,
+                input: 0.28900000000000003,
                 output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -13509,10 +13621,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.04,
-                output: 6.24,
+                input: 1.0270000000000001,
+                output: 6.162,
                 cacheRead: 0,
-                cacheWrite: 1.3,
+                cacheWrite: 1.28375,
             },
             contextWindow: 262144,
             maxTokens: 65536,
@@ -13534,6 +13646,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.7-flash": {
+            id: "qwen/qwen3.7-flash",
+            name: "Qwen: Qwen3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.03,
+                output: 0.13,
+                cacheRead: 0.006,
+                cacheWrite: 0.038000000000000006,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "qwen/qwen3.7-max": {
             id: "qwen/qwen3.7-max",
             name: "Qwen: Qwen3.7 Max",
@@ -13549,7 +13678,7 @@ export const MODELS = {
                 cacheWrite: 1.84375,
             },
             contextWindow: 1000000,
-            maxTokens: 65536,
+            maxTokens: 131072,
         },
         "qwen/qwen3.7-plus": {
             id: "qwen/qwen3.7-plus",
@@ -13566,7 +13695,24 @@ export const MODELS = {
                 cacheWrite: 0.39999999999999997,
             },
             contextWindow: 1000000,
-            maxTokens: 65536,
+            maxTokens: 131072,
+        },
+        "qwen/qwen3.8-max": {
+            id: "qwen/qwen3.8-max",
+            name: "Qwen: Qwen3.8 Max",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
@@ -13701,8 +13847,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 32768,
+            contextWindow: 1024000,
+            maxTokens: 1024000,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -13721,6 +13867,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 4096,
         },
+        "thinkingmachines/inkling-small": {
+            id: "thinkingmachines/inkling-small",
+            name: "Thinking Machines: Inkling Small",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 4096,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -14019,9 +14182,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.7868,
-                output: 2.4728,
-                cacheRead: 0.14612,
+                input: 0.6286,
+                output: 1.9756000000000002,
+                cacheRead: 0.11674,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14113,6 +14276,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "~deepseek/deepseek-v4-flash-latest": {
+            id: "~deepseek/deepseek-v4-flash-latest",
+            name: "DeepSeek V4 Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.018,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
             name: "Google Gemini Flash Latest",
@@ -14125,7 +14307,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 7.5,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.0833333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -14156,13 +14338,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
+                input: 2.9000000000000004,
+                output: 14,
+                cacheRead: 0.29,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 1048576,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -14323,7 +14505,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 3.75,
-                cacheRead: 0,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14423,6 +14605,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "moonshotai/Kimi-K3": {
+            id: "moonshotai/Kimi-K3",
+            name: "Kimi K3",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
             name: "Nemotron 3 Ultra 550B A55B",
@@ -14894,6 +15095,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-flash": {
+            id: "alibaba/qwen3.7-flash",
+            name: "Qwen 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.03,
+                output: 0.13,
+                cacheRead: 0.006,
+                cacheWrite: 0.038000000000000006,
+            },
+            contextWindow: 991000,
+            maxTokens: 64000,
+        },
         "alibaba/qwen3.7-max": {
             id: "alibaba/qwen3.7-max",
             name: "Qwen 3.7 Max",
@@ -14928,6 +15146,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.8-max": {
+            id: "alibaba/qwen3.8-max",
+            name: "Qwen 3.8 Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "amazon/nova-2-lite": {
             id: "amazon/nova-2-lite",
             name: "Nova 2 Lite",
@@ -15135,24 +15370,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.7-fast": {
-            id: "anthropic/claude-opus-4.7-fast",
-            name: "Claude Opus 4.7 (Fast)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 30,
-                output: 150,
-                cacheRead: 3,
-                cacheWrite: 37.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.8": {
             id: "anthropic/claude-opus-4.8",
             name: "Claude Opus 4.8",
@@ -15467,7 +15684,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.62,
@@ -15487,8 +15704,25 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
+                input: 0.19999999999999998,
+                output: 0.39999999999999997,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-flash-0731": {
+            id: "deepseek/deepseek-v4-flash-0731",
+            name: "DeepSeek V4 Flash 0731",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.13,
+                output: 0.26,
                 cacheRead: 0.028,
                 cacheWrite: 0,
             },
@@ -15580,23 +15814,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65000,
         },
-        "google/gemini-3-pro-preview": {
-            id: "google/gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 64000,
-        },
         "google/gemini-3.1-flash-lite": {
             id: "google/gemini-3.1-flash-lite",
             name: "Gemini 3.1 Flash Lite",
@@ -15614,23 +15831,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65000,
         },
-        "google/gemini-3.1-flash-lite-preview": {
-            id: "google/gemini-3.1-flash-lite-preview",
-            name: "Gemini 3.1 Flash Lite Preview",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1.5,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 65000,
-        },
         "google/gemini-3.1-pro-preview": {
             id: "google/gemini-3.1-pro-preview",
             name: "Gemini 3.1 Pro Preview",
@@ -15808,7 +16008,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.6,
@@ -15859,7 +16059,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.74,
                 output: 2.96,
@@ -16058,7 +16258,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
-            name: "MiniMax M2.7",
+            name: "Minimax M2.7",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -16216,7 +16416,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
@@ -16233,7 +16433,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.15,
@@ -16301,7 +16501,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.15,
@@ -16464,6 +16664,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "moonshotai/kimi-k3-fast": {
+            id: "moonshotai/kimi-k3-fast",
+            name: "Kimi K3 Fast",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 4.5,
+                output: 22.5,
+                cacheRead: 0.44999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
             name: "Nemotron 3 Nano 30B A3B",
@@ -16668,23 +16885,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-chat": {
-            id: "openai/gpt-5-chat",
-            name: "GPT 5 Chat",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-5-codex": {
             id: "openai/gpt-5-codex",
             name: "GPT-5-Codex",
@@ -16696,7 +16896,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -16764,7 +16964,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -16798,7 +16998,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -16815,7 +17015,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -16856,24 +17056,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.2-chat": {
-            id: "openai/gpt-5.2-chat",
-            name: "GPT 5.2 Chat",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
             name: "GPT 5.2 Codex",
@@ -17063,10 +17245,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -17097,10 +17279,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -17316,7 +17498,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.09,
                 output: 0.3,
@@ -17377,6 +17559,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "thinkingmachines/inkling-small": {
+            id: "thinkingmachines/inkling-small",
+            name: "Inkling Small",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -17760,9 +17959,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.95,
-                output: 3.15,
-                cacheRead: 0.19999999999999998,
+                input: 1,
+                output: 3.1999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 202800,
@@ -17794,8 +17993,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.3,
-                output: 4.300000000000001,
+                input: 1.4,
+                output: 4.4,
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
@@ -17811,12 +18010,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.1,
+                output: 3.851,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
-            contextWindow: 1040000,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "zai/glm-5.2-fast": {
@@ -18171,24 +18370,6 @@ export const MODELS = {
         },
     },
     "zai": {
-        "glm-4.5-air": {
-            id: "glm-4.5-air",
-            name: "GLM-4.5-Air",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/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",
@@ -18225,24 +18406,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
-        "glm-5.1": {
-            id: "glm-5.1",
-            name: "GLM-5.1",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/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-5.2": {
             id: "glm-5.2",
             name: "GLM-5.2",
@@ -18261,22 +18424,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "glm-5v-turbo": {
-            id: "glm-5v-turbo",
-            name: "GLM-5V-Turbo",
+        "glm-5.2-highspeed": {
+            id: "glm-5.2-highspeed",
+            name: "GLM-5.2 Highspeed",
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
             compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0,
                 output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 131072,
         },
     },