@elyracode/ai 0.6.4 → 0.7.0

package/dist/models.generated.js

@@ -3275,6 +3275,42 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 16384,
         },
+        "@cf/ibm-granite/granite-4.0-h-micro": {
+            id: "@cf/ibm-granite/granite-4.0-h-micro",
+            name: "Granite 4.0 H Micro",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.017,
+                output: 0.112,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 131000,
+        },
+        "@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
+            id: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+            name: "Llama 3.3 70B Instruct fp8 Fast",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.293,
+                output: 2.253,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 24000,
+            maxTokens: 24000,
+        },
         "@cf/meta/llama-4-scout-17b-16e-instruct": {
             id: "@cf/meta/llama-4-scout-17b-16e-instruct",
             name: "Llama 4 Scout 17B 16E Instruct",
@@ -3290,9 +3326,27 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131000,
             maxTokens: 16384,
         },
+        "@cf/mistralai/mistral-small-3.1-24b-instruct": {
+            id: "@cf/mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral Small 3.1 24B Instruct",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.351,
+                output: 0.555,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
         "@cf/moonshotai/kimi-k2.5": {
             id: "@cf/moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -3326,7 +3380,7 @@ export const MODELS = {
                 cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "@cf/nvidia/nemotron-3-120b-a12b": {
@@ -3383,6 +3437,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "@cf/qwen/qwen3-30b-a3b-fp8": {
+            id: "@cf/qwen/qwen3-30b-a3b-fp8",
+            name: "Qwen3 30B A3b fp8",
+            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"],
+            cost: {
+                input: 0.0509,
+                output: 0.335,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
         "@cf/zai-org/glm-4.7-flash": {
             id: "@cf/zai-org/glm-4.7-flash",
             name: "GLM-4.7-Flash",
@@ -3393,7 +3465,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -4146,57 +4218,6 @@ export const MODELS = {
         },
     },
     "google": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
         "gemini-2.0-flash": {
             id: "gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -4216,7 +4237,7 @@ export const MODELS = {
         },
         "gemini-2.0-flash-lite": {
             id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
+            name: "Gemini 2.0 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4250,7 +4271,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4265,91 +4286,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-lite-preview-06-17": {
-            id: "gemini-2.5-flash-lite-preview-06-17",
-            name: "Gemini 2.5 Flash Lite Preview 06-17",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-04-17": {
-            id: "gemini-2.5-flash-preview-04-17",
-            name: "Gemini 2.5 Flash Preview 04-17",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-05-20": {
-            id: "gemini-2.5-flash-preview-05-20",
-            name: "Gemini 2.5 Flash Preview 05-20",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-09-2025": {
-            id: "gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-25",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-2.5-pro": {
             id: "gemini-2.5-pro",
             name: "Gemini 2.5 Pro",
@@ -4367,40 +4303,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-pro-preview-05-06": {
-            id: "gemini-2.5-pro-preview-05-06",
-            name: "Gemini 2.5 Pro Preview 05-06",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro-preview-06-05": {
-            id: "gemini-2.5-pro-preview-06-05",
-            name: "Gemini 2.5 Pro Preview 06-05",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
             name: "Gemini 3 Flash Preview",
@@ -4434,8 +4336,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-flash-lite": {
             id: "gemini-3.1-flash-lite",
@@ -4561,60 +4463,9 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-live-2.5-flash": {
-            id: "gemini-live-2.5-flash",
-            name: "Gemini Live 2.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8000,
-        },
-        "gemini-live-2.5-flash-preview-native-audio": {
-            id: "gemini-live-2.5-flash-preview-native-audio",
-            name: "Gemini Live 2.5 Flash Preview Native Audio",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "gemma-3-27b-it": {
-            id: "gemma-3-27b-it",
-            name: "Gemma 3 27B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
         "gemma-4-26b-a4b-it": {
             id: "gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B",
+            name: "Gemma 4 26B A4B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4627,12 +4478,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "gemma-4-31b-it": {
             id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
+            name: "Gemma 4 31B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4645,8 +4496,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
     },
     "google-vertex": {
@@ -7898,6 +7749,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -7949,23 +7817,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "minimax-m2.5-free": {
-            id: "minimax-m2.5-free",
-            name: "MiniMax M2.5 Free",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "minimax-m2.7": {
             id: "minimax-m2.7",
             name: "MiniMax M2.7",
@@ -9457,9 +9308,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.06,
+                input: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12004,7 +11855,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0.195,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12104,13 +11955,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.149,
+                input: 0.15,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12240,13 +12091,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 16384,
         },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
@@ -12350,6 +12201,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 4096,
         },
+        "x-ai/grok-build-0.1": {
+            id: "x-ai/grok-build-0.1",
+            name: "xAI: Grok Build 0.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 4096,
+        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "Xiaomi: MiMo-V2-Flash",
@@ -15493,6 +15361,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "xai/grok-build-0.1": {
+            id: "xai/grok-build-0.1",
+            name: "Grok Build 0.1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "MiMo V2 Flash",
@@ -15784,108 +15669,6 @@ export const MODELS = {
         },
     },
     "xai": {
-        "grok-2": {
-            id: "grok-2",
-            name: "Grok 2",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-1212": {
-            id: "grok-2-1212",
-            name: "Grok 2 (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-latest": {
-            id: "grok-2-latest",
-            name: "Grok 2 Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-vision": {
-            id: "grok-2-vision",
-            name: "Grok 2 Vision",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-1212": {
-            id: "grok-2-vision-1212",
-            name: "Grok 2 Vision (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-latest": {
-            id: "grok-2-vision-latest",
-            name: "Grok 2 Vision Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
         "grok-4.20-0309-non-reasoning": {
             id: "grok-4.20-0309-non-reasoning",
             name: "Grok 4.20 (Non-Reasoning)",
@@ -15895,8 +15678,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15912,8 +15695,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15937,22 +15720,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 30000,
         },
-        "grok-beta": {
-            id: "grok-beta",
-            name: "Grok Beta",
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
@@ -15971,23 +15754,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 8192,
         },
-        "grok-vision-beta": {
-            id: "grok-vision-beta",
-            name: "Grok Vision Beta",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
     },
     "xiaomi": {
         "mimo-v2-flash": {