@earendil-works/pi-ai 0.79.2 → 0.79.4

package/dist/models.generated.js

@@ -3942,9 +3942,9 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
-        "accounts/fireworks/models/kimi-k2p5": {
-            id: "accounts/fireworks/models/kimi-k2p5",
-            name: "Kimi K2.5",
+        "accounts/fireworks/models/kimi-k2p6": {
+            id: "accounts/fireworks/models/kimi-k2p6",
+            name: "Kimi K2.6",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3952,17 +3952,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262000,
+            maxTokens: 262000,
         },
-        "accounts/fireworks/models/kimi-k2p6": {
-            id: "accounts/fireworks/models/kimi-k2p6",
-            name: "Kimi K2.6",
+        "accounts/fireworks/models/kimi-k2p7-code": {
+            id: "accounts/fireworks/models/kimi-k2p7-code",
+            name: "Kimi K2.7 Code",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3972,15 +3972,15 @@ export const MODELS = {
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.16,
+                cacheRead: 0.19,
                 cacheWrite: 0,
             },
             contextWindow: 262000,
             maxTokens: 262000,
         },
-        "accounts/fireworks/models/minimax-m2p5": {
-            id: "accounts/fireworks/models/minimax-m2p5",
-            name: "MiniMax-M2.5",
+        "accounts/fireworks/models/minimax-m2p7": {
+            id: "accounts/fireworks/models/minimax-m2p7",
+            name: "MiniMax-M2.7",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3990,15 +3990,15 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.03,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
             maxTokens: 196608,
         },
-        "accounts/fireworks/models/minimax-m2p7": {
-            id: "accounts/fireworks/models/minimax-m2p7",
-            name: "MiniMax-M2.7",
+        "accounts/fireworks/models/minimax-m3": {
+            id: "accounts/fireworks/models/minimax-m3",
+            name: "MiniMax-M3",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4011,12 +4011,12 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
-            maxTokens: 196608,
+            contextWindow: 512000,
+            maxTokens: 512000,
         },
-        "accounts/fireworks/models/qwen3p6-plus": {
-            id: "accounts/fireworks/models/qwen3p6-plus",
-            name: "Qwen 3.6 Plus",
+        "accounts/fireworks/models/qwen3p7-plus": {
+            id: "accounts/fireworks/models/qwen3p7-plus",
+            name: "Qwen 3.7 Plus",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4024,9 +4024,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4086,6 +4086,24 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "accounts/fireworks/routers/kimi-k2p7-code-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
+            name: "Kimi K2.7 Code Fast",
+            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: 2,
+                output: 8,
+                cacheRead: 0.38,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
     },
     "github-copilot": {
         "claude-fable-5": {
@@ -4173,7 +4191,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4193,7 +4211,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4251,6 +4269,7 @@ export const MODELS = {
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "forceAdaptiveThinking": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": "low", "xhigh": "max" },
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -4810,6 +4829,42 @@ 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-1.5-flash": {
@@ -7379,7 +7434,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.4-mini": {
@@ -7451,7 +7506,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.5-pro": {
@@ -7643,7 +7698,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.4-mini": {
@@ -7661,7 +7716,7 @@ export const MODELS = {
                 cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
         "gpt-5.5": {
@@ -7679,7 +7734,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
     },
@@ -7702,25 +7757,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "claude-fable-5": {
-            id: "claude-fable-5",
-            name: "Claude Fable 5",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            compat: { "forceAdaptiveThinking": true },
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -7887,7 +7923,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -7925,7 +7961,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8341,7 +8377,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8359,7 +8395,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8413,7 +8449,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8577,7 +8613,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
@@ -9430,13 +9466,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.098,
-                output: 0.196,
+                input: 0.09,
+                output: 0.18,
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -10471,13 +10507,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.19,
+                input: 0.75,
+                output: 3.5,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "nex-agi/nex-n2-pro:free": {
             id: "nex-agi/nex-n2-pro:free",
@@ -13079,6 +13115,25 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "MiniMaxAI/MiniMax-M3": {
+            id: "MiniMaxAI/MiniMax-M3",
+            name: "MiniMax-M3",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 250000,
+        },
         "Qwen/Qwen2.5-7B-Instruct-Turbo": {
             id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
             name: "Qwen 2.5 7B Instruct Turbo",
@@ -13283,6 +13338,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "moonshotai/Kimi-K2.7-Code": {
+            id: "moonshotai/Kimi-K2.7-Code",
+            name: "Kimi K2.7 Code",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
             name: "Nemotron 3 Ultra 550B A55B",
@@ -13788,25 +13862,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-fable-5": {
-            id: "anthropic/claude-fable-5",
-            name: "Claude Fable 5",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            compat: { "forceAdaptiveThinking": true },
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Claude Haiku 4.5",
@@ -16821,6 +16876,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            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"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",
@@ -16913,6 +16986,24 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",