@fleetagent/pi-ai 0.0.8 → 0.0.10

package/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,
@@ -345,6 +345,23 @@ 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,
+            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)",
@@ -466,6 +483,23 @@ 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,
+            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)",
@@ -1123,7 +1157,7 @@ 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,
@@ -1140,7 +1174,7 @@ 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,
@@ -1157,7 +1191,7 @@ 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,
@@ -1174,7 +1208,7 @@ 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,
@@ -1338,6 +1372,23 @@ 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,
+            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)",
@@ -1750,6 +1801,23 @@ 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",
+            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)",
@@ -2925,6 +2993,23 @@ 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",
+            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)",
@@ -3892,6 +3977,24 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131072,
         },
+        "accounts/fireworks/routers/kimi-k2p6-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p6-fast",
+            name: "Kimi K2.6 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: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
         "accounts/fireworks/routers/kimi-k2p6-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p6-turbo",
             name: "Kimi K2.6 Turbo",
@@ -4843,77 +4946,9 @@ export const MODELS = {
         },
     },
     "groq": {
-        "deepseek-r1-distill-llama-70b": {
-            id: "deepseek-r1-distill-llama-70b",
-            name: "DeepSeek R1 Distill Llama 70B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.75,
-                output: 0.99,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "gemma2-9b-it": {
-            id: "gemma2-9b-it",
-            name: "Gemma 2 9B",
-            api: "openai-completions",
-            provider: "groq",
-            baseUrl: "https://api.groq.com/openai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 0.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
-        "groq/compound": {
-            id: "groq/compound",
-            name: "Compound",
-            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",
+            name: "Llama 3.1 8B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -4930,7 +4965,7 @@ export const MODELS = {
         },
         "llama-3.3-70b-versatile": {
             id: "llama-3.3-70b-versatile",
-            name: "Llama 3.3 70B Versatile",
+            name: "Llama 3.3 70B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -4945,60 +4980,9 @@ export const MODELS = {
             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",
+            name: "Llama 4 Scout 17B 16E",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -5013,57 +4997,6 @@ 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",
@@ -5115,26 +5048,9 @@ 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",
@@ -7295,6 +7211,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
+        "claude-fable-5": {
+            id: "claude-fable-5",
+            name: "Claude Fable 5",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            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",
@@ -7467,7 +7400,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.03,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7492,6 +7425,25 @@ 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: { "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",
@@ -7973,26 +7925,26 @@ 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",
             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",
@@ -8004,8 +7956,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 256000,
+            maxTokens: 64000,
         },
         "qwen3.5-plus": {
             id: "qwen3.5-plus",
@@ -8226,11 +8178,11 @@ export const MODELS = {
             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: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 512000,
@@ -8426,6 +8378,23 @@ 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",
@@ -8719,23 +8688,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/ernie-4.5-vl-28b-a3b": {
-            id: "baidu/ernie-4.5-vl-28b-a3b",
-            name: "Baidu: ERNIE 4.5 VL 28B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.14,
-                output: 0.56,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8000,
-        },
         "bytedance-seed/seed-1.6": {
             id: "bytedance-seed/seed-1.6",
             name: "ByteDance Seed: Seed 1.6",
@@ -8869,7 +8821,7 @@ export const MODELS = {
                 cacheRead: 0.135,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3.1": {
@@ -9242,8 +9194,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
-                output: 0.13,
+                input: 0.049999999999999996,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9311,12 +9263,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.37,
-                cacheRead: 0,
+                output: 0.36,
+                cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9532,7 +9484,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
+                input: 0.09999999999999999,
                 output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -9601,8 +9553,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.15,
-                output: 1.15,
-                cacheRead: 0,
+                output: 0.8999999999999999,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -9617,9 +9569,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.27899999999999997,
-                output: 1.2,
-                cacheRead: 0,
+                input: 0.27,
+                output: 1.08,
+                cacheRead: 0.054,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -10009,21 +9961,20 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.6799999999999999,
+                output: 3.41,
+                cacheRead: 0.33999999999999997,
                 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)",
+        "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",
-            compat: { "supportsDeveloperRole": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -10033,24 +9984,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
-        },
-        "nex-agi/deepseek-v3.1-nex-n1": {
-            id: "nex-agi/deepseek-v3.1-nex-n1",
-            name: "Nex AGI: DeepSeek V3.1 Nex N1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.135,
-                output: 0.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 163840,
+            maxTokens: 262144,
         },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -10061,7 +9995,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.39999999999999997,
                 output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10307,23 +10241,6 @@ export const MODELS = {
             contextWindow: 8191,
             maxTokens: 4096,
         },
-        "openai/gpt-4-1106-preview": {
-            id: "openai/gpt-4-1106-preview",
-            name: "OpenAI: GPT-4 Turbo (older v1106)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 10,
-                output: 30,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-4-turbo": {
             id: "openai/gpt-4-turbo",
             name: "OpenAI: GPT-4 Turbo",
@@ -11399,7 +11316,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
+                input: 0.09,
                 output: 0.09999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11433,8 +11350,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11892,13 +11809,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.04,
+                input: 0.09999999999999999,
                 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",
@@ -11960,13 +11877,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.29,
-                output: 3.1999999999999997,
+                input: 0.28900000000000003,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262140,
+            maxTokens: 131072,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11977,13 +11894,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
+                input: 0.15,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262140,
+            maxTokens: 262144,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12104,23 +12021,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 128000,
         },
-        "sao10k/l3-euryale-70b": {
-            id: "sao10k/l3-euryale-70b",
-            name: "Sao10k: Llama 3 Euryale 70B v2.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.48,
-                output: 1.48,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
         "sao10k/l3.1-euryale-70b": {
             id: "sao10k/l3.1-euryale-70b",
             name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -12342,23 +12242,6 @@ 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",
@@ -12393,23 +12276,6 @@ 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",
@@ -12455,11 +12321,11 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.8999999999999999,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0.055,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 24000,
+            maxTokens: 32768,
         },
         "z-ai/glm-4.7": {
             id: "z-ai/glm-4.7",
@@ -12526,7 +12392,7 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "z-ai/glm-5.1": {
@@ -12546,22 +12412,22 @@ 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",
@@ -12657,13 +12523,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.684,
-                output: 3.42,
-                cacheRead: 0.144,
+                input: 0.6799999999999999,
+                output: 3.41,
+                cacheRead: 0.33999999999999997,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -13104,8 +12970,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.29,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13469,6 +13335,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
+        "anthropic/claude-fable-5": {
+            id: "anthropic/claude-fable-5",
+            name: "Claude Fable 5",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            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: "Claude Haiku 4.5",
@@ -13849,40 +13732,6 @@ 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",
@@ -16002,7 +15851,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
+            contextWindow: 1000000,
             maxTokens: 30000,
         },
         "grok-4.20-0309-reasoning": {
@@ -16019,7 +15868,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
+            contextWindow: 1000000,
             maxTokens: 30000,
         },
         "grok-4.3": {
@@ -16165,6 +16014,24 @@ 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": {
@@ -16239,6 +16106,24 @@ 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": {
@@ -16313,6 +16198,24 @@ 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": {
@@ -16387,6 +16290,24 @@ 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": {