@hyperspaceng/neural-ai 0.68.1 → 0.69.1

package/dist/models.generated.js

@@ -325,6 +325,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "au.anthropic.claude-opus-4-6-v1": {
+            id: "au.anthropic.claude-opus-4-6-v1",
+            name: "AU Anthropic Claude Opus 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 16.5,
+                output: 82.5,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "au.anthropic.claude-sonnet-4-6": {
+            id: "au.anthropic.claude-sonnet-4-6",
+            name: "AU Anthropic Claude Sonnet 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "deepseek.r1-v1:0": {
             id: "deepseek.r1-v1:0",
             name: "DeepSeek-R1",
@@ -381,7 +415,7 @@ export const MODELS = {
             name: "Claude Haiku 4.5 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -398,7 +432,7 @@ export const MODELS = {
             name: "Claude Opus 4.5 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -415,7 +449,7 @@ export const MODELS = {
             name: "Claude Opus 4.6 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -432,7 +466,7 @@ export const MODELS = {
             name: "Claude Opus 4.7 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -449,7 +483,7 @@ export const MODELS = {
             name: "Claude Sonnet 4 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -466,7 +500,7 @@ export const MODELS = {
             name: "Claude Sonnet 4.5 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -483,7 +517,7 @@ export const MODELS = {
             name: "Claude Sonnet 4.6 (EU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -2488,6 +2522,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 130000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -2695,6 +2746,314 @@ export const MODELS = {
             maxTokens: 40000,
         },
     },
+    "fireworks": {
+        "accounts/fireworks/models/deepseek-v3p1": {
+            id: "accounts/fireworks/models/deepseek-v3p1",
+            name: "DeepSeek V3.1",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.56,
+                output: 1.68,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 163840,
+            maxTokens: 163840,
+        },
+        "accounts/fireworks/models/deepseek-v3p2": {
+            id: "accounts/fireworks/models/deepseek-v3p2",
+            name: "DeepSeek V3.2",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.56,
+                output: 1.68,
+                cacheRead: 0.28,
+                cacheWrite: 0,
+            },
+            contextWindow: 160000,
+            maxTokens: 160000,
+        },
+        "accounts/fireworks/models/glm-4p5": {
+            id: "accounts/fireworks/models/glm-4p5",
+            name: "GLM 4.5",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.55,
+                output: 2.19,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/glm-4p5-air": {
+            id: "accounts/fireworks/models/glm-4p5-air",
+            name: "GLM 4.5 Air",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/glm-4p7": {
+            id: "accounts/fireworks/models/glm-4p7",
+            name: "GLM 4.7",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.2,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 198000,
+            maxTokens: 198000,
+        },
+        "accounts/fireworks/models/glm-5": {
+            id: "accounts/fireworks/models/glm-5",
+            name: "GLM 5",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3.2,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/glm-5p1": {
+            id: "accounts/fireworks/models/glm-5p1",
+            name: "GLM 5.1",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/models/gpt-oss-120b": {
+            id: "accounts/fireworks/models/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "accounts/fireworks/models/gpt-oss-20b": {
+            id: "accounts/fireworks/models/gpt-oss-20b",
+            name: "GPT OSS 20B",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.05,
+                output: 0.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "accounts/fireworks/models/kimi-k2-instruct": {
+            id: "accounts/fireworks/models/kimi-k2-instruct",
+            name: "Kimi K2 Instruct",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "accounts/fireworks/models/kimi-k2-thinking": {
+            id: "accounts/fireworks/models/kimi-k2-thinking",
+            name: "Kimi K2 Thinking",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "accounts/fireworks/models/kimi-k2p5": {
+            id: "accounts/fireworks/models/kimi-k2p5",
+            name: "Kimi K2.5",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+        "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",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
+        "accounts/fireworks/models/minimax-m2p1": {
+            id: "accounts/fireworks/models/minimax-m2p1",
+            name: "MiniMax-M2.1",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 200000,
+        },
+        "accounts/fireworks/models/minimax-m2p5": {
+            id: "accounts/fireworks/models/minimax-m2p5",
+            name: "MiniMax-M2.5",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
+        "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",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
+        "accounts/fireworks/models/qwen3p6-plus": {
+            id: "accounts/fireworks/models/qwen3p6-plus",
+            name: "Qwen 3.6 Plus",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "accounts/fireworks/routers/kimi-k2p5-turbo": {
+            id: "accounts/fireworks/routers/kimi-k2p5-turbo",
+            name: "Kimi K2.5 Turbo (firepass)",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
+    },
     "github-copilot": {
         "claude-haiku-4.5": {
             id: "claude-haiku-4.5",
@@ -3580,8 +3939,8 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
-        "gemma-4-26b-it": {
-            id: "gemma-4-26b-it",
+        "gemma-4-26b-a4b-it": {
+            id: "gemma-4-26b-a4b-it",
             name: "Gemma 4 26B",
             api: "google-generative-ai",
             provider: "google",
@@ -3856,6 +4215,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65535,
         },
+        "gemini-3.1-flash-lite-preview": {
+            id: "gemini-3.1-flash-lite-preview",
+            name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65535,
+        },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
             name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
@@ -5899,6 +6275,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 130000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -6668,6 +7061,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "hy3-preview-free": {
+            id: "hy3-preview-free",
+            name: "Hy3 preview Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 64000,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -6906,7 +7316,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "mimo-v2-pro": {
             id: "mimo-v2-pro",
@@ -6923,7 +7333,41 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 64000,
+            maxTokens: 128000,
+        },
+        "mimo-v2.5": {
+            id: "mimo-v2.5",
+            name: "MiMo V2.5",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 128000,
+        },
+        "mimo-v2.5-pro": {
+            id: "mimo-v2.5-pro",
+            name: "MiMo V2.5 Pro",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 128000,
         },
         "minimax-m2.5": {
             id: "minimax-m2.5",
@@ -7369,17 +7813,17 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "arcee-ai/trinity-large-preview:free": {
-            id: "arcee-ai/trinity-large-preview:free",
-            name: "Arcee AI: Trinity Large Preview (free)",
+        "arcee-ai/trinity-large-preview": {
+            id: "arcee-ai/trinity-large-preview",
+            name: "Arcee AI: Trinity Large Preview",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.15,
+                output: 0.44999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -7707,7 +8151,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 32768,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -7726,6 +8170,40 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 65536,
         },
+        "deepseek/deepseek-v4-flash": {
+            id: "deepseek/deepseek-v4-flash",
+            name: "DeepSeek: DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro": {
+            id: "deepseek/deepseek-v4-pro",
+            name: "DeepSeek: DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "essentialai/rnj-1-instruct": {
             id: "essentialai/rnj-1-instruct",
             name: "EssentialAI: Rnj 1 Instruct",
@@ -7956,13 +8434,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.07,
-                output: 0.35,
-                cacheRead: 0.04,
+                input: 0.06,
+                output: 0.33,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -7992,7 +8470,7 @@ export const MODELS = {
             cost: {
                 input: 0.13,
                 output: 0.38,
-                cacheRead: 0.019999999499999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -8032,6 +8510,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
+        "inclusionai/ling-2.6-1t:free": {
+            id: "inclusionai/ling-2.6-1t:free",
+            name: "inclusionAI: Ling-2.6-1T (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "inclusionai/ling-2.6-flash:free": {
             id: "inclusionai/ling-2.6-flash:free",
             name: "inclusionAI: Ling-2.6-flash (free)",
@@ -8229,12 +8724,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.15,
-                output: 1.2,
-                cacheRead: 0.075,
+                output: 1.15,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 65536,
+            maxTokens: 4096,
         },
         "minimax/minimax-m2.5:free": {
             id: "minimax/minimax-m2.5:free",
@@ -8500,13 +8995,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.04,
+                input: 0.01,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -8721,13 +9216,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.7999999999999999,
-                output: 3.5,
-                cacheRead: 0.19999999999999998,
+                input: 0.7448,
+                output: 4.655,
+                cacheRead: 0.1463,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 256000,
+            maxTokens: 65536,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10064,13 +10559,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.6,
+                input: 0.14950000000000002,
+                output: 1.495,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -10701,6 +11196,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "tencent/hy3-preview:free": {
+            id: "tencent/hy3-preview:free",
+            name: "Tencent: Hy3 preview (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: 262144,
+        },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
             name: "TheDrummer: Rocinante 12B",
@@ -10973,6 +11485,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "xiaomi/mimo-v2.5": {
+            id: "xiaomi/mimo-v2.5",
+            name: "Xiaomi: MiMo-V2.5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "xiaomi/mimo-v2.5-pro": {
+            id: "xiaomi/mimo-v2.5-pro",
+            name: "Xiaomi: MiMo-V2.5-Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
             name: "Z.ai: GLM 4 32B ",
@@ -11497,7 +12043,7 @@ export const MODELS = {
                 input: 0.5,
                 output: 3,
                 cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
+                cacheWrite: 0.625,
             },
             contextWindow: 1000000,
             maxTokens: 64000,
@@ -11876,6 +12422,40 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "deepseek/deepseek-v4-flash": {
+            id: "deepseek/deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.014,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro": {
+            id: "deepseek/deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "google/gemini-2.0-flash": {
             id: "google/gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -13619,9 +14199,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.29,
-                cacheRead: 0.045,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13838,15 +14418,15 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.4,
                 output: 4.4,
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 202752,
+            contextWindow: 202800,
+            maxTokens: 64000,
         },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",