@psnext/slingcli 2.5.20260617-1 → 2.5.20260621-1

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

@@ -4227,7 +4227,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4247,7 +4247,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4305,6 +4305,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": "low", "xhigh": "max" },
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -4562,25 +4563,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "raptor-mini": {
-            id: "raptor-mini",
-            name: "Raptor mini",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 2,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
     },
     "google": {
         "gemini-2.0-flash": {
@@ -4801,11 +4783,12 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4818,10 +4801,11 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
+                input: 0.25,
+                output: 1.5,
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
@@ -4864,132 +4848,11 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "gemma-4-E2B-it": {
-            id: "gemma-4-E2B-it",
-            name: "Gemma 4 E2B IT",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "gemma-4-E4B-it": {
-            id: "gemma-4-E4B-it",
-            name: "Gemma 4 E4B IT",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
     },
     "google-vertex": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-2.0-flash": {
-            id: "gemini-2.0-flash",
-            name: "Gemini 2.0 Flash (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
-        "gemini-2.0-flash-lite": {
-            id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-2.5-flash": {
             id: "gemini-2.5-flash",
-            name: "Gemini 2.5 Flash (Vertex)",
+            name: "Gemini 2.5 Flash",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5006,24 +4869,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5040,7 +4886,7 @@ export const MODELS = {
         },
         "gemini-2.5-pro": {
             id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro (Vertex)",
+            name: "Gemini 2.5 Pro",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5057,7 +4903,7 @@ export const MODELS = {
         },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview (Vertex)",
+            name: "Gemini 3 Flash Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5073,27 +4919,27 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview (Vertex)",
+        "gemini-3.1-flash-lite": {
+            id: "gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview (Vertex)",
+            name: "Gemini 3.1 Pro Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5111,7 +4957,7 @@ export const MODELS = {
         },
         "gemini-3.1-pro-preview-customtools": {
             id: "gemini-3.1-pro-preview-customtools",
-            name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+            name: "Gemini 3.1 Pro Preview Custom Tools",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5127,6 +4973,60 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gemini-flash-latest": {
+            id: "gemini-flash-latest",
+            name: "Gemini Flash Latest",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gemini-flash-lite-latest": {
+            id: "gemini-flash-lite-latest",
+            name: "Gemini Flash-Lite Latest",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
     },
     "groq": {
         "llama-3.1-8b-instant": {
@@ -6457,6 +6357,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -6475,6 +6376,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 1.9,
@@ -6621,6 +6523,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.cn/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -6639,6 +6542,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.cn/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 1.9,
@@ -8012,7 +7916,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8031,7 +7935,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8050,7 +7954,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8660,9 +8564,9 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM-5",
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8670,17 +8574,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.2,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
             maxTokens: 32768,
         },
-        "glm-5.1": {
-            id: "glm-5.1",
-            name: "GLM-5.1",
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8693,8 +8597,8 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 32768,
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
         "kimi-k2.6": {
             id: "kimi-k2.6",
@@ -9247,13 +9151,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.85,
+                input: 0.25,
+                output: 0.8,
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 80000,
         },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
@@ -9408,6 +9312,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4000,
         },
+        "cohere/north-mini-code:free": {
+            id: "cohere/north-mini-code:free",
+            name: "Cohere: North Mini Code (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: 256000,
+            maxTokens: 64000,
+        },
         "deepseek/deepseek-chat": {
             id: "deepseek/deepseek-chat",
             name: "DeepSeek: DeepSeek V3",
@@ -9716,7 +9637,24 @@ export const MODELS = {
                 cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65535,
+        },
+        "google/gemini-3-pro-image": {
+            id: "google/gemini-3-pro-image",
+            name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "google/gemini-3.1-flash-lite": {
             id: "google/gemini-3.1-flash-lite",
@@ -10005,8 +9943,25 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 80000,
+            contextWindow: 262144,
+            maxTokens: 144000,
+        },
+        "liquid/lfm-2.5-1.2b-thinking:free": {
+            id: "liquid/lfm-2.5-1.2b-thinking:free",
+            name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 4096,
         },
         "meta-llama/llama-3.1-70b-instruct": {
             id: "meta-llama/llama-3.1-70b-instruct",
@@ -10210,7 +10165,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 512000,
+            maxTokens: 4096,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10546,7 +10501,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.6,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10579,9 +10534,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.68,
-                output: 3.41,
-                cacheRead: 0.34,
+                input: 0.66,
+                output: 3.5,
+                cacheRead: 0.33,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10596,13 +10551,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.74,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.612,
+                output: 3.069,
+                cacheRead: 0.1296,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "nex-agi/nex-n2-pro:free": {
             id: "nex-agi/nex-n2-pro:free",
@@ -10925,7 +10880,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 32768,
+            maxTokens: 4096,
         },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
@@ -10955,7 +10910,7 @@ export const MODELS = {
             cost: {
                 input: 2.5,
                 output: 10,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11091,11 +11046,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.025,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 4096,
         },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
@@ -11159,11 +11114,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -11250,7 +11205,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -11549,7 +11504,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 32768,
         },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
@@ -11562,7 +11517,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0.037,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -11772,6 +11727,23 @@ export const MODELS = {
             contextWindow: 1048756,
             maxTokens: 262144,
         },
+        "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: 0.2,
+                output: 0.4,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "poolside/laguna-m.1:free": {
             id: "poolside/laguna-m.1:free",
             name: "Poolside: Laguna M.1 (free)",
@@ -11789,6 +11761,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "poolside/laguna-xs.2": {
+            id: "poolside/laguna-xs.2",
+            name: "Poolside: Laguna XS.2",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.2,
+                cacheRead: 0.05,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
             name: "Poolside: Laguna XS.2 (free)",
@@ -11840,6 +11829,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "qwen/qwen-2.5-7b-instruct": {
+            id: "qwen/qwen-2.5-7b-instruct",
+            name: "Qwen: Qwen2.5 7B Instruct",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.04,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
             name: "Qwen: Qwen-Plus",
@@ -12432,8 +12438,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 256000,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -12512,9 +12518,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
-                cacheRead: 0.05,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12699,13 +12705,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.066,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.021,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -12809,23 +12815,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "xiaomi/mimo-v2-flash": {
-            id: "xiaomi/mimo-v2-flash",
-            name: "Xiaomi: MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
             name: "Xiaomi: MiMo-V2.5",
@@ -13039,13 +13028,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.2,
+                output: 4.1,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "~anthropic/claude-fable-latest": {
             id: "~anthropic/claude-fable-latest",
@@ -13158,9 +13147,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.68,
-                output: 3.41,
-                cacheRead: 0.34,
+                input: 0.66,
+                output: 3.5,
+                cacheRead: 0.33,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -15004,13 +14993,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.04,
+                input: 0.15,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 128000,
+            maxTokens: 128000,
         },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
@@ -15163,7 +15152,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 32768,
         },
         "nvidia/nemotron-3-super-120b-a12b": {
             id: "nvidia/nemotron-3-super-120b-a12b",
@@ -15936,8 +15925,8 @@ export const MODELS = {
             cost: {
                 input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0.02,
+                cacheRead: 0.02,
+                cacheWrite: 0,
             },
             contextWindow: 262114,
             maxTokens: 262114,
@@ -16410,9 +16399,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.5,
+                output: 4.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -17022,8 +17011,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0,
@@ -17132,8 +17122,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai-coding-cn",
             baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0,