@hyperspaceng/neural-ai 0.70.1 → 0.70.6

package/dist/models.generated.js

@@ -2536,8 +2536,25 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
             contextWindow: 1050000,
-            maxTokens: 130000,
+            maxTokens: 128000,
         },
         "o1": {
             id: "o1",
@@ -2746,6 +2763,190 @@ export const MODELS = {
             maxTokens: 40000,
         },
     },
+    "cloudflare-workers-ai": {
+        "@cf/google/gemma-4-26b-a4b-it": {
+            id: "@cf/google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            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: 0.1,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
+        "@cf/meta/llama-4-scout-17b-16e-instruct": {
+            id: "@cf/meta/llama-4-scout-17b-16e-instruct",
+            name: "Llama 4 Scout 17B 16E Instruct",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.27,
+                output: 0.85,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@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",
+            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: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "@cf/nvidia/nemotron-3-120b-a12b": {
+            id: "@cf/nvidia/nemotron-3-120b-a12b",
+            name: "Nemotron 3 Super 120B",
+            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"],
+            cost: {
+                input: 0.5,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "@cf/openai/gpt-oss-120b": {
+            id: "@cf/openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            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"],
+            cost: {
+                input: 0.35,
+                output: 0.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@cf/openai/gpt-oss-20b": {
+            id: "@cf/openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
+            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"],
+            cost: {
+                input: 0.2,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@cf/zai-org/glm-4.7-flash": {
+            id: "@cf/zai-org/glm-4.7-flash",
+            name: "GLM-4.7-Flash",
+            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"],
+            cost: {
+                input: 0.06,
+                output: 0.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+    },
+    "deepseek": {
+        "deepseek-v4-flash": {
+            id: "deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "deepseek",
+            baseUrl: "https://api.deepseek.com",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek-v4-pro": {
+            id: "deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "deepseek",
+            baseUrl: "https://api.deepseek.com",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+    },
     "fireworks": {
         "accounts/fireworks/models/deepseek-v3p1": {
             id: "accounts/fireworks/models/deepseek-v3p1",
@@ -2781,6 +2982,23 @@ export const MODELS = {
             contextWindow: 160000,
             maxTokens: 160000,
         },
+        "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: 1.74,
+                output: 3.48,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/glm-4p5": {
             id: "accounts/fireworks/models/glm-4p5",
             name: "GLM 4.5",
@@ -3496,6 +3714,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            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,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -5001,6 +5237,24 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 65536,
         },
+        "deepseek-ai/DeepSeek-V4-Pro": {
+            id: "deepseek-ai/DeepSeek-V4-Pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 393216,
+        },
         "moonshotai/Kimi-K2-Instruct": {
             id: "moonshotai/Kimi-K2-Instruct",
             name: "Kimi-K2-Instruct",
@@ -6295,8 +6549,25 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
             contextWindow: 1050000,
-            maxTokens: 130000,
+            maxTokens: 128000,
         },
         "o1": {
             id: "o1",
@@ -6603,7 +6874,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
     },
@@ -6625,23 +6896,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 128000,
         },
-        "claude-3-5-haiku": {
-            id: "claude-3-5-haiku",
-            name: "Claude Haiku 3.5",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -7099,7 +7353,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
-            maxTokens: 130000,
+            maxTokens: 128000,
         },
         "gpt-5.5-pro": {
             id: "gpt-5.5-pro",
@@ -7296,12 +7550,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7313,12 +7568,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.74,
                 output: 3.48,
-                cacheRead: 0.145,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7338,8 +7594,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "glm-5.1": {
             id: "glm-5.1",
@@ -7355,8 +7611,8 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "kimi-k2.5": {
             id: "kimi-k2.5",
@@ -7440,7 +7696,7 @@ export const MODELS = {
                 cacheRead: 0.08,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "mimo-v2.5-pro": {
@@ -8267,12 +8523,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -8284,12 +8541,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -8652,18 +8910,18 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ling-2.6-flash:free": {
-            id: "inclusionai/ling-2.6-flash:free",
-            name: "inclusionAI: Ling-2.6-flash (free)",
+        "inclusionai/ling-2.6-flash": {
+            id: "inclusionai/ling-2.6-flash",
+            name: "inclusionAI: Ling-2.6-flash",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.24,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9120,7 +9378,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.01,
+                input: 0.02,
                 output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9434,6 +9692,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
+            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
+            name: "NVIDIA: Nemotron 3 Nano Omni (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
         "nvidia/nemotron-3-super-120b-a12b": {
             id: "nvidia/nemotron-3-super-120b-a12b",
             name: "NVIDIA: Nemotron 3 Super",
@@ -10505,6 +10780,40 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
+        "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: 131072,
+            maxTokens: 8192,
+        },
+        "poolside/laguna-xs.2:free": {
+            id: "poolside/laguna-xs.2:free",
+            name: "Poolside: Laguna XS.2 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
             name: "Prime Intellect: INTELLECT-3",
@@ -10531,8 +10840,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.39,
+                input: 0.36,
+                output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10821,8 +11130,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.22,
-                output: 1,
-                cacheRead: 0.022,
+                output: 1.7999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11236,9 +11545,26 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwen3.6-plus": {
-            id: "qwen/qwen3.6-plus",
-            name: "Qwen: Qwen3.6 Plus",
+        "qwen/qwen3.5-plus-20260420": {
+            id: "qwen/qwen3.5-plus-20260420",
+            name: "Qwen: Qwen3.5 Plus 2026-04-20",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.6-27b": {
+            id: "qwen/qwen3.6-27b",
+            name: "Qwen: Qwen3.6 27B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -11246,29 +11572,63 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.325,
-                output: 1.95,
+                output: 3.25,
                 cacheRead: 0,
-                cacheWrite: 0.40625,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.6-flash": {
+            id: "qwen/qwen3.6-flash",
+            name: "Qwen: Qwen3.6 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0.3125,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwq-32b": {
-            id: "qwen/qwq-32b",
-            name: "Qwen: QwQ 32B",
+        "qwen/qwen3.6-max-preview": {
+            id: "qwen/qwen3.6-max-preview",
+            name: "Qwen: Qwen3.6 Max Preview",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.58,
+                input: 1.04,
+                output: 6.24,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 1.3,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.6-plus": {
+            id: "qwen/qwen3.6-plus",
+            name: "Qwen: Qwen3.6 Plus",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.325,
+                output: 1.95,
+                cacheRead: 0,
+                cacheWrite: 0.40625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
         },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
@@ -11899,6 +12259,23 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "~anthropic/claude-haiku-latest": {
+            id: "~anthropic/claude-haiku-latest",
+            name: "Anthropic Claude Haiku Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
         "~anthropic/claude-opus-latest": {
             id: "~anthropic/claude-opus-latest",
             name: "Anthropic: Claude Opus Latest",
@@ -11916,6 +12293,108 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "~anthropic/claude-sonnet-latest": {
+            id: "~anthropic/claude-sonnet-latest",
+            name: "Anthropic Claude Sonnet Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "~google/gemini-flash-latest": {
+            id: "~google/gemini-flash-latest",
+            name: "Google Gemini Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~google/gemini-pro-latest": {
+            id: "~google/gemini-pro-latest",
+            name: "Google Gemini Pro Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~moonshotai/kimi-latest": {
+            id: "~moonshotai/kimi-latest",
+            name: "MoonshotAI Kimi Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.7448,
+                output: 4.655,
+                cacheRead: 0.1463,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "~openai/gpt-latest": {
+            id: "~openai/gpt-latest",
+            name: "OpenAI GPT Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "~openai/gpt-mini-latest": {
+            id: "~openai/gpt-mini-latest",
+            name: "OpenAI GPT Mini Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -12592,7 +13071,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -12607,9 +13086,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -15050,24 +15529,6 @@ export const MODELS = {
         },
     },
     "zai": {
-        "glm-4.5": {
-            id: "glm-4.5",
-            name: "GLM-4.5",
-            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-4.5-air": {
             id: "glm-4.5-air",
             name: "GLM-4.5-Air",
@@ -15086,78 +15547,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 98304,
         },
-        "glm-4.5-flash": {
-            id: "glm-4.5-flash",
-            name: "GLM-4.5-Flash",
-            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-4.5v": {
-            id: "glm-4.5v",
-            name: "GLM-4.5V",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 64000,
-            maxTokens: 16384,
-        },
-        "glm-4.6": {
-            id: "glm-4.6",
-            name: "GLM-4.6",
-            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: 204800,
-            maxTokens: 131072,
-        },
-        "glm-4.6v": {
-            id: "glm-4.6v",
-            name: "GLM-4.6V",
-            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"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "glm-4.7": {
             id: "glm-4.7",
             name: "GLM-4.7",
@@ -15176,60 +15565,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "glm-4.7-flash": {
-            id: "glm-4.7-flash",
-            name: "GLM-4.7-Flash",
-            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-4.7-flashx": {
-            id: "glm-4.7-flashx",
-            name: "GLM-4.7-FlashX",
-            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: 0.07,
-                output: 0.4,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 131072,
-        },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM-5",
-            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: 204800,
-            maxTokens: 131072,
-        },
         "glm-5-turbo": {
             id: "glm-5-turbo",
             name: "GLM-5-Turbo",