@entelligentsia/forgecli 1.0.3 → 1.0.10

package/node_modules/@earendil-works/pi-ai/dist/models.generated.js

@@ -157,6 +157,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-opus-4-8": {
+            id: "anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5",
@@ -226,6 +244,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "au.anthropic.claude-opus-4-8": {
+            id: "au.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (AU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (AU)",
@@ -381,6 +417,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "eu.anthropic.claude-opus-4-8": {
+            id: "eu.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (EU)",
@@ -485,6 +539,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-opus-4-8": {
+            id: "global.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (Global)",
@@ -571,6 +643,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "jp.anthropic.claude-opus-4-8": {
+            id: "jp.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (JP)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (JP)",
@@ -1270,6 +1360,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-opus-4-8": {
+            id: "us.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (US)",
@@ -1752,6 +1860,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4-0": {
             id: "claude-sonnet-4-0",
             name: "Claude Sonnet 4 (latest)",
@@ -1919,7 +2046,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2004,7 +2131,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2130,7 +2257,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2431,7 +2558,7 @@ export const MODELS = {
             provider: "azure-openai-responses",
             baseUrl: "",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -2555,7 +2682,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2614,23 +2741,6 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 8000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 32000,
-        },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
             name: "Z.AI GLM-4.7",
@@ -2858,6 +2968,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4 (latest)",
@@ -3755,8 +3884,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
-            maxTokens: 32000,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
         "claude-opus-4.5": {
             id: "claude-opus-4.5",
@@ -3773,7 +3902,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 160000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-opus-4.6": {
@@ -3794,7 +3923,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 32000,
         },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
@@ -3813,7 +3942,27 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-opus-4.8": {
+            id: "claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            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: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "claude-sonnet-4.5": {
@@ -3832,7 +3981,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-sonnet-4.6": {
@@ -3908,7 +4057,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gemini-3.5-flash": {
@@ -3927,7 +4076,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gpt-4.1": {
@@ -4003,8 +4152,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
         "gpt-5.2-codex": {
             id: "gpt-5.2-codex",
@@ -4847,7 +4996,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4864,7 +5013,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4881,7 +5030,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -6262,7 +6411,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -6347,7 +6496,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -6473,7 +6622,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -6774,7 +6923,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -6898,7 +7047,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -7139,6 +7288,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -7575,7 +7743,7 @@ export const MODELS = {
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -7592,7 +7760,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 1,
@@ -7626,6 +7796,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7637,6 +7808,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -7819,7 +8007,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -7839,9 +8029,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7856,9 +8046,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.2,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -7898,9 +8088,9 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "qwen3.5-plus": {
-            id: "qwen3.5-plus",
-            name: "Qwen3.5 Plus",
+        "qwen3.6-plus": {
+            id: "qwen3.6-plus",
+            name: "Qwen3.6 Plus",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -7908,30 +8098,29 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.2,
-                output: 1.2,
-                cacheRead: 0.02,
-                cacheWrite: 0.25,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
+                cacheWrite: 0.625,
             },
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "qwen3.6-plus": {
-            id: "qwen3.6-plus",
-            name: "Qwen3.6 Plus",
-            api: "openai-completions",
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "qwen" },
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.05,
-                cacheWrite: 0.625,
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
     },
@@ -8212,6 +8401,42 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Anthropic: Claude Opus 4.8",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-opus-4.8-fast": {
+            id: "anthropic/claude-opus-4.8-fast",
+            name: "Anthropic: Claude Opus 4.8 (Fast)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Anthropic: Claude Sonnet 4",
@@ -8280,23 +8505,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (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: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -8348,23 +8556,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/cobuddy:free": {
-            id: "baidu/cobuddy:free",
-            name: "Baidu Qianfan: CoBuddy (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: 65536,
-        },
         "baidu/ernie-4.5-21b-a3b": {
             id: "baidu/ernie-4.5-21b-a3b",
             name: "Baidu: ERNIE 4.5 21B A3B",
@@ -8643,18 +8834,18 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.19999999999999998,
-                cacheRead: 0.02,
+                input: 0.0983,
+                output: 0.1966,
+                cacheRead: 0.019700000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "deepseek/deepseek-v4-flash:free": {
             id: "deepseek/deepseek-v4-flash:free",
@@ -8662,9 +8853,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
                 input: 0,
@@ -8681,9 +8872,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
                 input: 0.435,
@@ -8725,7 +8916,7 @@ export const MODELS = {
                 cacheRead: 0.024999999999999998,
                 cacheWrite: 0.08333333333333334,
             },
-            contextWindow: 1000000,
+            contextWindow: 1048576,
             maxTokens: 8192,
         },
         "google/gemini-2.0-flash-lite-001": {
@@ -9772,16 +9963,35 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 4096,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10208,23 +10418,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o-audio-preview": {
-            id: "openai/gpt-4o-audio-preview",
-            name: "OpenAI: GPT-4o Audio",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-4o-mini": {
             id: "openai/gpt-4o-mini",
             name: "OpenAI: GPT-4o-mini",
@@ -10372,11 +10565,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -10389,7 +10582,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -10423,11 +10616,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -10463,7 +10656,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -10634,7 +10827,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -11016,8 +11209,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -11099,7 +11292,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -11677,7 +11870,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11694,7 +11887,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11711,7 +11904,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11725,13 +11918,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2,
-                cacheRead: 0.15,
+                input: 0.29,
+                output: 3.1999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11742,7 +11935,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11810,10 +12003,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
-                cacheRead: 0,
-                cacheWrite: 3.125,
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11903,6 +12096,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "StepFun: Step 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
             name: "Tencent: Hy3 preview",
@@ -11912,13 +12122,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06599999999999999,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.020999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -12150,13 +12360,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
+                input: 0.125,
                 output: 0.85,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -12422,13 +12632,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 262144,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12826,20 +13036,20 @@ export const MODELS = {
         },
         "alibaba/qwen-3-235b": {
             id: "alibaba/qwen-3-235b",
-            name: "Qwen3 235B A22b Instruct 2507",
+            name: "Qwen3 235B A22B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0.6,
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 40000,
+            contextWindow: 262144,
+            maxTokens: 16384,
         },
         "alibaba/qwen-3-30b": {
             id: "alibaba/qwen-3-30b",
@@ -13270,6 +13480,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -14870,7 +15099,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -15051,6 +15280,23 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "Step 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -15264,9 +15510,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15281,9 +15527,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15725,24 +15971,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-ams": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-ams",
-            baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15817,24 +16045,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-cn": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-cn",
-            baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15909,24 +16119,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-sgp": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-sgp",
-            baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",