@mariozechner/pi-ai 0.70.4 → 0.70.6

package/dist/models.generated.js

@@ -2746,6 +2746,152 @@ export const MODELS = {
             maxTokens: 40000,
         },
     },
+    "cloudflare-workers-ai": {
+        "@cf/google/gemma-4-26b-a4b-it": {
+            id: "@cf/google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
+        "@cf/meta/llama-4-scout-17b-16e-instruct": {
+            id: "@cf/meta/llama-4-scout-17b-16e-instruct",
+            name: "Llama 4 Scout 17B 16E 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", "image"],
+            cost: {
+                input: 0.27,
+                output: 0.85,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@cf/moonshotai/kimi-k2.5": {
+            id: "@cf/moonshotai/kimi-k2.5",
+            name: "Kimi K2.5",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "@cf/moonshotai/kimi-k2.6": {
+            id: "@cf/moonshotai/kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "@cf/nvidia/nemotron-3-120b-a12b": {
+            id: "@cf/nvidia/nemotron-3-120b-a12b",
+            name: "Nemotron 3 Super 120B",
+            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: 0.5,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "@cf/openai/gpt-oss-120b": {
+            id: "@cf/openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            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: 0.35,
+                output: 0.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@cf/openai/gpt-oss-20b": {
+            id: "@cf/openai/gpt-oss-20b",
+            name: "GPT OSS 20B",
+            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: 0.2,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "@cf/zai-org/glm-4.7-flash": {
+            id: "@cf/zai-org/glm-4.7-flash",
+            name: "GLM-4.7-Flash",
+            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: 0.06,
+                output: 0.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+    },
     "deepseek": {
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
@@ -2819,6 +2965,23 @@ export const MODELS = {
             contextWindow: 160000,
             maxTokens: 160000,
         },
+        "accounts/fireworks/models/deepseek-v4-pro": {
+            id: "accounts/fireworks/models/deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/glm-4p5": {
             id: "accounts/fireworks/models/glm-4p5",
             name: "GLM 4.5",
@@ -7397,8 +7560,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "glm-5.1": {
             id: "glm-5.1",
@@ -7414,8 +7577,8 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "kimi-k2.5": {
             id: "kimi-k2.5",
@@ -9495,6 +9658,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
+            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
+            name: "NVIDIA: Nemotron 3 Nano Omni (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: 256000,
+            maxTokens: 65536,
+        },
         "nvidia/nemotron-3-super-120b-a12b": {
             id: "nvidia/nemotron-3-super-120b-a12b",
             name: "NVIDIA: Nemotron 3 Super",
@@ -10566,6 +10746,40 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
+        "poolside/laguna-m.1:free": {
+            id: "poolside/laguna-m.1:free",
+            name: "Poolside: Laguna M.1 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "poolside/laguna-xs.2:free": {
+            id: "poolside/laguna-xs.2:free",
+            name: "Poolside: Laguna XS.2 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
             name: "Prime Intellect: INTELLECT-3",
@@ -11323,12 +11537,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0.25,
+                input: 0.325,
+                output: 3.25,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 256000,
             maxTokens: 65536,
         },
         "qwen/qwen3.6-flash": {
@@ -11357,10 +11571,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.3,
-                output: 7.8,
+                input: 1.04,
+                output: 6.24,
                 cacheRead: 0,
-                cacheWrite: 1.625,
+                cacheWrite: 1.3,
             },
             contextWindow: 262144,
             maxTokens: 65536,
@@ -12840,7 +13054,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,