@draht/ai 2026.3.25-1 → 2026.4.5

package/dist/models.generated.js

@@ -815,8 +815,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 131072,
+            contextWindow: 196608,
+            maxTokens: 98304,
         },
         "mistral.devstral-2-123b": {
             id: "mistral.devstral-2-123b",
@@ -1056,6 +1056,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "nvidia.nemotron-super-3-120b": {
+            id: "nvidia.nemotron-super-3-120b",
+            name: "NVIDIA Nemotron 3 Super 120B A12B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.65,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1444,8 +1461,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 101376,
         },
     },
     "anthropic": {
@@ -1534,23 +1551,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-3-7-sonnet-latest": {
-            id: "claude-3-7-sonnet-latest",
-            name: "Claude Sonnet 3.7 (latest)",
-            api: "anthropic-messages",
-            provider: "anthropic",
-            baseUrl: "https://api.anthropic.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "claude-3-haiku-20240307": {
             id: "claude-3-haiku-20240307",
             name: "Claude Haiku 3",
@@ -2284,6 +2284,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -3443,6 +3460,57 @@ export const MODELS = {
             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": {
+            id: "gemma-4-26b",
+            name: "Gemma 4 26B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+        "gemma-4-31b": {
+            id: "gemma-4-31b",
+            name: "Gemma 4 31B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
     },
     "google-antigravity": {
         "claude-opus-4-5-thinking": {
@@ -3944,6 +4012,40 @@ export const MODELS = {
             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",
@@ -4131,6 +4233,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "openai/gpt-oss-safeguard-20b": {
+            id: "openai/gpt-oss-safeguard-20b",
+            name: "Safety GPT OSS 20B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.037,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 65536,
+        },
         "qwen-qwq-32b": {
             id: "qwen-qwq-32b",
             name: "Qwen QwQ 32B",
@@ -4163,7 +4282,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 40960,
         },
     },
     "huggingface": {
@@ -5094,22 +5213,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "mistral-small-2603": {
+            id: "mistral-small-2603",
+            name: "Mistral Small 4",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral-small-latest": {
             id: "mistral-small-latest",
             name: "Mistral Small (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.3,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "open-mistral-7b": {
             id: "open-mistral-7b",
@@ -5640,6 +5776,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -6494,40 +6647,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "mimo-v2-omni-free": {
-            id: "mimo-v2-omni-free",
-            name: "MiMo V2 Omni Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 64000,
-        },
-        "mimo-v2-pro-free": {
-            id: "mimo-v2-pro-free",
-            name: "MiMo V2 Pro Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 64000,
-        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -6576,9 +6695,26 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 204800,
             maxTokens: 128000,
         },
+        "qwen3.6-plus-free": {
+            id: "qwen3.6-plus-free",
+            name: "Qwen3.6 Plus Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 64000,
+        },
     },
     "opencode-go": {
         "glm-5": {
@@ -6615,12 +6751,46 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "mimo-v2-omni": {
+            id: "mimo-v2-omni",
+            name: "MiMo V2 Omni",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 64000,
+        },
+        "mimo-v2-pro": {
+            id: "mimo-v2-pro",
+            name: "MiMo V2 Pro",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 64000,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6821,30 +6991,13 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.5-sonnet": {
-            id: "anthropic/claude-3.5-sonnet",
-            name: "Anthropic: Claude 3.5 Sonnet",
+        "anthropic/claude-3.7-sonnet": {
+            id: "anthropic/claude-3.7-sonnet",
+            name: "Anthropic: Claude 3.7 Sonnet",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 6,
-                output: 30,
-                cacheRead: 0.6,
-                cacheWrite: 7.5,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic/claude-3.7-sonnet": {
-            id: "anthropic/claude-3.7-sonnet",
-            name: "Anthropic: Claude 3.7 Sonnet",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -7025,6 +7178,23 @@ export const MODELS = {
             contextWindow: 131000,
             maxTokens: 4096,
         },
+        "arcee-ai/trinity-large-thinking": {
+            id: "arcee-ai/trinity-large-thinking",
+            name: "Arcee AI: Trinity Large Thinking",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.22,
+                output: 0.85,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -7465,7 +7635,7 @@ export const MODELS = {
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65535,
         },
         "google/gemini-2.5-pro": {
             id: "google/gemini-2.5-pro",
@@ -7535,23 +7705,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3-pro-preview": {
-            id: "google/gemini-3-pro-preview",
-            name: "Google: Gemini 3 Pro Preview",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -7603,6 +7756,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "google/gemma-4-26b-a4b-it": {
+            id: "google/gemma-4-26b-a4b-it",
+            name: "Google: Gemma 4 26B A4B ",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.13,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "google/gemma-4-31b-it": {
+            id: "google/gemma-4-31b-it",
+            name: "Google: Gemma 4 31B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.14,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "inception/mercury": {
             id: "inception/mercury",
             name: "Inception: Mercury",
@@ -7654,22 +7841,22 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 32000,
         },
-        "kwaipilot/kat-coder-pro": {
-            id: "kwaipilot/kat-coder-pro",
-            name: "Kwaipilot: KAT-Coder-Pro V1",
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kwaipilot: KAT-Coder-Pro V2",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.207,
-                output: 0.828,
-                cacheRead: 0.0414,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 128000,
+            maxTokens: 80000,
         },
         "meituan/longcat-flash-chat": {
             id: "meituan/longcat-flash-chat",
@@ -7867,9 +8054,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.17,
-                cacheRead: 0.09999999999999999,
+                input: 0.118,
+                output: 0.9900000000000001,
+                cacheRead: 0.059,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -8164,23 +8351,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 4096,
         },
-        "mistralai/mistral-small-24b-instruct-2501": {
-            id: "mistralai/mistral-small-24b-instruct-2501",
-            name: "Mistral: Mistral Small 3",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.08,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 16384,
-        },
         "mistralai/mistral-small-2603": {
             id: "mistralai/mistral-small-2603",
             name: "Mistral: Mistral Small 4",
@@ -8198,23 +8368,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "mistralai/mistral-small-3.1-24b-instruct:free": {
-            id: "mistralai/mistral-small-3.1-24b-instruct:free",
-            name: "Mistral: Mistral Small 3.1 24B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "mistralai/mistral-small-3.2-24b-instruct": {
             id: "mistralai/mistral-small-3.2-24b-instruct",
             name: "Mistral: Mistral Small 3.2 24B",
@@ -9252,6 +9405,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-audio": {
+            id: "openai/gpt-audio",
+            name: "OpenAI: GPT Audio",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 10,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "openai/gpt-audio-mini": {
+            id: "openai/gpt-audio-mini",
+            name: "OpenAI: GPT Audio Mini",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "OpenAI: gpt-oss-120b",
@@ -9813,23 +10000,6 @@ export const MODELS = {
             contextWindow: 40960,
             maxTokens: 40960,
         },
-        "qwen/qwen3-4b:free": {
-            id: "qwen/qwen3-4b:free",
-            name: "Qwen: Qwen3 4B (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: 40960,
-            maxTokens: 4096,
-        },
         "qwen/qwen3-8b": {
             id: "qwen/qwen3-8b",
             name: "Qwen: Qwen3 8B",
@@ -10236,7 +10406,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 65536,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -10272,6 +10442,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.6-plus:free": {
+            id: "qwen/qwen3.6-plus:free",
+            name: "Qwen: Qwen3.6 Plus (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "qwen/qwq-32b": {
             id: "qwen/qwq-32b",
             name: "Qwen: QwQ 32B",
@@ -10289,6 +10476,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "rekaai/reka-edge": {
+            id: "rekaai/reka-edge",
+            name: "Reka Edge",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 16384,
+            maxTokens: 16384,
+        },
         "relace/relace-search": {
             id: "relace/relace-search",
             name: "Relace: Relace Search",
@@ -10351,11 +10555,11 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0.02,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "stepfun/step-3.5-flash:free": {
             id: "stepfun/step-3.5-flash:free",
@@ -10561,9 +10765,9 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "x-ai/grok-4.20-beta": {
-            id: "x-ai/grok-4.20-beta",
-            name: "xAI: Grok 4.20 Beta",
+        "x-ai/grok-4.20": {
+            id: "x-ai/grok-4.20",
+            name: "xAI: Grok 4.20",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10833,6 +11037,23 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "z-ai/glm-5v-turbo": {
+            id: "z-ai/glm-5v-turbo",
+            name: "Z.ai: GLM 5V Turbo",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -10854,19 +11075,19 @@ export const MODELS = {
         },
         "alibaba/qwen-3-235b": {
             id: "alibaba/qwen-3-235b",
-            name: "Qwen3-235B-A22B",
+            name: "Qwen3 235B A22b Instruct 2507",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
-                output: 0.463,
-                cacheRead: 0,
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 32768,
             maxTokens: 16384,
         },
         "alibaba/qwen-3-30b": {
@@ -10895,13 +11116,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.29,
-                output: 0.59,
-                cacheRead: 0.145,
+                input: 0.16,
+                output: 0.64,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 40960,
+            contextWindow: 128000,
+            maxTokens: 8192,
         },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10929,13 +11150,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.022,
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 66536,
+            maxTokens: 65536,
         },
         "alibaba/qwen3-coder-30b-a3b": {
             id: "alibaba/qwen3-coder-30b-a3b",
@@ -11048,13 +11269,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.88,
+                input: 0.39999999999999997,
+                output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "alibaba/qwen3.5-flash": {
             id: "alibaba/qwen3.5-flash",
@@ -11090,6 +11311,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.6-plus": {
+            id: "alibaba/qwen3.6-plus",
+            name: "Qwen 3.6 Plus",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0.625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -11124,40 +11362,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.5-sonnet": {
-            id: "anthropic/claude-3.5-sonnet",
-            name: "Claude 3.5 Sonnet",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic/claude-3.5-sonnet-20240620": {
-            id: "anthropic/claude-3.5-sonnet-20240620",
-            name: "Claude 3.5 Sonnet (2024-06-20)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-3.7-sonnet": {
             id: "anthropic/claude-3.7-sonnet",
             name: "Claude 3.7 Sonnet",
@@ -11328,6 +11532,23 @@ export const MODELS = {
             contextWindow: 131000,
             maxTokens: 131000,
         },
+        "arcee-ai/trinity-large-thinking": {
+            id: "arcee-ai/trinity-large-thinking",
+            name: "Trinity Large Thinking",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.25,
+                output: 0.8999999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262100,
+            maxTokens: 80000,
+        },
         "bytedance/seed-1.6": {
             id: "bytedance/seed-1.6",
             name: "Seed 1.6",
@@ -11405,13 +11626,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
+                input: 0.56,
+                output: 1.68,
+                cacheRead: 0.28,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -11617,6 +11838,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemma-4-26b-a4b-it": {
+            id: "google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.13,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
+        "google/gemma-4-31b-it": {
+            id: "google/gemma-4-31b-it",
+            name: "Gemma 4 31B IT",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.14,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Mercury 2",
@@ -11651,34 +11906,34 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 16384,
         },
-        "meituan/longcat-flash-chat": {
-            id: "meituan/longcat-flash-chat",
-            name: "LongCat Flash Chat",
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kat Coder Pro V2",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 100000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
-        "meituan/longcat-flash-thinking": {
-            id: "meituan/longcat-flash-thinking",
-            name: "LongCat Flash Thinking",
+        "meituan/longcat-flash-chat": {
+            id: "meituan/longcat-flash-chat",
+            name: "LongCat Flash Chat",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 1.5,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11711,13 +11966,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.22,
+                output: 0.22,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta/llama-3.2-11b": {
             id: "meta/llama-3.2-11b",
@@ -12095,20 +12350,20 @@ export const MODELS = {
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
-            name: "Kimi K2",
+            name: "Kimi K2 Instruct",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.5,
-                cacheRead: 0.15,
+                input: 0.5700000000000001,
+                output: 2.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "moonshotai/kimi-k2-0905": {
             id: "moonshotai/kimi-k2-0905",
@@ -12121,11 +12376,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 16384,
+            maxTokens: 128000,
         },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
@@ -12688,6 +12943,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "gpt-oss-20b",
@@ -12697,12 +12969,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.3,
+                input: 0.049999999999999996,
+                output: 0.19999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "openai/gpt-oss-safeguard-20b": {
@@ -13173,9 +13445,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.02,
+                input: 0.09,
+                output: 0.29,
+                cacheRead: 0.045,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13311,7 +13583,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.2,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -13385,6 +13657,23 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131100,
         },
+        "zai/glm-5v-turbo": {
+            id: "zai/glm-5v-turbo",
+            name: "GLM 5V Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 128000,
+        },
     },
     "xai": {
         "grok-2": {
@@ -13875,7 +14164,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -13893,7 +14182,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -13911,7 +14200,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -13929,7 +14218,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -13941,13 +14230,31 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-4.7-flashx": {
+            id: "glm-4.7-flashx",
+            name: "GLM-4.7-FlashX",
+            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: 0.07,
+                output: 0.4,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -13965,7 +14272,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -13977,6 +14284,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5v-turbo": {
+            id: "glm-5v-turbo",
+            name: "glm-5v-turbo",
+            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", "image"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
     },
 };
 //# sourceMappingURL=models.generated.js.map