@psnext/slingcli 2.4.20260507-3 → 2.4.20260509-1

package/node_modules/{@mariozechner → @earendil-works}/pi-ai/dist/models.generated.js

@@ -4705,6 +4705,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "gemini-3.1-flash-lite": {
+            id: "gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 1,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-3.1-flash-lite-preview": {
             id: "gemini-3.1-flash-lite-preview",
             name: "Gemini 3.1 Flash Lite Preview",
@@ -5816,24 +5834,6 @@ export const MODELS = {
         },
     },
     "kimi-coding": {
-        "k2p6": {
-            id: "k2p6",
-            name: "Kimi K2.6",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "kimi-for-coding": {
             id: "kimi-for-coding",
             name: "Kimi For Coding",
@@ -6963,7 +6963,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": "none" },
             input: ["text", "image"],
             cost: {
                 input: 1.25,
@@ -7053,7 +7053,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 1.75,
@@ -7143,7 +7143,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 1.75,
@@ -7179,7 +7179,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 2.5,
@@ -7197,7 +7197,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0.75,
@@ -7215,7 +7215,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0.2,
@@ -7251,7 +7251,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -8111,23 +8111,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "hy3-preview-free": {
-            id: "hy3-preview-free",
-            name: "Hy3 preview Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 64000,
-        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -9281,7 +9264,7 @@ export const MODELS = {
                 cacheRead: 0.024999999999999998,
                 cacheWrite: 0.08333333333333334,
             },
-            contextWindow: 1048576,
+            contextWindow: 1000000,
             maxTokens: 8192,
         },
         "google/gemini-2.0-flash-lite-001": {
@@ -9420,6 +9403,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "google/gemini-3.1-flash-lite": {
+            id: "google/gemini-3.1-flash-lite",
+            name: "Google: Gemini 3.1 Flash Lite",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.024999999999999998,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -9607,18 +9607,18 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
-        "inclusionai/ling-2.6-1t:free": {
-            id: "inclusionai/ling-2.6-1t:free",
-            name: "inclusionAI: Ling-2.6-1T (free)",
+        "inclusionai/ling-2.6-1t": {
+            id: "inclusionai/ling-2.6-1t",
+            name: "inclusionAI: Ling-2.6-1T",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.3,
+                output: 2.5,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9641,6 +9641,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "inclusionai/ring-2.6-1t:free": {
+            id: "inclusionai/ring-2.6-1t:free",
+            name: "inclusionAI: Ring-2.6-1T (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: 65536,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9805,11 +9822,11 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 1.15,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 131072,
+            maxTokens: 196608,
         },
         "minimax/minimax-m2.5:free": {
             id: "minimax/minimax-m2.5:free",
@@ -9837,13 +9854,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
+                input: 0.29900000000000004,
                 output: 1.2,
-                cacheRead: 0.059,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10168,23 +10185,6 @@ export const MODELS = {
             contextWindow: 65536,
             maxTokens: 4096,
         },
-        "mistralai/mixtral-8x7b-instruct": {
-            id: "mistralai/mixtral-8x7b-instruct",
-            name: "Mistral: Mixtral 8x7B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.54,
-                output: 0.54,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 16384,
-        },
         "mistralai/pixtral-large-2411": {
             id: "mistralai/pixtral-large-2411",
             name: "Mistral: Pixtral Large 2411",
@@ -10321,23 +10321,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 163840,
         },
-        "nvidia/llama-3.1-nemotron-70b-instruct": {
-            id: "nvidia/llama-3.1-nemotron-70b-instruct",
-            name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.2,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
             name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -11839,12 +11822,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.08,
-                output: 0.24,
-                cacheRead: 0.04,
+                output: 0.28,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 40960,
-            maxTokens: 40960,
+            maxTokens: 16384,
         },
         "qwen/qwen3-8b": {
             id: "qwen/qwen3-8b",
@@ -12475,18 +12458,18 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "tencent/hy3-preview:free": {
-            id: "tencent/hy3-preview:free",
-            name: "Tencent: Hy3 preview (free)",
+        "tencent/hy3-preview": {
+            id: "tencent/hy3-preview",
+            name: "Tencent: Hy3 preview",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.06599999999999999,
+                output: 0.26,
+                cacheRead: 0.029,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12526,23 +12509,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 32768,
         },
-        "tngtech/deepseek-r1t2-chimera": {
-            id: "tngtech/deepseek-r1t2-chimera",
-            name: "TNG: DeepSeek R1T2 Chimera",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.1,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -12739,9 +12705,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.29,
-                cacheRead: 0.045,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12813,7 +12779,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12943,13 +12909,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.38,
-                output: 1.74,
-                cacheRead: 0,
+                input: 0.39999999999999997,
+                output: 1.75,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.7-flash": {
             id: "z-ai/glm-4.7-flash",
@@ -13173,6 +13139,328 @@ export const MODELS = {
             maxTokens: 128000,
         },
     },
+    "together": {
+        "MiniMaxAI/MiniMax-M2.5": {
+            id: "MiniMaxAI/MiniMax-M2.5",
+            name: "MiniMax-M2.5",
+            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 },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
+            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 },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
+        "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
+            id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
+            name: "Qwen3 235B A22B Instruct 2507 FP8",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.2,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+            id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
+            name: "Qwen3 Coder 480B A35B Instruct",
+            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 },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3-Coder-Next-FP8": {
+            id: "Qwen/Qwen3-Coder-Next-FP8",
+            name: "Qwen3 Coder Next FP8",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3.5-397B-A17B": {
+            id: "Qwen/Qwen3.5-397B-A17B",
+            name: "Qwen3.5 397B A17B",
+            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: 0.6,
+                output: 3.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 130000,
+        },
+        "Qwen/Qwen3.6-Plus": {
+            id: "Qwen/Qwen3.6-Plus",
+            name: "Qwen3.6 Plus",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 500000,
+        },
+        "deepseek-ai/DeepSeek-V3": {
+            id: "deepseek-ai/DeepSeek-V3",
+            name: "DeepSeek V3",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 1.25,
+                output: 1.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "deepseek-ai/DeepSeek-V3-1": {
+            id: "deepseek-ai/DeepSeek-V3-1",
+            name: "DeepSeek V3.1",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 1.7,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "deepseek-ai/DeepSeek-V4-Pro": {
+            id: "deepseek-ai/DeepSeek-V4-Pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
+            input: ["text"],
+            cost: {
+                input: 2.1,
+                output: 4.4,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 384000,
+        },
+        "essentialai/Rnj-1-Instruct": {
+            id: "essentialai/Rnj-1-Instruct",
+            name: "Rnj-1 Instruct",
+            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 },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
+        "google/gemma-4-31B-it": {
+            id: "google/gemma-4-31B-it",
+            name: "Gemma 4 31B Instruct",
+            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: 0.2,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
+        "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+            id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+            name: "Llama 3.3 70B",
+            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 },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.88,
+                output: 0.88,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "moonshotai/Kimi-K2.5": {
+            id: "moonshotai/Kimi-K2.5",
+            name: "Kimi K2.5",
+            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: 0.5,
+                output: 2.8,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/Kimi-K2.6": {
+            id: "moonshotai/Kimi-K2.6",
+            name: "Kimi K2.6",
+            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: 1.2,
+                output: 4.5,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131000,
+        },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null },
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "zai-org/GLM-5.1": {
+            id: "zai-org/GLM-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
+    },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
             id: "alibaba/qwen-3-14b",
@@ -14009,6 +14297,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.1-flash-lite": {
+            id: "google/gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
+            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-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Gemini 3.1 Flash Lite Preview",