@psnext/slingcli 2.5.20260607-2 → 2.5.20260615-1

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

@@ -8,7 +8,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 0.33,
@@ -347,6 +347,24 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 81920,
         },
+        "eu.anthropic.claude-fable-5": {
+            id: "eu.anthropic.claude-fable-5",
+            name: "Claude Fable 5 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 11,
+                output: 55,
+                cacheRead: 1.1,
+                cacheWrite: 13.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (EU)",
@@ -469,6 +487,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "global.anthropic.claude-fable-5": {
+            id: "global.anthropic.claude-fable-5",
+            name: "Claude Fable 5 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (Global)",
@@ -1128,7 +1164,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.15,
@@ -1145,7 +1181,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.15,
@@ -1162,7 +1198,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.07,
@@ -1179,7 +1215,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.07,
@@ -1343,6 +1379,24 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "us.anthropic.claude-fable-5": {
+            id: "us.anthropic.claude-fable-5",
+            name: "Claude Fable 5 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (US)",
@@ -1813,6 +1867,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
+        "claude-fable-5": {
+            id: "claude-fable-5",
+            name: "Claude Fable 5",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "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 (latest)",
@@ -2370,7 +2443,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 272000,
+            maxTokens: 128000,
         },
         "gpt-5.1": {
             id: "gpt-5.1",
@@ -2603,7 +2676,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 1050000,
             maxTokens: 128000,
         },
         "gpt-5.4-mini": {
@@ -2675,7 +2748,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 1050000,
             maxTokens: 128000,
         },
         "gpt-5.5-pro": {
@@ -2843,30 +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",
@@ -2874,7 +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,
@@ -2883,7 +2939,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 40000,
+            maxTokens: 40960,
         },
     },
     "cloudflare-ai-gateway": {
@@ -2989,6 +3045,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
+        "claude-fable-5": {
+            id: "claude-fable-5",
+            name: "Claude Fable 5",
+            api: "anthropic-messages",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "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 (latest)",
@@ -3627,6 +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",
@@ -3849,9 +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",
@@ -3859,17 +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",
@@ -3879,15 +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",
@@ -3897,15 +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",
@@ -3918,12 +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",
@@ -3931,9 +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,
@@ -3993,8 +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)",
@@ -4698,6 +4828,42 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "gemma-4-E2B-it": {
+            id: "gemma-4-E2B-it",
+            name: "Gemma 4 E2B IT",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "gemma-4-E4B-it": {
+            id: "gemma-4-E4B-it",
+            name: "Gemma 4 E4B IT",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
     },
     "google-vertex": {
         "gemini-1.5-flash": {
@@ -4927,167 +5093,48 @@ 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"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "groq/compound-mini": {
-            id: "groq/compound-mini",
-            name: "Compound Mini",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "llama-3.1-8b-instant": {
-            id: "llama-3.1-8b-instant",
-            name: "Llama 3.1 8B Instant",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.05,
-                output: 0.08,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "llama-3.3-70b-versatile": {
-            id: "llama-3.3-70b-versatile",
-            name: "Llama 3.3 70B Versatile",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.59,
-                output: 0.79,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "llama3-70b-8192": {
-            id: "llama3-70b-8192",
-            name: "Llama 3 70B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.59,
-                output: 0.79,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
-        "llama3-8b-8192": {
-            id: "llama3-8b-8192",
-            name: "Llama 3 8B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.05,
-                output: 0.08,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
-        "meta-llama/llama-4-maverick-17b-128e-instruct": {
-            id: "meta-llama/llama-4-maverick-17b-128e-instruct",
-            name: "Llama 4 Maverick 17B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "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"],
+            reasoning: false,
+            input: ["text", "image"],
             cost: {
                 input: 0.11,
                 output: 0.34,
@@ -5097,57 +5144,6 @@ export const MODELS = {
             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",
@@ -5199,26 +5195,9 @@ export const MODELS = {
             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",
+            name: "Qwen3-32B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -5634,6 +5613,24 @@ 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",
@@ -6296,7 +6293,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6314,7 +6311,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6332,7 +6329,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6350,7 +6347,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6368,7 +6365,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6386,7 +6383,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6404,7 +6401,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai",
             baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6416,6 +6413,24 @@ 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": {
@@ -6424,7 +6439,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6442,7 +6457,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6460,7 +6475,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6478,7 +6493,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6496,7 +6511,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -6514,7 +6529,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6532,7 +6547,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "moonshotai-cn",
             baseUrl: "https://api.moonshot.cn/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6668,8 +6683,8 @@ 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,
@@ -6698,9 +6713,9 @@ 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",
+        "nvidia/nemotron-3-nano-30b-a3b": {
+            id: "nvidia/nemotron-3-nano-30b-a3b",
+            name: "nemotron-3-nano-30b-a3b",
             api: "openai-completions",
             provider: "nvidia",
             baseUrl: "https://integrate.api.nvidia.com/v1",
@@ -6717,28 +6732,28 @@ export const MODELS = {
             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",
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
+            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+            name: "Nemotron 3 Nano Omni",
             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"],
+            input: ["text", "image"],
             cost: {
                 input: 0,
                 output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 256000,
+            maxTokens: 65536,
         },
-        "nvidia/nemotron-3-nano-30b-a3b": {
-            id: "nvidia/nemotron-3-nano-30b-a3b",
-            name: "nemotron-3-nano-30b-a3b",
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "Nemotron 3 Super",
             api: "openai-completions",
             provider: "nvidia",
             baseUrl: "https://integrate.api.nvidia.com/v1",
@@ -6747,36 +6762,36 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.2,
+                output: 0.8,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
-            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
-            name: "Nemotron 3 Nano Omni",
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
             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", "image"],
+            input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "nvidia/nemotron-3-super-120b-a12b": {
-            id: "nvidia/nemotron-3-super-120b-a12b",
-            name: "Nemotron 3 Super",
+        "nvidia/nvidia-nemotron-nano-9b-v2": {
+            id: "nvidia/nvidia-nemotron-nano-9b-v2",
+            name: "nvidia-nemotron-nano-9b-v2",
             api: "openai-completions",
             provider: "nvidia",
             baseUrl: "https://integrate.api.nvidia.com/v1",
@@ -6785,17 +6800,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.2,
-                output: 0.8,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
-        "nvidia/nvidia-nemotron-nano-9b-v2": {
-            id: "nvidia/nvidia-nemotron-nano-9b-v2",
-            name: "nvidia-nemotron-nano-9b-v2",
+        "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",
@@ -6809,8 +6824,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 128000,
+            maxTokens: 8192,
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
@@ -6831,25 +6846,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
-        "qwen/qwen3-coder-480b-a35b-instruct": {
-            id: "qwen/qwen3-coder-480b-a35b-instruct",
-            name: "Qwen3 Coder 480B A35B Instruct",
-            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,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 66536,
-        },
         "qwen/qwen3.5-122b-a10b": {
             id: "qwen/qwen3.5-122b-a10b",
             name: "Qwen3.5 122B-A10B",
@@ -7204,7 +7200,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 272000,
+            maxTokens: 128000,
         },
         "gpt-5.1": {
             id: "gpt-5.1",
@@ -7748,6 +7744,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -7925,14 +7922,14 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.03,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7944,7 +7941,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -7957,6 +7954,25 @@ 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", "supportsLongCacheRetention": false, "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",
@@ -8017,6 +8033,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8034,6 +8051,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8339,7 +8357,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "supportsReasoningEffort": false },
+            compat: { "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
             reasoning: true,
             thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
@@ -8358,6 +8376,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8375,7 +8394,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8393,6 +8412,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8410,6 +8430,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8427,6 +8448,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8438,29 +8460,31 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "minimax-m3-free": {
-            id: "minimax-m3-free",
-            name: "MiniMax M3 Free",
-            api: "anthropic-messages",
+        "nemotron-3-ultra-free": {
+            id: "nemotron-3-ultra-free",
+            name: "Nemotron 3 Ultra Free",
+            api: "openai-completions",
             provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0,
                 output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 32000,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "nemotron-3-ultra-free": {
-            id: "nemotron-3-ultra-free",
-            name: "Nemotron 3 Ultra Free",
+        "north-mini-code-free": {
+            id: "north-mini-code-free",
+            name: "North Mini Code Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8469,8 +8493,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 256000,
+            maxTokens: 64000,
         },
         "qwen3.5-plus": {
             id: "qwen3.5-plus",
@@ -8514,7 +8538,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8533,7 +8557,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8552,6 +8576,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8569,6 +8594,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8580,41 +8606,42 @@ 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: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             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 },
+            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",
@@ -8622,6 +8649,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8639,6 +8667,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8650,29 +8679,13 @@ 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",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8686,16 +8699,16 @@ 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: 0.6,
-                output: 2.4,
-                cacheRead: 0.12,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 512000,
@@ -8707,7 +8720,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "qwen" },
+            compat: { "thinkingFormat": "qwen", "maxTokensField": "max_tokens" },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8849,8 +8862,8 @@ 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,
             },
@@ -8883,7 +8896,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
+                input: 0.8,
                 output: 4,
                 cacheRead: 0.08,
                 cacheWrite: 1,
@@ -8891,6 +8904,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
+        "anthropic/claude-fable-5": {
+            id: "anthropic/claude-fable-5",
+            name: "Anthropic: Claude Fable 5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            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: "Anthropic: Claude Haiku 4.5",
@@ -8902,7 +8932,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -9246,8 +9276,8 @@ 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,
             },
@@ -9297,8 +9327,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.20020000000000002,
-                output: 0.8000999999999999,
+                input: 0.2002,
+                output: 0.8001,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9314,7 +9344,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.77,
                 cacheRead: 0.135,
                 cacheWrite: 0,
@@ -9332,7 +9362,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.21,
-                output: 0.7899999999999999,
+                output: 0.79,
                 cacheRead: 0.13,
                 cacheWrite: 0,
             },
@@ -9366,7 +9396,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.5,
-                output: 2.1500000000000004,
+                output: 2.15,
                 cacheRead: 0.35,
                 cacheWrite: 0,
             },
@@ -9435,13 +9465,13 @@ 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: 0.09,
+                output: 0.18,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -9491,7 +9521,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 2.5,
                 cacheRead: 0.03,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -9505,10 +9535,10 @@ 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,
@@ -9522,10 +9552,10 @@ 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,
@@ -9592,8 +9622,8 @@ 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,
@@ -9609,8 +9639,8 @@ 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,
@@ -9626,8 +9656,8 @@ 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,
@@ -9643,7 +9673,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -9660,7 +9690,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048756,
@@ -9678,7 +9708,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 9,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9692,8 +9722,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
-                output: 0.13,
+                input: 0.05,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9761,12 +9791,12 @@ 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",
@@ -9794,9 +9824,9 @@ 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,
@@ -9814,7 +9844,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 0.75,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -9897,8 +9927,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9931,7 +9961,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.32,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9982,7 +10012,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9999,7 +10029,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10051,8 +10081,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.15,
-                output: 1.15,
-                cacheRead: 0,
+                output: 0.9,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -10067,13 +10097,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.27899999999999997,
-                output: 1.2,
-                cacheRead: 0,
+                input: 0.25,
+                output: 1,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 196608,
+            maxTokens: 131072,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -10102,7 +10132,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
@@ -10118,7 +10148,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10135,8 +10165,8 @@ 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,
             },
@@ -10152,8 +10182,8 @@ 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,
             },
@@ -10188,7 +10218,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -10205,7 +10235,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -10222,7 +10252,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 1.5,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10237,7 +10267,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10271,7 +10301,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -10305,7 +10335,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.6,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -10340,7 +10370,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.075,
-                output: 0.19999999999999998,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10358,7 +10388,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 65536,
@@ -10373,7 +10403,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -10390,7 +10420,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5700000000000001,
+                input: 0.57,
                 output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10459,48 +10489,47 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.68,
+                output: 3.41,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 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: 0.75,
+                output: 3.5,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
-        "nex-agi/deepseek-v3.1-nex-n1": {
-            id: "nex-agi/deepseek-v3.1-nex-n1",
-            name: "Nex AGI: DeepSeek V3.1 Nex N1",
+        "nex-agi/nex-n2-pro:free": {
+            id: "nex-agi/nex-n2-pro:free",
+            name: "Nex AGI: Nex-N2-Pro (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 0.135,
-                output: 0.5,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 163840,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -10511,8 +10540,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10528,8 +10557,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
+                input: 0.05,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10580,7 +10609,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.09,
-                output: 0.44999999999999996,
+                output: 0.45,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10655,23 +10684,6 @@ 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)",
@@ -10817,9 +10829,9 @@ 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,
@@ -10834,9 +10846,9 @@ 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,
@@ -10989,7 +11001,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11004,8 +11016,8 @@ 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,
             },
@@ -11108,7 +11120,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11268,7 +11280,7 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.25,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -11713,7 +11725,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11731,7 +11743,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.36,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11749,7 +11761,7 @@ export const MODELS = {
             cost: {
                 input: 0.26,
                 output: 0.78,
-                cacheRead: 0.052000000000000005,
+                cacheRead: 0.052,
                 cacheWrite: 0.325,
             },
             contextWindow: 1000000,
@@ -11798,7 +11810,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11815,8 +11827,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.45499999999999996,
-                output: 1.8199999999999998,
+                input: 0.455,
+                output: 1.82,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11832,8 +11844,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
-                output: 0.09999999999999999,
+                input: 0.09,
+                output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11849,9 +11861,9 @@ 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,
@@ -11866,8 +11878,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11901,7 +11913,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.08,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.08,
                 cacheWrite: 0,
             },
@@ -11934,9 +11946,9 @@ 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,
@@ -11952,7 +11964,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.22,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12003,7 +12015,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.11,
-                output: 0.7999999999999999,
+                output: 0.8,
                 cacheRead: 0.07,
                 cacheWrite: 0,
             },
@@ -12138,7 +12150,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.88,
                 cacheRead: 0.11,
                 cacheWrite: 0,
@@ -12206,8 +12218,8 @@ 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,
             },
@@ -12293,7 +12305,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12325,13 +12337,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
+                input: 0.1,
                 output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -12377,7 +12389,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.3,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0,
                 cacheWrite: 0.375,
             },
@@ -12393,13 +12405,13 @@ 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",
@@ -12410,13 +12422,13 @@ 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",
@@ -12495,10 +12507,10 @@ 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,
@@ -12512,8 +12524,8 @@ 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,
             },
@@ -12580,7 +12592,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.15,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -12599,7 +12611,7 @@ export const MODELS = {
             cost: {
                 input: 0.063,
                 output: 0.21,
-                cacheRead: 0.020999999999999998,
+                cacheRead: 0.021,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12614,7 +12626,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.16999999999999998,
+                input: 0.17,
                 output: 0.43,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -12631,8 +12643,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.4,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12667,7 +12679,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -12684,7 +12696,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -12701,7 +12713,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 2,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -12716,7 +12728,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -12758,23 +12770,6 @@ 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",
@@ -12809,23 +12804,6 @@ 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",
@@ -12836,7 +12814,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },
@@ -12870,12 +12848,12 @@ 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",
@@ -12886,7 +12864,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 1.75,
                 cacheRead: 0.08,
                 cacheWrite: 0,
@@ -12904,7 +12882,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -12942,7 +12920,7 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "z-ai/glm-5.1": {
@@ -12962,22 +12940,22 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 4096,
         },
-        "z-ai/glm-5v-turbo": {
-            id: "z-ai/glm-5v-turbo",
-            name: "Z.ai: GLM 5V Turbo",
+        "~anthropic/claude-fable-latest": {
+            id: "~anthropic/claude-fable-latest",
+            name: "Anthropic: Claude Fable Latest",
             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,
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
             },
-            contextWindow: 202752,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
         "~anthropic/claude-haiku-latest": {
             id: "~anthropic/claude-haiku-latest",
@@ -12990,7 +12968,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -13042,7 +13020,7 @@ export const MODELS = {
                 input: 1.5,
                 output: 9,
                 cacheRead: 0.15,
-                cacheWrite: 0.08333333333333334,
+                cacheWrite: 0.083333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -13058,7 +13036,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -13073,13 +13051,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.68,
+                output: 3.41,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -13117,9 +13095,9 @@ export const MODELS = {
         },
     },
     "together": {
-        "MiniMaxAI/MiniMax-M2.5": {
-            id: "MiniMaxAI/MiniMax-M2.5",
-            name: "MiniMax-M2.5",
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13133,50 +13111,49 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
+            contextWindow: 202752,
             maxTokens: 131072,
         },
-        "MiniMaxAI/MiniMax-M2.7": {
-            id: "MiniMaxAI/MiniMax-M2.7",
-            name: "MiniMax-M2.7",
+        "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 },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
-            input: ["text"],
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
             cost: {
                 input: 0.3,
                 output: 1.2,
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 131072,
+            contextWindow: 524288,
+            maxTokens: 250000,
         },
-        "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
-            id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
-            name: "Qwen3 235B A22B Instruct 2507 FP8",
+        "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",
-            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: 0.2,
-                output: 0.6,
+                input: 0.3,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 32768,
+            maxTokens: 32768,
         },
-        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
-            id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
-            name: "Qwen3 Coder 480B A35B Instruct",
+        "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",
@@ -13184,36 +13161,36 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 2,
-                output: 2,
+                input: 0.2,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "Qwen/Qwen3-Coder-Next-FP8": {
-            id: "Qwen/Qwen3-Coder-Next-FP8",
-            name: "Qwen3 Coder Next FP8",
+        "Qwen/Qwen3.5-397B-A17B": {
+            id: "Qwen/Qwen3.5-397B-A17B",
+            name: "Qwen3.5 397B A17B",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 1.2,
+                input: 0.6,
+                output: 3.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 130000,
         },
-        "Qwen/Qwen3.5-397B-A17B": {
-            id: "Qwen/Qwen3.5-397B-A17B",
-            name: "Qwen3.5 397B A17B",
+        "Qwen/Qwen3.5-9B": {
+            id: "Qwen/Qwen3.5-9B",
+            name: "Qwen3.5 9B",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13222,13 +13199,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3.6,
+                input: 0.17,
+                output: 0.25,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 130000,
+            maxTokens: 65536,
         },
         "Qwen/Qwen3.6-Plus": {
             id: "Qwen/Qwen3.6-Plus",
@@ -13255,9 +13232,8 @@ export const MODELS = {
             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: 2.5,
@@ -13268,44 +13244,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 500000,
         },
-        "deepseek-ai/DeepSeek-V3": {
-            id: "deepseek-ai/DeepSeek-V3",
-            name: "DeepSeek-V3",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text"],
-            cost: {
-                input: 1.25,
-                output: 1.25,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "deepseek-ai/DeepSeek-V3-1": {
-            id: "deepseek-ai/DeepSeek-V3-1",
-            name: "DeepSeek V3.1",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.7,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "deepseek-ai/DeepSeek-V4-Pro": {
             id: "deepseek-ai/DeepSeek-V4-Pro",
             name: "DeepSeek V4 Pro",
@@ -13317,8 +13255,8 @@ 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,
             },
@@ -13354,8 +13292,8 @@ 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,
             },
@@ -13380,9 +13318,9 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "moonshotai/Kimi-K2.5": {
-            id: "moonshotai/Kimi-K2.5",
-            name: "Kimi K2.5",
+        "moonshotai/Kimi-K2.6": {
+            id: "moonshotai/Kimi-K2.6",
+            name: "Kimi K2.6",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13391,32 +13329,32 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2.8,
-                cacheRead: 0,
+                input: 1.2,
+                output: 4.5,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 131000,
         },
-        "moonshotai/Kimi-K2.6": {
-            id: "moonshotai/Kimi-K2.6",
-            name: "Kimi K2.6",
+        "moonshotai/Kimi-K2.7-Code": {
+            id: "moonshotai/Kimi-K2.7-Code",
+            name: "Kimi K2.7 Code",
             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"],
+            input: ["text"],
             cost: {
-                input: 1.2,
-                output: 4.5,
-                cacheRead: 0.2,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131000,
+            maxTokens: 131072,
         },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -13424,36 +13362,74 @@ export const MODELS = {
             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" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512300,
+            maxTokens: 512300,
+        },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null },
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "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: { "minimal": null, "low": null, "medium": null },
+            thinkingLevelMap: { "off": null, "minimal": null },
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 3.6,
-                cacheRead: 0.2,
+                input: 0.05,
+                output: 0.2,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 512300,
-            maxTokens: 512300,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
-        "openai/gpt-oss-120b": {
-            id: "openai/gpt-oss-120b",
-            name: "GPT OSS 120B",
+        "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": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 1,
+                output: 3.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 202752,
             maxTokens: 131072,
         },
         "zai-org/GLM-5.1": {
@@ -13520,8 +13496,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.29,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13571,7 +13547,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -13641,7 +13617,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -13741,7 +13717,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -13758,8 +13734,8 @@ 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,
             },
@@ -13775,7 +13751,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2.4,
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
@@ -13793,7 +13769,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 3.5999999999999996,
+                output: 3.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13811,7 +13787,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 0.625,
             },
             contextWindow: 1000000,
@@ -13843,8 +13819,8 @@ 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,
             },
@@ -13877,7 +13853,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
+                input: 0.8,
                 output: 4,
                 cacheRead: 0.08,
                 cacheWrite: 1,
@@ -13896,7 +13872,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 1.25,
             },
             contextWindow: 200000,
@@ -14089,7 +14065,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.25,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14107,7 +14083,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -14266,40 +14242,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "google/gemini-2.0-flash": {
-            id: "google/gemini-2.0-flash",
-            name: "Gemini 2.0 Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
-        "google/gemini-2.0-flash-lite": {
-            id: "google/gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Gemini 2.5 Flash",
@@ -14326,8 +14268,8 @@ 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,
             },
@@ -14362,7 +14304,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14379,7 +14321,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14430,7 +14372,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 12,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -14480,7 +14422,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.14,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14498,7 +14440,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 0.75,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -14650,7 +14592,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.24,
-                output: 0.9700000000000001,
+                output: 0.97,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14666,7 +14608,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.16999999999999998,
+                input: 0.17,
                 output: 0.66,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14820,7 +14762,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.3,
-                output: 0.8999999999999999,
+                output: 0.9,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14836,7 +14778,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14853,7 +14795,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14870,7 +14812,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14887,8 +14829,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.1,
+                output: 0.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -14921,7 +14863,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.4,
                 output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -14972,7 +14914,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15023,7 +14965,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.5700000000000001,
+                input: 0.57,
                 output: 2.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15048,40 +14990,6 @@ 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",
@@ -15093,7 +15001,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 262114,
@@ -15116,6 +15024,23 @@ 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",
@@ -15159,7 +15084,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -15177,7 +15102,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.22999999999999998,
+                output: 0.23,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -15227,9 +15152,9 @@ 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,
@@ -15244,9 +15169,9 @@ 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,
@@ -15348,7 +15273,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -15363,8 +15288,8 @@ 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,
             },
@@ -15433,7 +15358,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -15627,7 +15552,7 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.25,
                 cacheRead: 0.02,
                 cacheWrite: 0,
@@ -15715,8 +15640,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
+                input: 0.05,
+                output: 0.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -15902,7 +15827,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.15,
                 cacheRead: 0.04,
                 cacheWrite: 0,
@@ -15919,9 +15844,9 @@ 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,
@@ -15936,9 +15861,9 @@ 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,
@@ -15955,7 +15880,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -15972,7 +15897,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -15989,7 +15914,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16006,7 +15931,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16023,7 +15948,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16040,7 +15965,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
@@ -16057,7 +15982,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 2.5,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16074,7 +15999,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 2,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -16089,7 +16014,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.1,
                 output: 0.3,
                 cacheRead: 0.01,
                 cacheWrite: 0,
@@ -16108,7 +16033,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16174,7 +16099,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
+                input: 0.2,
                 output: 1.1,
                 cacheRead: 0.03,
                 cacheWrite: 0,
@@ -16192,7 +16117,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.6,
-                output: 1.7999999999999998,
+                output: 1.8,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },
@@ -16226,8 +16151,8 @@ 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,
@@ -16277,7 +16202,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.07,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -16294,7 +16219,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.06,
-                output: 0.39999999999999997,
+                output: 0.4,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
@@ -16311,8 +16236,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 1,
-                output: 3.1999999999999997,
-                cacheRead: 0.19999999999999998,
+                output: 3.2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 202800,
@@ -16419,7 +16344,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
+            contextWindow: 1000000,
             maxTokens: 30000,
         },
         "grok-4.20-0309-reasoning": {
@@ -16436,7 +16361,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
+            contextWindow: 1000000,
             maxTokens: 30000,
         },
         "grok-4.3": {
@@ -16582,6 +16507,24 @@ 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": {
@@ -16656,6 +16599,24 @@ 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": {
@@ -16730,6 +16691,24 @@ 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": {
@@ -16804,6 +16783,24 @@ 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": {
@@ -16878,6 +16875,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",
@@ -16970,6 +16985,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",