@caupulican/pi-ai 0.90.6 → 0.90.11

package/dist/models.generated.js

@@ -4148,6 +4148,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
+        "accounts/fireworks/models/inkling": {
+            id: "accounts/fireworks/models/inkling",
+            name: "Inkling",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.17,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "accounts/fireworks/models/kimi-k2p6": {
             id: "accounts/fireworks/models/kimi-k2p6",
             name: "Kimi K2.6",
@@ -4238,6 +4256,60 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 512000,
         },
+        "accounts/fireworks/models/muse-glimmer-30b": {
+            id: "accounts/fireworks/models/muse-glimmer-30b",
+            name: "Muse Glimmer 30B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.35,
+                output: 1.5,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
+            id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
+            name: "Nemotron 3 Ultra 550B A55B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.119,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 128000,
+        },
+        "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
+            id: "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
+            name: "Nemotron 3.5 Lightning 30B A3B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.05,
+                output: 0.2,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "accounts/fireworks/models/qwen3p7-plus": {
             id: "accounts/fireworks/models/qwen3p7-plus",
             name: "Qwen 3.7 Plus",
@@ -4256,6 +4328,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "accounts/fireworks/models/qwen3p8-max": {
+            id: "accounts/fireworks/models/qwen3p8-max",
+            name: "Qwen3.8 Max",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/routers/glm-5p2-fast": {
             id: "accounts/fireworks/routers/glm-5p2-fast",
             name: "GLM 5.2 Fast",
@@ -5284,6 +5374,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-flash-latest": {
             id: "gemini-flash-latest",
             name: "Gemini Flash Latest",
@@ -6191,6 +6299,24 @@ export const MODELS = {
             contextWindow: 64000,
             maxTokens: 8192,
         },
+        "deepseek-ai/DeepSeek-V3-0324": {
+            id: "deepseek-ai/DeepSeek-V3-0324",
+            name: "DeepSeek V3 0324",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.27,
+                output: 1.12,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 163840,
+            maxTokens: 163840,
+        },
         "deepseek-ai/DeepSeek-V3.1": {
             id: "deepseek-ai/DeepSeek-V3.1",
             name: "DeepSeek-V3.1",
@@ -9077,6 +9203,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -9647,23 +9791,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "ling-3.0-tiny-free": {
-            id: "ling-3.0-tiny-free",
-            name: "Ling-3.0-tiny 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: 262144,
-            maxTokens: 32768,
-        },
         "mimo-v2.5-free": {
             id: "mimo-v2.5-free",
             name: "MiMo V2.5 Free",
@@ -11061,7 +11188,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
+            contextWindow: 64000,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -11162,13 +11289,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 393216,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -11574,10 +11701,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -11591,10 +11718,44 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.75,
-                cacheRead: 0.075,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Google: Gemini 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash:batch": {
+            id: "google/gemini-3.7-flash:batch",
+            name: "Google: Gemini 3.7 Flash (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1875,
+                output: 0.9375,
+                cacheRead: 0.01875,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -11787,23 +11948,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ling-3.0-tiny:free": {
-            id: "inclusionai/ling-3.0-tiny:free",
-            name: "inclusionAI: Ling 3.0 Tiny (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: 262144,
-            maxTokens: 32768,
-        },
         "inclusionai/ring-2.6-1t": {
             id: "inclusionai/ring-2.6-1t",
             name: "inclusionAI: Ring-2.6-1T",
@@ -11887,7 +12031,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32768,
+            maxTokens: 8192,
         },
         "meituan/longcat-2.0": {
             id: "meituan/longcat-2.0",
@@ -12511,9 +12655,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5795,
-                output: 2.44,
-                cacheRead: 0.0976,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12740,6 +12884,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "nvidia/nemotron-3.5-lightning": {
+            id: "nvidia/nemotron-3.5-lightning",
+            name: "NVIDIA: Nemotron 3.5 Lightning",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.25,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 262144,
+        },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
             name: "NVIDIA: Nemotron 3.5 Lightning (free)",
@@ -14820,13 +14981,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14843,7 +15004,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -14888,13 +15049,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -15007,9 +15168,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
-                output: 1,
-                cacheRead: 0,
+                input: 0.25,
+                output: 1.25,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -15247,11 +15408,11 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 52429,
+            contextWindow: 1010000,
+            maxTokens: 262144,
         },
         "qwen/qwen3.8-max": {
             id: "qwen/qwen3.8-max",
@@ -15704,9 +15865,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.11,
+                input: 0.5,
+                output: 2,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -15823,13 +15984,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.49,
-                output: 1.54,
-                cacheRead: 0.091,
+                input: 0.63,
+                output: 1.9800000000000002,
+                cacheRead: 0.0945,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -15965,10 +16126,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -17448,6 +17609,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.8-2.4t-a95b": {
+            id: "alibaba/qwen3.8-2.4t-a95b",
+            name: "Qwen3.8 2.4T A95B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -18214,6 +18392,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Google Gemma 4 26B A4B",
@@ -18245,7 +18440,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "inception/mercury-2": {
@@ -18299,23 +18494,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "inclusionai/ling-3.0-tiny-free": {
-            id: "inclusionai/ling-3.0-tiny-free",
-            name: "Ling 3.0 Tiny (Free)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 32000,
-        },
         "interfaze/interfaze-beta": {
             id: "interfaze/interfaze-beta",
             name: "Interfaze Beta",
@@ -20456,91 +20634,6 @@ export const MODELS = {
         },
     },
     "xai": {
-        "grok-3": {
-            id: "grok-3",
-            name: "Grok 3",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-fast": {
-            id: "grok-3-fast",
-            name: "Grok 3 Fast",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-4.20-0309-non-reasoning": {
-            id: "grok-4.20-0309-non-reasoning",
-            name: "Grok 4.20 (Non-Reasoning)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 2.5,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 30000,
-        },
-        "grok-4.20-0309-reasoning": {
-            id: "grok-4.20-0309-reasoning",
-            name: "Grok 4.20 (Reasoning)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 2.5,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 30000,
-        },
-        "grok-4.3": {
-            id: "grok-4.3",
-            name: "Grok 4.3",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 2.5,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 30000,
-        },
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
@@ -20549,6 +20642,7 @@ export const MODELS = {
             baseUrl: "https://api.x.ai/v1",
             compat: { "supportsLongCacheRetention": false },
             reasoning: true,
+            defaultThinkingLevel: "high",
             thinkingLevelMap: { "off": null, "minimal": null },
             input: ["text", "image"],
             cost: {
@@ -20563,10 +20657,13 @@ export const MODELS = {
         "grok-4.6": {
             id: "grok-4.6",
             name: "Grok 4.6",
-            api: "openai-completions",
+            api: "openai-responses",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
+            compat: { "supportsLongCacheRetention": false },
             reasoning: true,
+            defaultThinkingLevel: "high",
+            thinkingLevelMap: { "off": null, "minimal": null, "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 2,
@@ -20577,40 +20674,6 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
-        "grok-build-0.1": {
-            id: "grok-build-0.1",
-            name: "Grok Build 0.1",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 2,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "grok-code-fast-1": {
-            id: "grok-code-fast-1",
-            name: "Grok Code Fast 1",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 1.5,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 8192,
-        },
     },
     "xiaomi": {
         "mimo-v2-flash": {