@earendil-works/pi-ai 0.79.8 → 0.79.9

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": {
@@ -9187,13 +9152,13 @@ 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",
@@ -9689,7 +9654,7 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0.375,
             },
-            contextWindow: 65536,
+            contextWindow: 131072,
             maxTokens: 32768,
         },
         "google/gemini-3.1-flash-lite": {
@@ -9877,7 +9842,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 8192,
+            maxTokens: 32768,
         },
         "ibm-granite/granite-4.1-8b": {
             id: "ibm-granite/granite-4.1-8b",
@@ -9979,8 +9944,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 80000,
+            contextWindow: 262144,
+            maxTokens: 144000,
         },
         "liquid/lfm-2.5-1.2b-thinking:free": {
             id: "liquid/lfm-2.5-1.2b-thinking:free",
@@ -10201,7 +10166,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 512000,
+            maxTokens: 4096,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10537,7 +10502,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.6,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10570,13 +10535,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
+                input: 0.66,
                 output: 3.5,
-                cacheRead: 0.2,
+                cacheRead: 0.33,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -10587,13 +10552,13 @@ 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",
@@ -10916,7 +10881,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 32768,
+            maxTokens: 4096,
         },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
@@ -10946,7 +10911,7 @@ export const MODELS = {
             cost: {
                 input: 2.5,
                 output: 10,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11082,11 +11047,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.025,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 4096,
         },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
@@ -11150,11 +11115,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -11241,7 +11206,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -12454,11 +12419,11 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -12491,8 +12456,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 256000,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -12758,13 +12723,13 @@ 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",
@@ -13079,6 +13044,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text"],
             cost: {
                 input: 1.2,
@@ -13200,13 +13166,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
+                input: 0.66,
                 output: 3.5,
-                cacheRead: 0.2,
+                cacheRead: 0.33,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -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,