@openachieve/ai 0.78.0 → 0.79.1

package/dist/models.generated.js

@@ -1086,6 +1086,59 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "openai.gpt-5.4": {
+            id: "openai.gpt-5.4",
+            name: "GPT-5.4",
+            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: 2.75,
+                output: 16.5,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.5": {
+            id: "openai.gpt-5.5",
+            name: "GPT-5.5",
+            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: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-oss-120b": {
+            id: "openai.gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1103,6 +1156,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai.gpt-oss-20b": {
+            id: "openai.gpt-oss-20b",
+            name: "gpt-oss-20b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-20b-1:0": {
             id: "openai.gpt-oss-20b-1:0",
             name: "gpt-oss-20b",
@@ -3887,6 +3957,24 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131072,
         },
+        "accounts/fireworks/routers/kimi-k2p6-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p6-fast",
+            name: "Kimi K2.6 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
         "accounts/fireworks/routers/kimi-k2p6-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p6-turbo",
             name: "Kimi K2.6 Turbo",
@@ -6019,11 +6107,11 @@ export const MODELS = {
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
+                input: 0.4,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -6458,6 +6546,82 @@ export const MODELS = {
         },
     },
     "nvidia": {
+        "abacusai/dracarys-llama-3_1-70b-instruct": {
+            id: "abacusai/dracarys-llama-3_1-70b-instruct",
+            name: "dracarys-llama-3.1-70b-instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "deepseek-ai/deepseek-v3.1-terminus": {
+            id: "deepseek-ai/deepseek-v3.1-terminus",
+            name: "DeepSeek V3.1 Terminus",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "deepseek-ai/deepseek-v3.2": {
+            id: "deepseek-ai/deepseek-v3.2",
+            name: "DeepSeek V3.2",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 163840,
+            maxTokens: 65536,
+        },
+        "google/gemma-3-27b-it": {
+            id: "google/gemma-3-27b-it",
+            name: "Gemma-3-27B-IT",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "meta/llama-3.1-70b-instruct": {
             id: "meta/llama-3.1-70b-instruct",
             name: "Llama 3.1 70b Instruct",
@@ -6553,6 +6717,63 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "minimaxai/minimax-m2.5": {
+            id: "minimaxai/minimax-m2.5",
+            name: "MiniMax-M2.5",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "mistralai/devstral-2-123b-instruct-2512": {
+            id: "mistralai/devstral-2-123b-instruct-2512",
+            name: "Devstral-2-123B-Instruct-2512",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "mistralai/mistral-7b-instruct-v03": {
+            id: "mistralai/mistral-7b-instruct-v03",
+            name: "Mistral-7B-Instruct-v0.3",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 65536,
+            maxTokens: 65536,
+        },
         "mistralai/mistral-large-3-675b-instruct-2512": {
             id: "mistralai/mistral-large-3-675b-instruct-2512",
             name: "Mistral Large 3 675B Instruct 2512",
@@ -6591,6 +6812,101 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
+        "mistralai/mixtral-8x22b-instruct": {
+            id: "mistralai/mixtral-8x22b-instruct",
+            name: "Mistral: Mixtral 8x22B Instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 65536,
+            maxTokens: 13108,
+        },
+        "mistralai/mixtral-8x7b-instruct": {
+            id: "mistralai/mixtral-8x7b-instruct",
+            name: "Mistral: Mixtral 8x7B Instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 16384,
+        },
+        "moonshotai/kimi-k2-instruct": {
+            id: "moonshotai/kimi-k2-instruct",
+            name: "Kimi K2 Instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
+        "moonshotai/kimi-k2-instruct-0905": {
+            id: "moonshotai/kimi-k2-instruct-0905",
+            name: "Kimi K2 0905",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/kimi-k2-thinking": {
+            id: "moonshotai/kimi-k2-thinking",
+            name: "Kimi K2 Thinking",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "moonshotai/kimi-k2.6": {
             id: "moonshotai/kimi-k2.6",
             name: "Kimi K2.6",
@@ -6610,8 +6926,8 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "nvidia/llama-3.3-nemotron-super-49b-v1": {
-            id: "nvidia/llama-3.3-nemotron-super-49b-v1",
+        "nvidia/llama-3_3-nemotron-super-49b-v1": {
+            id: "nvidia/llama-3_3-nemotron-super-49b-v1",
             name: "Llama 3.3 Nemotron Super 49B v1",
             api: "openai-completions",
             provider: "nvidia",
@@ -6629,8 +6945,8 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
-            id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+        "nvidia/llama-3_3-nemotron-super-49b-v1_5": {
+            id: "nvidia/llama-3_3-nemotron-super-49b-v1_5",
             name: "Llama 3.3 Nemotron Super 49B v1.5",
             api: "openai-completions",
             provider: "nvidia",
@@ -6705,6 +7021,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "nvidia/nemotron-voicechat": {
+            id: "nvidia/nemotron-voicechat",
+            name: "nemotron-voicechat",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
         "nvidia/nvidia-nemotron-nano-9b-v2": {
             id: "nvidia/nvidia-nemotron-nano-9b-v2",
             name: "nvidia-nemotron-nano-9b-v2",
@@ -6743,6 +7078,25 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
+        "qwen/qwen2.5-coder-32b-instruct": {
+            id: "qwen/qwen2.5-coder-32b-instruct",
+            name: "Qwen2.5 Coder 32b Instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
         "qwen/qwen3-coder-480b-a35b-instruct": {
             id: "qwen/qwen3-coder-480b-a35b-instruct",
             name: "Qwen3 Coder 480B A35B Instruct",
@@ -6762,6 +7116,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 66536,
         },
+        "qwen/qwen3-next-80b-a3b-thinking": {
+            id: "qwen/qwen3-next-80b-a3b-thinking",
+            name: "Qwen3-Next-80B-A3B-Thinking",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 16384,
+        },
         "qwen/qwen3.5-122b-a10b": {
             id: "qwen/qwen3.5-122b-a10b",
             name: "Qwen3.5 122B-A10B",
@@ -6819,6 +7192,25 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 16384,
         },
+        "upstage/solar-10_7b-instruct": {
+            id: "upstage/solar-10_7b-instruct",
+            name: "solar-10.7b-instruct",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8192,
+        },
         "z-ai/glm-5.1": {
             id: "z-ai/glm-5.1",
             name: "GLM-5.1",
@@ -6838,6 +7230,25 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "z-ai/glm4.7": {
+            id: "z-ai/glm4.7",
+            name: "GLM-4.7",
+            api: "openai-completions",
+            provider: "nvidia",
+            baseUrl: "https://integrate.api.nvidia.com/v1",
+            headers: { "NVCF-POLL-SECONDS": "3600" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
     },
     "openai": {
         "gpt-4": {
@@ -8367,9 +8778,9 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "nemotron-3-super-free": {
-            id: "nemotron-3-super-free",
-            name: "Nemotron 3 Super Free",
+        "nemotron-3-ultra-free": {
+            id: "nemotron-3-ultra-free",
+            name: "Nemotron 3 Ultra Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -8381,7 +8792,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "qwen3.5-plus": {
@@ -8628,7 +9039,7 @@ export const MODELS = {
                 cacheRead: 0.05,
                 cacheWrite: 0.625,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
         "qwen3.7-max": {
@@ -8662,7 +9073,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
     },
@@ -9690,12 +10101,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.37,
-                cacheRead: 0,
+                output: 0.36,
+                cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9844,7 +10255,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.049999999999999996,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10533,6 +10944,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 262144,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "NVIDIA: Nemotron 3 Ultra",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 16384,
+        },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
             name: "NVIDIA: Nemotron 3 Ultra (free)",
@@ -11801,7 +12229,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 20000,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -12466,23 +12894,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 128000,
         },
-        "sao10k/l3-euryale-70b": {
-            id: "sao10k/l3-euryale-70b",
-            name: "Sao10k: Llama 3 Euryale 70B v2.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.48,
-                output: 1.48,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
         "sao10k/l3.1-euryale-70b": {
             id: "sao10k/l3.1-euryale-70b",
             name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -13216,7 +13627,7 @@ export const MODELS = {
         },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
-            name: "DeepSeek V3",
+            name: "DeepSeek-V3",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -13364,6 +13775,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512300,
+            maxTokens: 512300,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -15060,6 +15490,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",