@earendil-works/pi-ai 0.79.1 → 0.79.3

package/dist/models.generated.js

@@ -354,7 +354,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 11,
@@ -494,7 +494,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -1386,7 +1386,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -1875,7 +1875,7 @@ export const MODELS = {
             baseUrl: "https://api.anthropic.com",
             compat: { "forceAdaptiveThinking": true },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -2916,30 +2916,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.69,
+                input: 0.35,
+                output: 0.75,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "llama3.1-8b": {
-            id: "llama3.1-8b",
-            name: "Llama 3.1 8B",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.1,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32000,
-            maxTokens: 8000,
+            maxTokens: 40960,
         },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
@@ -2947,7 +2930,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "cerebras",
             baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 2.25,
@@ -2956,7 +2939,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 40000,
+            maxTokens: 40960,
         },
     },
     "cloudflare-ai-gateway": {
@@ -3070,7 +3053,7 @@ export const MODELS = {
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
             compat: { "forceAdaptiveThinking": true },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 10,
@@ -3719,6 +3702,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 256000,
         },
+        "@cf/moonshotai/kimi-k2.7-code": {
+            id: "@cf/moonshotai/kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
+            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: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "@cf/nvidia/nemotron-3-120b-a12b": {
             id: "@cf/nvidia/nemotron-3-120b-a12b",
             name: "Nemotron 3 Super 120B",
@@ -3941,9 +3942,9 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
-        "accounts/fireworks/models/kimi-k2p5": {
-            id: "accounts/fireworks/models/kimi-k2p5",
-            name: "Kimi K2.5",
+        "accounts/fireworks/models/kimi-k2p6": {
+            id: "accounts/fireworks/models/kimi-k2p6",
+            name: "Kimi K2.6",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3951,17 +3952,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262000,
+            maxTokens: 262000,
         },
-        "accounts/fireworks/models/kimi-k2p6": {
-            id: "accounts/fireworks/models/kimi-k2p6",
-            name: "Kimi K2.6",
+        "accounts/fireworks/models/kimi-k2p7-code": {
+            id: "accounts/fireworks/models/kimi-k2p7-code",
+            name: "Kimi K2.7 Code",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3971,15 +3972,15 @@ export const MODELS = {
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.16,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262000,
             maxTokens: 262000,
         },
-        "accounts/fireworks/models/minimax-m2p5": {
-            id: "accounts/fireworks/models/minimax-m2p5",
-            name: "MiniMax-M2.5",
+        "accounts/fireworks/models/minimax-m2p7": {
+            id: "accounts/fireworks/models/minimax-m2p7",
+            name: "MiniMax-M2.7",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3989,15 +3990,15 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.03,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
             maxTokens: 196608,
         },
-        "accounts/fireworks/models/minimax-m2p7": {
-            id: "accounts/fireworks/models/minimax-m2p7",
-            name: "MiniMax-M2.7",
+        "accounts/fireworks/models/minimax-m3": {
+            id: "accounts/fireworks/models/minimax-m3",
+            name: "MiniMax-M3",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4010,12 +4011,12 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
-            maxTokens: 196608,
+            contextWindow: 512000,
+            maxTokens: 512000,
         },
-        "accounts/fireworks/models/qwen3p6-plus": {
-            id: "accounts/fireworks/models/qwen3p6-plus",
-            name: "Qwen 3.6 Plus",
+        "accounts/fireworks/models/qwen3p7-plus": {
+            id: "accounts/fireworks/models/qwen3p7-plus",
+            name: "Qwen 3.7 Plus",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4023,9 +4024,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4085,8 +4086,45 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "accounts/fireworks/routers/kimi-k2p7-code-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
+            name: "Kimi K2.7 Code Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.38,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
     },
     "github-copilot": {
+        "claude-fable-5": {
+            id: "claude-fable-5",
+            name: "Claude Fable 5",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-haiku-4.5": {
             id: "claude-haiku-4.5",
             name: "Claude Haiku 4.5 (latest)",
@@ -5019,354 +5057,167 @@ export const MODELS = {
         },
     },
     "groq": {
-        "deepseek-r1-distill-llama-70b": {
-            id: "deepseek-r1-distill-llama-70b",
-            name: "DeepSeek R1 Distill Llama 70B",
+        "llama-3.1-8b-instant": {
+            id: "llama-3.1-8b-instant",
+            name: "Llama 3.1 8B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.75,
-                output: 0.99,
+                input: 0.05,
+                output: 0.08,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 131072,
         },
-        "gemma2-9b-it": {
-            id: "gemma2-9b-it",
-            name: "Gemma 2 9B",
+        "llama-3.3-70b-versatile": {
+            id: "llama-3.3-70b-versatile",
+            name: "Llama 3.3 70B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2,
-                output: 0.2,
+                input: 0.59,
+                output: 0.79,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
-        "groq/compound": {
-            id: "groq/compound",
-            name: "Compound",
+        "meta-llama/llama-4-scout-17b-16e-instruct": {
+            id: "meta-llama/llama-4-scout-17b-16e-instruct",
+            name: "Llama 4 Scout 17B 16E",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
+            reasoning: false,
+            input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.11,
+                output: 0.34,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
             maxTokens: 8192,
         },
-        "groq/compound-mini": {
-            id: "groq/compound-mini",
-            name: "Compound Mini",
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 65536,
         },
-        "llama-3.1-8b-instant": {
-            id: "llama-3.1-8b-instant",
-            name: "Llama 3.1 8B Instant",
+        "openai/gpt-oss-20b": {
+            id: "openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.05,
-                output: 0.08,
-                cacheRead: 0,
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 65536,
         },
-        "llama-3.3-70b-versatile": {
-            id: "llama-3.3-70b-versatile",
-            name: "Llama 3.3 70B Versatile",
+        "openai/gpt-oss-safeguard-20b": {
+            id: "openai/gpt-oss-safeguard-20b",
+            name: "Safety GPT OSS 20B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.59,
-                output: 0.79,
-                cacheRead: 0,
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.037,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 32768,
+            maxTokens: 65536,
         },
-        "llama3-70b-8192": {
-            id: "llama3-70b-8192",
-            name: "Llama 3 70B",
+        "qwen/qwen3-32b": {
+            id: "qwen/qwen3-32b",
+            name: "Qwen3-32B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "default" },
             input: ["text"],
             cost: {
-                input: 0.59,
-                output: 0.79,
+                input: 0.29,
+                output: 0.59,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 131072,
+            maxTokens: 40960,
         },
-        "llama3-8b-8192": {
-            id: "llama3-8b-8192",
-            name: "Llama 3 8B",
+    },
+    "huggingface": {
+        "MiniMaxAI/MiniMax-M2.1": {
+            id: "MiniMaxAI/MiniMax-M2.1",
+            name: "MiniMax-M2.1",
             api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.05,
-                output: 0.08,
+                input: 0.3,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 8192,
-            maxTokens: 8192,
+            contextWindow: 204800,
+            maxTokens: 131072,
         },
-        "meta-llama/llama-4-maverick-17b-128e-instruct": {
-            id: "meta-llama/llama-4-maverick-17b-128e-instruct",
-            name: "Llama 4 Maverick 17B",
+        "MiniMaxAI/MiniMax-M2.5": {
+            id: "MiniMaxAI/MiniMax-M2.5",
+            name: "MiniMax-M2.5",
             api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text", "image"],
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
             cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 204800,
+            maxTokens: 131072,
         },
-        "meta-llama/llama-4-scout-17b-16e-instruct": {
-            id: "meta-llama/llama-4-scout-17b-16e-instruct",
-            name: "Llama 4 Scout 17B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.11,
-                output: 0.34,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "mistral-saba-24b": {
-            id: "mistral-saba-24b",
-            name: "Mistral Saba 24B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.79,
-                output: 0.79,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
-        "moonshotai/kimi-k2-instruct": {
-            id: "moonshotai/kimi-k2-instruct",
-            name: "Kimi K2 Instruct",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
-        "moonshotai/kimi-k2-instruct-0905": {
-            id: "moonshotai/kimi-k2-instruct-0905",
-            name: "Kimi K2 Instruct 0905",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 16384,
-        },
-        "openai/gpt-oss-120b": {
-            id: "openai/gpt-oss-120b",
-            name: "GPT OSS 120B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "openai/gpt-oss-20b": {
-            id: "openai/gpt-oss-20b",
-            name: "GPT OSS 20B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "openai/gpt-oss-safeguard-20b": {
-            id: "openai/gpt-oss-safeguard-20b",
-            name: "Safety GPT OSS 20B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.037,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "qwen-qwq-32b": {
-            id: "qwen-qwq-32b",
-            name: "Qwen QwQ 32B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.29,
-                output: 0.39,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
-        "qwen/qwen3-32b": {
-            id: "qwen/qwen3-32b",
-            name: "Qwen3 32B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "default" },
-            input: ["text"],
-            cost: {
-                input: 0.29,
-                output: 0.59,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 40960,
-        },
-    },
-    "huggingface": {
-        "MiniMaxAI/MiniMax-M2.1": {
-            id: "MiniMaxAI/MiniMax-M2.1",
-            name: "MiniMax-M2.1",
-            api: "openai-completions",
-            provider: "huggingface",
-            baseUrl: "https://router.huggingface.co/v1",
-            compat: { "supportsDeveloperRole": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMaxAI/MiniMax-M2.5": {
-            id: "MiniMaxAI/MiniMax-M2.5",
-            name: "MiniMax-M2.5",
-            api: "openai-completions",
-            provider: "huggingface",
-            baseUrl: "https://router.huggingface.co/v1",
-            compat: { "supportsDeveloperRole": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMaxAI/MiniMax-M2.7": {
-            id: "MiniMaxAI/MiniMax-M2.7",
-            name: "MiniMax-M2.7",
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
             api: "openai-completions",
             provider: "huggingface",
             baseUrl: "https://router.huggingface.co/v1",
@@ -5726,6 +5577,24 @@ export const MODELS = {
         },
     },
     "kimi-coding": {
+        "k2p7": {
+            id: "k2p7",
+            name: "Kimi K2.7 Code",
+            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",
@@ -6508,6 +6377,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k2.7-code": {
+            id: "kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
     },
     "moonshotai-cn": {
         "kimi-k2-0711-preview": {
@@ -6760,8 +6647,8 @@ export const MODELS = {
             baseUrl: "https://integrate.api.nvidia.com/v1",
             headers: { "NVCF-POLL-SECONDS": "3600" },
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0,
                 output: 0,
@@ -6790,44 +6677,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "nvidia/llama-3.3-nemotron-super-49b-v1": {
-            id: "nvidia/llama-3.3-nemotron-super-49b-v1",
-            name: "Llama 3.3 Nemotron Super 49B v1",
-            api: "openai-completions",
-            provider: "nvidia",
-            baseUrl: "https://integrate.api.nvidia.com/v1",
-            headers: { "NVCF-POLL-SECONDS": "3600" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
-            id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
-            name: "Llama 3.3 Nemotron Super 49B v1.5",
-            api: "openai-completions",
-            provider: "nvidia",
-            baseUrl: "https://integrate.api.nvidia.com/v1",
-            headers: { "NVCF-POLL-SECONDS": "3600" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
             name: "nemotron-3-nano-30b-a3b",
@@ -6923,9 +6772,9 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/gpt-oss-20b": {
-            id: "openai/gpt-oss-20b",
-            name: "GPT OSS 20B",
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT-OSS-120B",
             api: "openai-completions",
             provider: "nvidia",
             baseUrl: "https://integrate.api.nvidia.com/v1",
@@ -6939,18 +6788,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            contextWindow: 128000,
+            maxTokens: 8192,
         },
-        "qwen/qwen3-coder-480b-a35b-instruct": {
-            id: "qwen/qwen3-coder-480b-a35b-instruct",
-            name: "Qwen3 Coder 480B A35B Instruct",
+        "openai/gpt-oss-20b": {
+            id: "openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
             api: "openai-completions",
             provider: "nvidia",
             baseUrl: "https://integrate.api.nvidia.com/v1",
             headers: { "NVCF-POLL-SECONDS": "3600" },
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0,
@@ -6958,8 +6807,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 66536,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-122b-a10b": {
             id: "qwen/qwen3.5-122b-a10b",
@@ -7871,25 +7720,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "claude-fable-5": {
-            id: "claude-fable-5",
-            name: "Claude Fable 5",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            compat: { "forceAdaptiveThinking": true },
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -8063,7 +7893,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.03,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -8088,6 +7918,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 128000,
         },
+        "deepseek-v4-pro": {
+            id: "deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.84,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -8721,42 +8570,42 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 32768,
         },
-        "kimi-k2.5": {
-            id: "kimi-k2.5",
-            name: "Kimi K2.5",
+        "kimi-k2.6": {
+            id: "kimi-k2.6",
+            name: "Kimi K2.6",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "maxTokensField": "max_tokens" },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "kimi-k2.6": {
-            id: "kimi-k2.6",
-            name: "Kimi K2.6",
+        "kimi-k2.7-code": {
+            id: "kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.16,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "mimo-v2.5": {
             id: "mimo-v2.5",
@@ -8794,23 +8643,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 128000,
         },
-        "minimax-m2.5": {
-            id: "minimax-m2.5",
-            name: "MiniMax M2.5",
-            api: "anthropic-messages",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 65536,
-        },
         "minimax-m2.7": {
             id: "minimax-m2.7",
             name: "MiniMax M2.7",
@@ -8831,16 +8663,16 @@ export const MODELS = {
         },
         "minimax-m3": {
             id: "minimax-m3",
-            name: "MiniMax M3",
+            name: "MiniMax M3 (3x usage)",
             api: "anthropic-messages",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 512000,
@@ -8994,8 +8826,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
-                output: 3.1999999999999997,
+                input: 0.8,
+                output: 3.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9028,7 +8860,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
+                input: 0.8,
                 output: 4,
                 cacheRead: 0.08,
                 cacheWrite: 1,
@@ -9064,7 +8896,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -9408,8 +9240,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.1,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9459,8 +9291,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.20020000000000002,
-                output: 0.8000999999999999,
+                input: 0.2002,
+                output: 0.8001,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9476,7 +9308,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.77,
                 cacheRead: 0.135,
                 cacheWrite: 0,
@@ -9494,7 +9326,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.21,
-                output: 0.7899999999999999,
+                output: 0.79,
                 cacheRead: 0.13,
                 cacheWrite: 0,
             },
@@ -9528,7 +9360,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.5,
-                output: 2.1500000000000004,
+                output: 2.15,
                 cacheRead: 0.35,
                 cacheWrite: 0,
             },
@@ -9597,13 +9429,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.0983,
-                output: 0.1966,
-                cacheRead: 0.019700000000000002,
+                input: 0.098,
+                output: 0.196,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -9653,7 +9485,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 2.5,
                 cacheRead: 0.03,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -9667,10 +9499,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.1,
+                output: 0.4,
                 cacheRead: 0.01,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -9684,10 +9516,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.1,
+                output: 0.4,
                 cacheRead: 0.01,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -9754,8 +9586,8 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0.08333333333333334,
+                cacheRead: 0.05,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9771,8 +9603,8 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 1.5,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
+                cacheRead: 0.025,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9788,8 +9620,8 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 1.5,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
+                cacheRead: 0.025,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9805,7 +9637,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -9822,7 +9654,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048756,
@@ -9840,7 +9672,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 9,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9854,7 +9686,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.049999999999999996,
+                input: 0.05,
                 output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9923,12 +9755,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.36,
+                output: 0.35,
                 cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 8192,
+            maxTokens: 262144,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9956,9 +9788,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.09999999999999999,
-                cacheRead: 0.049999999999999996,
+                input: 0.05,
+                output: 0.1,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -9976,7 +9808,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 0.75,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -10059,8 +9891,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10093,7 +9925,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.32,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10144,7 +9976,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10161,7 +9993,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10213,8 +10045,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.15,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                output: 0.9,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -10229,9 +10061,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.27,
-                output: 1.08,
-                cacheRead: 0.054,
+                input: 0.25,
+                output: 1,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -10264,7 +10096,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
@@ -10280,7 +10112,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10297,8 +10129,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.19999999999999998,
+                input: 0.2,
+                output: 0.2,
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
@@ -10314,8 +10146,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.1,
+                output: 0.1,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -10350,7 +10182,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -10367,7 +10199,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -10384,7 +10216,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 1.5,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10399,7 +10231,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10433,7 +10265,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10467,7 +10299,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.6,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -10502,7 +10334,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.075,
-                output: 0.19999999999999998,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10520,7 +10352,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 65536,
@@ -10535,7 +10367,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -10552,7 +10384,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5700000000000001,
+                input: 0.57,
                 output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10621,27 +10453,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6799999999999999,
+                input: 0.68,
                 output: 3.41,
-                cacheRead: 0.33999999999999997,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 262142,
         },
-        "moonshotai/kimi-k2.6:free": {
-            id: "moonshotai/kimi-k2.6:free",
-            name: "MoonshotAI: Kimi K2.6 (free)",
+        "moonshotai/kimi-k2.7-code": {
+            id: "moonshotai/kimi-k2.7-code",
+            name: "MoonshotAI: Kimi K2.7 Code",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10673,8 +10504,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10690,8 +10521,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
+                input: 0.05,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10742,7 +10573,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.09,
-                output: 0.44999999999999996,
+                output: 0.45,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10817,23 +10648,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
-        "nvidia/nemotron-nano-9b-v2": {
-            id: "nvidia/nemotron-nano-9b-v2",
-            name: "NVIDIA: Nemotron Nano 9B V2",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.04,
-                output: 0.16,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
         "nvidia/nemotron-nano-9b-v2:free": {
             id: "nvidia/nemotron-nano-9b-v2:free",
             name: "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -10979,9 +10793,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -10996,9 +10810,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -11151,7 +10965,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11166,8 +10980,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.39999999999999997,
+                input: 0.05,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -11270,7 +11084,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11430,7 +11244,7 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.25,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -11875,7 +11689,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11893,7 +11707,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.36,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11911,7 +11725,7 @@ export const MODELS = {
             cost: {
                 input: 0.26,
                 output: 0.78,
-                cacheRead: 0.052000000000000005,
+                cacheRead: 0.052,
                 cacheWrite: 0.325,
             },
             contextWindow: 1000000,
@@ -11960,7 +11774,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11977,8 +11791,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.45499999999999996,
-                output: 1.8199999999999998,
+                input: 0.455,
+                output: 1.82,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11995,7 +11809,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.09,
-                output: 0.09999999999999999,
+                output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12011,9 +11825,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12063,7 +11877,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.08,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.08,
                 cacheWrite: 0,
             },
@@ -12096,9 +11910,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.39999999999999997,
-                cacheRead: 0.049999999999999996,
+                input: 0.05,
+                output: 0.4,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12114,7 +11928,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.22,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12165,7 +11979,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.11,
-                output: 0.7999999999999999,
+                output: 0.8,
                 cacheRead: 0.07,
                 cacheWrite: 0,
             },
@@ -12300,7 +12114,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.88,
                 cacheRead: 0.11,
                 cacheWrite: 0,
@@ -12368,8 +12182,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.10400000000000001,
-                output: 0.41600000000000004,
+                input: 0.104,
+                output: 0.416,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12455,7 +12269,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12487,7 +12301,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -12539,7 +12353,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.3,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0,
                 cacheWrite: 0.375,
             },
@@ -12555,13 +12369,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.28900000000000003,
-                output: 2.4,
+                input: 0.2885,
+                output: 3.17,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -12572,13 +12386,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
+                input: 0.15,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262140,
+            maxTokens: 262144,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12657,10 +12471,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.08,
-                cacheWrite: 0.5,
+                input: 0.32,
+                output: 1.28,
+                cacheRead: 0.064,
+                cacheWrite: 0.4,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12674,8 +12488,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.1,
+                output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12742,7 +12556,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.15,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -12761,7 +12575,7 @@ export const MODELS = {
             cost: {
                 input: 0.063,
                 output: 0.21,
-                cacheRead: 0.020999999999999998,
+                cacheRead: 0.021,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12776,7 +12590,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.16999999999999998,
+                input: 0.17,
                 output: 0.43,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -12793,8 +12607,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12829,7 +12643,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -12846,7 +12660,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -12863,7 +12677,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 2,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -12878,7 +12692,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -12920,23 +12734,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "z-ai/glm-4-32b": {
-            id: "z-ai/glm-4-32b",
-            name: "Z.ai: GLM 4 32B ",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "z-ai/glm-4.5": {
             id: "z-ai/glm-4.5",
             name: "Z.ai: GLM 4.5",
@@ -12971,23 +12768,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131070,
         },
-        "z-ai/glm-4.5-air:free": {
-            id: "z-ai/glm-4.5-air:free",
-            name: "Z.ai: GLM 4.5 Air (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: 96000,
-        },
         "z-ai/glm-4.5v": {
             id: "z-ai/glm-4.5v",
             name: "Z.ai: GLM 4.5V",
@@ -12998,7 +12778,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },
@@ -13032,12 +12812,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                output: 0.9,
+                cacheRead: 0.055,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 24000,
+            maxTokens: 32768,
         },
         "z-ai/glm-4.7": {
             id: "z-ai/glm-4.7",
@@ -13048,7 +12828,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 1.75,
                 cacheRead: 0.08,
                 cacheWrite: 0,
@@ -13066,7 +12846,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -13104,7 +12884,7 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "z-ai/glm-5.1": {
@@ -13124,23 +12904,6 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 4096,
         },
-        "z-ai/glm-5v-turbo": {
-            id: "z-ai/glm-5v-turbo",
-            name: "Z.ai: GLM 5V Turbo",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.2,
-                output: 4,
-                cacheRead: 0.24,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
         "~anthropic/claude-fable-latest": {
             id: "~anthropic/claude-fable-latest",
             name: "Anthropic: Claude Fable Latest",
@@ -13169,7 +12932,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -13221,7 +12984,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 9,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -13237,7 +13000,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -13252,9 +13015,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6799999999999999,
+                input: 0.68,
                 output: 3.41,
-                cacheRead: 0.33999999999999997,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13296,25 +13059,6 @@ export const MODELS = {
         },
     },
     "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, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "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",
@@ -13334,28 +13078,28 @@ export const MODELS = {
             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",
+        "MiniMaxAI/MiniMax-M3": {
+            id: "MiniMaxAI/MiniMax-M3",
+            name: "MiniMax-M3",
             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"],
+            input: ["text", "image"],
             cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 524288,
+            maxTokens: 250000,
         },
-        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
-            id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
-            name: "Qwen3 Coder 480B A35B Instruct",
+        "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+            id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
+            name: "Qwen 2.5 7B Instruct Turbo",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13363,27 +13107,26 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 2,
-                output: 2,
+                input: 0.3,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 32768,
+            maxTokens: 32768,
         },
-        "Qwen/Qwen3-Coder-Next-FP8": {
-            id: "Qwen/Qwen3-Coder-Next-FP8",
-            name: "Qwen3 Coder Next FP8",
+        "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 },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 1.2,
+                input: 0.2,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13409,28 +13152,28 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 130000,
         },
-        "Qwen/Qwen3.6-Plus": {
-            id: "Qwen/Qwen3.6-Plus",
-            name: "Qwen3.6 Plus",
+        "Qwen/Qwen3.5-9B": {
+            id: "Qwen/Qwen3.5-9B",
+            name: "Qwen3.5 9B",
             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"],
+            input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
+                input: 0.17,
+                output: 0.25,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 500000,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
-        "Qwen/Qwen3.7-Max": {
-            id: "Qwen/Qwen3.7-Max",
-            name: "Qwen3.7 Max",
+        "Qwen/Qwen3.6-Plus": {
+            id: "Qwen/Qwen3.6-Plus",
+            name: "Qwen3.6 Plus",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13439,51 +13182,31 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
+                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",
+        "Qwen/Qwen3.7-Max": {
+            id: "Qwen/Qwen3.7-Max",
+            name: "Qwen3.7 Max",
             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 },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.7,
+                input: 2.5,
+                output: 7.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 500000,
         },
         "deepseek-ai/DeepSeek-V4-Pro": {
             id: "deepseek-ai/DeepSeek-V4-Pro",
@@ -13496,8 +13219,8 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
             input: ["text"],
             cost: {
-                input: 2.1,
-                output: 4.4,
+                input: 1.74,
+                output: 3.48,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -13533,8 +13256,8 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.2,
-                output: 0.5,
+                input: 0.39,
+                output: 0.97,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13559,25 +13282,6 @@ export const MODELS = {
             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",
@@ -13635,6 +13339,44 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "openai/gpt-oss-20b": {
+            id: "openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
+            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: 0.05,
+                output: 0.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "zai-org/GLM-5": {
+            id: "zai-org/GLM-5",
+            name: "GLM-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"],
+            cost: {
+                input: 1,
+                output: 3.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
         "zai-org/GLM-5.1": {
             id: "zai-org/GLM-5.1",
             name: "GLM-5.1",
@@ -13750,7 +13492,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -13820,7 +13562,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -13920,7 +13662,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -13937,8 +13679,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.1,
+                output: 0.4,
                 cacheRead: 0.001,
                 cacheWrite: 0.125,
             },
@@ -13954,7 +13696,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2.4,
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
@@ -13972,7 +13714,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 3.5999999999999996,
+                output: 3.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13990,7 +13732,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 0.625,
             },
             contextWindow: 1000000,
@@ -14022,8 +13764,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
+                input: 0.4,
+                output: 1.6,
                 cacheRead: 0.08,
                 cacheWrite: 0.5,
             },
@@ -14056,7 +13798,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
+                input: 0.8,
                 output: 4,
                 cacheRead: 0.08,
                 cacheWrite: 1,
@@ -14064,25 +13806,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-fable-5": {
-            id: "anthropic/claude-fable-5",
-            name: "Claude Fable 5",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            compat: { "forceAdaptiveThinking": true },
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Claude Haiku 4.5",
@@ -14094,7 +13817,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -14287,7 +14010,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.25,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14305,7 +14028,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -14490,8 +14213,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.1,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -14526,7 +14249,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14543,7 +14266,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14594,7 +14317,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14644,7 +14367,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.14,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14662,7 +14385,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 0.75,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -14814,7 +14537,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.24,
-                output: 0.9700000000000001,
+                output: 0.97,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14830,7 +14553,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.16999999999999998,
+                input: 0.17,
                 output: 0.66,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14984,7 +14707,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -15000,7 +14723,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15017,7 +14740,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15034,7 +14757,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15051,8 +14774,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.1,
+                output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -15085,7 +14808,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15136,7 +14859,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15187,7 +14910,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5700000000000001,
+                input: 0.57,
                 output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15212,40 +14935,6 @@ export const MODELS = {
             contextWindow: 262114,
             maxTokens: 262114,
         },
-        "moonshotai/kimi-k2-thinking-turbo": {
-            id: "moonshotai/kimi-k2-thinking-turbo",
-            name: "Kimi K2 Thinking Turbo",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.15,
-                output: 8,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 262114,
-            maxTokens: 262114,
-        },
-        "moonshotai/kimi-k2-turbo": {
-            id: "moonshotai/kimi-k2-turbo",
-            name: "Kimi K2 Turbo",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.15,
-                output: 8,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 16384,
-        },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -15257,7 +14946,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 262114,
@@ -15280,6 +14969,23 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "moonshotai/kimi-k2.7-code": {
+            id: "moonshotai/kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32768,
+        },
         "nvidia/nemotron-3-super-120b-a12b": {
             id: "nvidia/nemotron-3-super-120b-a12b",
             name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -15323,7 +15029,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15341,7 +15047,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.22999999999999998,
+                output: 0.23,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -15391,9 +15097,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -15408,9 +15114,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -15512,7 +15218,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -15527,8 +15233,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.39999999999999997,
+                input: 0.05,
+                output: 0.4,
                 cacheRead: 0.005,
                 cacheWrite: 0,
             },
@@ -15597,7 +15303,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -15791,7 +15497,7 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.25,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -15879,8 +15585,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
+                input: 0.05,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -16066,7 +15772,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.15,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -16083,9 +15789,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.5,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16100,9 +15806,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.5,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16119,7 +15825,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16136,7 +15842,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16153,7 +15859,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16170,7 +15876,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16187,7 +15893,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16204,7 +15910,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16221,7 +15927,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16238,7 +15944,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 2,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -16253,7 +15959,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -16272,7 +15978,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16338,7 +16044,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.1,
                 cacheRead: 0.03,
                 cacheWrite: 0,
@@ -16356,7 +16062,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },
@@ -16390,8 +16096,8 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                output: 0.9,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -16441,7 +16147,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.07,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -16458,7 +16164,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -16475,8 +16181,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 1,
-                output: 3.1999999999999997,
-                cacheRead: 0.19999999999999998,
+                output: 3.2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 202800,
@@ -16746,6 +16452,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "mimo-v2.5-pro-ultraspeed": {
+            id: "mimo-v2.5-pro-ultraspeed",
+            name: "MiMo-V2.5-Pro-UltraSpeed",
+            api: "openai-completions",
+            provider: "xiaomi",
+            baseUrl: "https://api.xiaomimimo.com/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "xiaomi-token-plan-ams": {
         "mimo-v2-omni": {
@@ -16820,6 +16544,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "mimo-v2.5-pro-ultraspeed": {
+            id: "mimo-v2.5-pro-ultraspeed",
+            name: "MiMo-V2.5-Pro-UltraSpeed",
+            api: "openai-completions",
+            provider: "xiaomi-token-plan-ams",
+            baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "xiaomi-token-plan-cn": {
         "mimo-v2-omni": {
@@ -16894,6 +16636,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "mimo-v2.5-pro-ultraspeed": {
+            id: "mimo-v2.5-pro-ultraspeed",
+            name: "MiMo-V2.5-Pro-UltraSpeed",
+            api: "openai-completions",
+            provider: "xiaomi-token-plan-cn",
+            baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "xiaomi-token-plan-sgp": {
         "mimo-v2-omni": {
@@ -16968,6 +16728,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "mimo-v2.5-pro-ultraspeed": {
+            id: "mimo-v2.5-pro-ultraspeed",
+            name: "MiMo-V2.5-Pro-UltraSpeed",
+            api: "openai-completions",
+            provider: "xiaomi-token-plan-sgp",
+            baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "zai": {
         "glm-4.5-air": {