npm - @dreb/ai - Versions diffs - 2.48.0 → 2.50.0 - Mend

@dreb/ai 2.48.0 → 2.50.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (5) hide show

package/dist/models.generated.d.ts +118 -506
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +192 -582
package/dist/models.generated.js.map +1 -1
package/package.json +1 -1

package/dist/models.generated.js CHANGED Viewed

@@ -1354,10 +1354,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.22,
+                output: 1.32,
+                cacheRead: 0.022,
+                cacheWrite: 0.275,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -1371,10 +1371,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 6.88,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -1388,10 +1388,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2.2,
+                output: 13.2,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
             },
             contextWindow: 272000,
             maxTokens: 128000,
@@ -2752,10 +2752,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2786,10 +2786,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -5273,6 +5273,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 1048576,
         },
+        "thinkingmachines/Inkling-Small": {
+            id: "thinkingmachines/Inkling-Small",
+            name: "Inkling Small",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 1048576,
+        },
         "zai-org/GLM-4.5": {
             id: "zai-org/GLM-4.5",
             name: "GLM-4.5",
@@ -6162,6 +6180,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
+        "voxtral-small-latest": {
+            id: "voxtral-small-latest",
+            name: "Voxtral Small (latest)",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32000,
+            maxTokens: 32000,
+        },
     },
     "openai": {
         "gpt-4": {
@@ -6700,10 +6735,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -6734,10 +6769,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -7275,7 +7310,7 @@ export const MODELS = {
         },
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
+            name: "DeepSeek V4 Flash 0731",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -7292,7 +7327,7 @@ export const MODELS = {
         },
         "deepseek-v4-flash-free": {
             id: "deepseek-v4-flash-free",
-            name: "DeepSeek V4 Flash Free",
+            name: "DeepSeek V4 Flash Free (New)",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -7741,10 +7776,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8059,7 +8094,7 @@ export const MODELS = {
     "opencode-go": {
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
+            name: "DeepSeek V4 Flash (New)",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8125,6 +8160,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "gpt-5.6-luna": {
+            id: "gpt-5.6-luna",
+            name: "GPT-5.6 Luna (2x usage)",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.6,
+                cacheRead: 0.01,
+                cacheWrite: 0.125,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
@@ -8195,7 +8247,7 @@ export const MODELS = {
         },
         "kimi-k3": {
             id: "kimi-k3",
-            name: "Kimi K3 (2x usage)",
+            name: "Kimi K3",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8518,23 +8570,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-fable-5:batch": {
-            id: "anthropic/claude-fable-5:batch",
-            name: "Anthropic: Claude Fable 5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Anthropic: Claude Haiku 4.5",
@@ -8552,23 +8587,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "anthropic/claude-haiku-4.5:batch": {
-            id: "anthropic/claude-haiku-4.5:batch",
-            name: "Anthropic: Claude Haiku 4.5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 2.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0.625,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "anthropic/claude-opus-4": {
             id: "anthropic/claude-opus-4",
             name: "Anthropic: Claude Opus 4",
@@ -8603,23 +8621,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "anthropic/claude-opus-4.1:batch": {
-            id: "anthropic/claude-opus-4.1:batch",
-            name: "Anthropic: Claude Opus 4.1 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 7.5,
-                output: 37.5,
-                cacheRead: 0.75,
-                cacheWrite: 9.375,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
         "anthropic/claude-opus-4.5": {
             id: "anthropic/claude-opus-4.5",
             name: "Anthropic: Claude Opus 4.5",
@@ -8637,23 +8638,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "anthropic/claude-opus-4.5:batch": {
-            id: "anthropic/claude-opus-4.5:batch",
-            name: "Anthropic: Claude Opus 4.5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 12.5,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "anthropic/claude-opus-4.6": {
             id: "anthropic/claude-opus-4.6",
             name: "Anthropic: Claude Opus 4.6",
@@ -8671,23 +8655,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.6:batch": {
-            id: "anthropic/claude-opus-4.6:batch",
-            name: "Anthropic: Claude Opus 4.6 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 12.5,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.7": {
             id: "anthropic/claude-opus-4.7",
             name: "Anthropic: Claude Opus 4.7",
@@ -8722,23 +8689,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.7:batch": {
-            id: "anthropic/claude-opus-4.7:batch",
-            name: "Anthropic: Claude Opus 4.7 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 12.5,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.8": {
             id: "anthropic/claude-opus-4.8",
             name: "Anthropic: Claude Opus 4.8",
@@ -8773,23 +8723,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.8:batch": {
-            id: "anthropic/claude-opus-4.8:batch",
-            name: "Anthropic: Claude Opus 4.8 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 12.5,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-5": {
             id: "anthropic/claude-opus-5",
             name: "Claude Opus 5",
@@ -8858,23 +8791,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "anthropic/claude-sonnet-4.5:batch": {
-            id: "anthropic/claude-sonnet-4.5:batch",
-            name: "Anthropic: Claude Sonnet 4.5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 1.875,
-            },
-            contextWindow: 1000000,
-            maxTokens: 64000,
-        },
         "anthropic/claude-sonnet-4.6": {
             id: "anthropic/claude-sonnet-4.6",
             name: "Anthropic: Claude Sonnet 4.6",
@@ -8909,23 +8825,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-sonnet-5:batch": {
-            id: "anthropic/claude-sonnet-5:batch",
-            name: "Anthropic: Claude Sonnet 5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "arcee-ai/trinity-large-thinking": {
             id: "arcee-ai/trinity-large-thinking",
             name: "Arcee AI: Trinity Large Thinking",
@@ -9249,6 +9148,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 393216,
         },
+        "deepseek/deepseek-v4-flash-0731": {
+            id: "deepseek/deepseek-v4-flash-0731",
+            name: "DeepSeek: DeepSeek V4 Flash 0731",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.018,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
             name: "DeepSeek: DeepSeek V4 Pro",
@@ -9300,56 +9216,22 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65535,
         },
-        "google/gemini-2.5-flash-lite:batch": {
-            id: "google/gemini-2.5-flash-lite:batch",
-            name: "Google: Gemini 2.5 Flash Lite (batch)",
+        "google/gemini-2.5-pro": {
+            id: "google/gemini-2.5-pro",
+            name: "Google: Gemini 2.5 Pro",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.01,
-                cacheWrite: 0,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0.375,
             },
             contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "google/gemini-2.5-flash:batch": {
-            id: "google/gemini-2.5-flash:batch",
-            name: "Google: Gemini 2.5 Flash (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 1.25,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
-        "google/gemini-2.5-pro": {
-            id: "google/gemini-2.5-pro",
-            name: "Google: Gemini 2.5 Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65536,
         },
         "google/gemini-2.5-pro-preview": {
             id: "google/gemini-2.5-pro-preview",
@@ -9385,23 +9267,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65535,
         },
-        "google/gemini-2.5-pro:batch": {
-            id: "google/gemini-2.5-pro:batch",
-            name: "Google: Gemini 2.5 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3-flash-preview": {
             id: "google/gemini-3-flash-preview",
             name: "Google: Gemini 3 Flash Preview",
@@ -9419,23 +9284,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65535,
         },
-        "google/gemini-3-flash-preview:batch": {
-            id: "google/gemini-3-flash-preview:batch",
-            name: "Google: Gemini 3 Flash Preview (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
         "google/gemini-3-pro-image": {
             id: "google/gemini-3-pro-image",
             name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
@@ -9487,23 +9335,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3.1-flash-lite:batch": {
-            id: "google/gemini-3.1-flash-lite:batch",
-            name: "Google: Gemini 3.1 Flash Lite (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.125,
-                output: 0.75,
-                cacheRead: 0.012499999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3.1-pro-preview": {
             id: "google/gemini-3.1-pro-preview",
             name: "Google: Gemini 3.1 Pro Preview",
@@ -9538,23 +9369,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3.1-pro-preview:batch": {
-            id: "google/gemini-3.1-pro-preview:batch",
-            name: "Google: Gemini 3.1 Pro Preview (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3.5-flash": {
             id: "google/gemini-3.5-flash",
             name: "Google: Gemini 3.5 Flash",
@@ -9589,40 +9403,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3.5-flash-lite:batch": {
-            id: "google/gemini-3.5-flash-lite:batch",
-            name: "Google: Gemini 3.5 Flash Lite (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 1.25,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "google/gemini-3.5-flash:batch": {
-            id: "google/gemini-3.5-flash:batch",
-            name: "Google: Gemini 3.5 Flash (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.75,
-                output: 4.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemini-3.6-flash": {
             id: "google/gemini-3.6-flash",
             name: "Google: Gemini 3.6 Flash",
@@ -9640,23 +9420,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3.6-flash:batch": {
-            id: "google/gemini-3.6-flash:batch",
-            name: "Google: Gemini 3.6 Flash (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.75,
-                output: 3.75,
-                cacheRead: 0.075,
-                cacheWrite: 0.08333333333333334,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Google: Gemma 3 12B",
@@ -10133,23 +9896,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 512000,
         },
-        "minimax/minimax-m3:batch": {
-            id: "minimax/minimax-m3:batch",
-            name: "MiniMax: MiniMax M3 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 524288,
-            maxTokens: 4096,
-        },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
             name: "Mistral: Codestral 2508",
@@ -10167,23 +9913,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "mistralai/devstral-2512": {
-            id: "mistralai/devstral-2512",
-            name: "Mistral: Devstral 2 2512",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 4096,
-        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -10397,13 +10126,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
+                input: 0.075,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
             id: "mistralai/mixtral-8x22b-instruct",
@@ -10516,9 +10245,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.16,
+                input: 0.6,
+                output: 3.41,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11034,23 +10763,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-mini:batch": {
-            id: "openai/gpt-5-mini:batch",
-            name: "OpenAI: GPT-5 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.125,
-                output: 1,
-                cacheRead: 0.012499999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
             name: "OpenAI: GPT-5 Nano",
@@ -11068,23 +10780,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-nano:batch": {
-            id: "openai/gpt-5-nano:batch",
-            name: "OpenAI: GPT-5 Nano (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.024999999999999998,
-                output: 0.19999999999999998,
-                cacheRead: 0.0025,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-pro": {
             id: "openai/gpt-5-pro",
             name: "OpenAI: GPT-5 Pro",
@@ -11119,23 +10814,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.1-chat": {
-            id: "openai/gpt-5.1-chat",
-            name: "OpenAI: GPT-5.1 Chat",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.13,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32000,
-        },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
             name: "OpenAI: GPT-5.1-Codex",
@@ -11187,23 +10865,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.1:batch": {
-            id: "openai/gpt-5.1:batch",
-            name: "OpenAI: GPT-5.1 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.0625,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
             name: "OpenAI: GPT-5.2",
@@ -11272,23 +10933,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.2:batch": {
-            id: "openai/gpt-5.2:batch",
-            name: "OpenAI: GPT-5.2 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.875,
-                output: 7,
-                cacheRead: 0.0875,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.3-chat": {
             id: "openai/gpt-5.3-chat",
             name: "OpenAI: GPT-5.3 Chat",
@@ -11357,23 +11001,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-mini:batch": {
-            id: "openai/gpt-5.4-mini:batch",
-            name: "OpenAI: GPT-5.4 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.375,
-                output: 2.25,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.4-nano": {
             id: "openai/gpt-5.4-nano",
             name: "OpenAI: GPT-5.4 Nano",
@@ -11391,23 +11018,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-nano:batch": {
-            id: "openai/gpt-5.4-nano:batch",
-            name: "OpenAI: GPT-5.4 Nano (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.625,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "OpenAI: GPT-5.4 Pro",
@@ -11425,23 +11035,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4:batch": {
-            id: "openai/gpt-5.4:batch",
-            name: "OpenAI: GPT-5.4 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.5": {
             id: "openai/gpt-5.5",
             name: "OpenAI: GPT-5.5",
@@ -11476,23 +11069,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.5:batch": {
-            id: "openai/gpt-5.5:batch",
-            name: "OpenAI: GPT-5.5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.6-luna": {
             id: "openai/gpt-5.6-luna",
             name: "OpenAI: GPT-5.6 Luna",
@@ -11503,9 +11079,9 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.09999999999999999,
-                output: 0.6000000000000001,
+                output: 0.6,
                 cacheRead: 0.01,
-                cacheWrite: 0.12500000000000003,
+                cacheWrite: 0.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -11595,23 +11171,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5:batch": {
-            id: "openai/gpt-5:batch",
-            name: "OpenAI: GPT-5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.0625,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-audio": {
             id: "openai/gpt-audio",
             name: "OpenAI: GPT Audio",
@@ -12234,12 +11793,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.07,
-                output: 0.27,
+                output: 0.28,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 262144,
         },
         "qwen/qwen3-coder-flash": {
             id: "qwen/qwen3-coder-flash",
@@ -12403,13 +11962,13 @@ 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",
@@ -12732,7 +12291,7 @@ export const MODELS = {
                 cacheWrite: 1.84375,
             },
             contextWindow: 1000000,
-            maxTokens: 65536,
+            maxTokens: 131072,
         },
         "qwen/qwen3.7-plus": {
             id: "qwen/qwen3.7-plus",
@@ -12749,7 +12308,7 @@ export const MODELS = {
                 cacheWrite: 0.39999999999999997,
             },
             contextWindow: 1000000,
-            maxTokens: 65536,
+            maxTokens: 131072,
         },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
@@ -12921,6 +12480,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 4096,
         },
+        "thinkingmachines/inkling-small": {
+            id: "thinkingmachines/inkling-small",
+            name: "Thinking Machines: Inkling Small",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 4096,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -13219,13 +12795,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.966,
-                output: 3.036,
-                cacheRead: 0.1794,
+                input: 0.2842,
+                output: 0.8932,
+                cacheRead: 0.05278,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 128000,
+            maxTokens: 131072,
         },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
@@ -13312,6 +12888,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "~deepseek/deepseek-v4-flash-latest": {
+            id: "~deepseek/deepseek-v4-flash-latest",
+            name: "DeepSeek V4 Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.18,
+                cacheRead: 0.018,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
             name: "Google Gemini Flash Latest",
@@ -14377,8 +13970,25 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13799999999999998,
-                output: 0.275,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-flash-0731": {
+            id: "deepseek/deepseek-v4-flash-0731",
+            name: "DeepSeek V4 Flash 0731",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.13,
+                output: 0.26,
                 cacheRead: 0.028,
                 cacheWrite: 0,
             },
@@ -14664,7 +14274,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.6,
@@ -14715,7 +14325,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.74,
                 output: 2.96,
@@ -15072,7 +14682,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
@@ -15089,7 +14699,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.15,
@@ -15157,7 +14767,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.15,
                 output: 0.15,
@@ -16160,7 +15770,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.09,
                 output: 0.3,