@earendil-works/pi-ai 0.79.8 → 0.79.10

package/dist/models.generated.js

@@ -3927,11 +3927,12 @@ export const MODELS = {
         "accounts/fireworks/models/glm-5p2": {
             id: "accounts/fireworks/models/glm-5p2",
             name: "GLM 5.2",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            baseUrl: "https://api.fireworks.ai/inference/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false },
             reasoning: true,
+            thinkingLevelMap: { "off": "none", "minimal": null, "low": "high", "medium": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 1.4,
@@ -4848,42 +4849,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "gemma-4-E2B-it": {
-            id: "gemma-4-E2B-it",
-            name: "Gemma 4 E2B IT",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "gemma-4-E4B-it": {
-            id: "gemma-4-E4B-it",
-            name: "Gemma 4 E4B IT",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
     },
     "google-vertex": {
         "gemini-2.5-flash": {
@@ -8917,23 +8882,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
-        "anthropic/claude-3.5-haiku": {
-            id: "anthropic/claude-3.5-haiku",
-            name: "Anthropic: Claude 3.5 Haiku",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-fable-5": {
             id: "anthropic/claude-fable-5",
             name: "Anthropic: Claude Fable 5",
@@ -9187,13 +9135,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.85,
+                input: 0.25,
+                output: 0.8,
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 80000,
         },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
@@ -10570,9 +10518,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
-                output: 3.5,
-                cacheRead: 0.2,
+                input: 0.66,
+                output: 3.41,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10587,13 +10535,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.74,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.612,
+                output: 3.069,
+                cacheRead: 0.1296,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "nex-agi/nex-n2-pro:free": {
             id: "nex-agi/nex-n2-pro:free",
@@ -10610,7 +10558,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 256000,
         },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -12758,13 +12706,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.066,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.021,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -13066,11 +13014,11 @@ export const MODELS = {
             cost: {
                 input: 0.98,
                 output: 3.08,
-                cacheRead: 0.182,
+                cacheRead: 0.49,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 65535,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -13079,15 +13027,16 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.2,
-                output: 4.1,
-                cacheRead: 0.2,
+                input: 1,
+                output: 4,
+                cacheRead: 0.18,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 32768,
         },
         "~anthropic/claude-fable-latest": {
             id: "~anthropic/claude-fable-latest",
@@ -13200,9 +13149,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
-                output: 3.5,
-                cacheRead: 0.2,
+                input: 0.66,
+                output: 3.41,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -15967,6 +15916,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
+        "sakana/fugu-ultra": {
+            id: "sakana/fugu-ultra",
+            name: "Fugu Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun 3.5 Flash",
@@ -15978,8 +15944,8 @@ export const MODELS = {
             cost: {
                 input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0.02,
+                cacheRead: 0.02,
+                cacheWrite: 0,
             },
             contextWindow: 262114,
             maxTokens: 262114,