@mariozechner/pi-ai 0.63.2 → 0.65.0

package/dist/models.generated.js

@@ -1551,23 +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",
@@ -2301,6 +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",
@@ -5026,22 +5026,39 @@ 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",
@@ -5572,6 +5589,23 @@ 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",
@@ -6426,40 +6460,6 @@ 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",
@@ -6508,9 +6508,26 @@ 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": {
@@ -6547,12 +6564,46 @@ 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: {
@@ -6957,6 +7008,23 @@ 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",
@@ -7397,7 +7465,7 @@ export const MODELS = {
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65535,
         },
         "google/gemini-2.5-pro": {
             id: "google/gemini-2.5-pro",
@@ -7518,6 +7586,40 @@ 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",
@@ -7569,23 +7671,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 32000,
         },
-        "kwaipilot/kat-coder-pro": {
-            id: "kwaipilot/kat-coder-pro",
-            name: "Kwaipilot: KAT-Coder-Pro V1",
-            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,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 128000,
-        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -7799,9 +7884,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19,
-                output: 1.15,
-                cacheRead: 0.095,
+                input: 0.118,
+                output: 0.9900000000000001,
+                cacheRead: 0.059,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -8096,23 +8181,6 @@ 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",
@@ -9167,6 +9235,40 @@ 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",
@@ -10134,7 +10236,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 65536,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -10170,6 +10272,23 @@ 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",
@@ -10187,8 +10306,8 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "reka/reka-edge": {
-            id: "reka/reka-edge",
+        "rekaai/reka-edge": {
+            id: "rekaai/reka-edge",
             name: "Reka Edge",
             api: "openai-completions",
             provider: "openrouter",
@@ -10266,11 +10385,11 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0.02,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 65536,
         },
         "stepfun/step-3.5-flash:free": {
             id: "stepfun/step-3.5-flash:free",
@@ -10476,9 +10595,9 @@ 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",
@@ -10748,6 +10867,23 @@ 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": {
@@ -10776,12 +10912,12 @@ export const MODELS = {
             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": {
@@ -10810,13 +10946,13 @@ 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",
@@ -10844,13 +10980,13 @@ 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",
@@ -11005,6 +11141,23 @@ 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",
@@ -11243,6 +11396,23 @@ 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",
@@ -11320,13 +11490,13 @@ 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",
@@ -11532,6 +11702,40 @@ 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: true,
+            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: true,
+            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",
@@ -11598,7 +11802,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 100000,
+            maxTokens: 8192,
         },
         "meituan/longcat-flash-thinking": {
             id: "meituan/longcat-flash-thinking",
@@ -11643,13 +11847,13 @@ 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",
@@ -11711,12 +11915,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.24,
-                output: 0.9700000000000001,
+                input: 0.35,
+                output: 1.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 524288,
             maxTokens: 8192,
         },
         "meta/llama-4-scout": {
@@ -12036,7 +12240,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12053,11 +12257,11 @@ 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",
@@ -12620,6 +12824,23 @@ 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",
@@ -12629,12 +12850,12 @@ 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": {
@@ -13105,9 +13326,9 @@ 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,
@@ -13243,7 +13464,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.2,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -13283,6 +13504,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 128000,
         },
+        "zai/glm-5": {
+            id: "zai/glm-5",
+            name: "GLM 5",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3.1999999999999997,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 131100,
+        },
         "zai/glm-5-turbo": {
             id: "zai/glm-5-turbo",
             name: "GLM 5 Turbo",
@@ -13300,6 +13538,23 @@ 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": {
@@ -13790,7 +14045,7 @@ 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: {
@@ -13808,7 +14063,7 @@ 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: {
@@ -13826,7 +14081,7 @@ 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: {
@@ -13844,7 +14099,7 @@ 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: {
@@ -13862,7 +14117,7 @@ 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: {
@@ -13880,7 +14135,7 @@ 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: {
@@ -13898,7 +14153,7 @@ 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: {
@@ -13910,6 +14165,24 @@ 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