@opengsd/gsd-pi 1.2.0-dev.84c56d87 → 1.2.0-dev.8e6112e9

package/packages/pi-ai/dist/models.generated.js

@@ -3092,13 +3092,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.35,
-                output: 0.75,
+                input: 0.25,
+                output: 0.69,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 40960,
+            maxTokens: 32768,
+        },
+        "llama3.1-8b": {
+            id: "llama3.1-8b",
+            name: "Llama 3.1 8B",
+            api: "openai-completions",
+            provider: "cerebras",
+            baseUrl: "https://api.cerebras.ai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32000,
+            maxTokens: 8000,
         },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
@@ -3106,7 +3123,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "cerebras",
             baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 2.25,
@@ -3115,7 +3132,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 40960,
+            maxTokens: 40000,
         },
     },
     "cloudflare-ai-gateway": {
@@ -4246,26 +4263,6 @@ export const MODELS = {
         },
     },
     "github-copilot": {
-        "claude-fable-5": {
-            id: "claude-fable-5",
-            name: "Claude Fable 5",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "claude-haiku-4.5": {
             id: "claude-haiku-4.5",
             name: "Claude Haiku 4.5 (latest)",
@@ -5198,9 +5195,77 @@ export const MODELS = {
         },
     },
     "groq": {
+        "deepseek-r1-distill-llama-70b": {
+            id: "deepseek-r1-distill-llama-70b",
+            name: "DeepSeek R1 Distill Llama 70B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.75,
+                output: 0.99,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "gemma2-9b-it": {
+            id: "gemma2-9b-it",
+            name: "Gemma 2 9B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.2,
+                output: 0.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "groq/compound": {
+            id: "groq/compound",
+            name: "Compound",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "groq/compound-mini": {
+            id: "groq/compound-mini",
+            name: "Compound Mini",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "llama-3.1-8b-instant": {
             id: "llama-3.1-8b-instant",
-            name: "Llama 3.1 8B",
+            name: "Llama 3.1 8B Instant",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -5217,7 +5282,7 @@ export const MODELS = {
         },
         "llama-3.3-70b-versatile": {
             id: "llama-3.3-70b-versatile",
-            name: "Llama 3.3 70B",
+            name: "Llama 3.3 70B Versatile",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -5232,9 +5297,60 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 32768,
         },
+        "llama3-70b-8192": {
+            id: "llama3-70b-8192",
+            name: "Llama 3 70B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.59,
+                output: 0.79,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "llama3-8b-8192": {
+            id: "llama3-8b-8192",
+            name: "Llama 3 8B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.05,
+                output: 0.08,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "meta-llama/llama-4-maverick-17b-128e-instruct": {
+            id: "meta-llama/llama-4-maverick-17b-128e-instruct",
+            name: "Llama 4 Maverick 17B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "meta-llama/llama-4-scout-17b-16e-instruct": {
             id: "meta-llama/llama-4-scout-17b-16e-instruct",
-            name: "Llama 4 Scout 17B 16E",
+            name: "Llama 4 Scout 17B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -5249,6 +5365,57 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
+        "mistral-saba-24b": {
+            id: "mistral-saba-24b",
+            name: "Mistral Saba 24B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.79,
+                output: 0.79,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
+        "moonshotai/kimi-k2-instruct": {
+            id: "moonshotai/kimi-k2-instruct",
+            name: "Kimi K2 Instruct",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+        "moonshotai/kimi-k2-instruct-0905": {
+            id: "moonshotai/kimi-k2-instruct-0905",
+            name: "Kimi K2 Instruct 0905",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 16384,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -5300,9 +5467,26 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "qwen-qwq-32b": {
+            id: "qwen-qwq-32b",
+            name: "Qwen QwQ 32B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.29,
+                output: 0.39,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
         "qwen/qwen3-32b": {
             id: "qwen/qwen3-32b",
-            name: "Qwen3-32B",
+            name: "Qwen3 32B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -7497,25 +7681,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "claude-fable-5": {
-            id: "claude-fable-5",
-            name: "Claude Fable 5",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            compat: { "forceAdaptiveThinking": true },
-            reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -7689,7 +7854,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7714,25 +7879,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 128000,
         },
-        "deepseek-v4-pro": {
-            id: "deepseek-v4-pro",
-            name: "DeepSeek V4 Pro",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
-            input: ["text"],
-            cost: {
-                input: 1.74,
-                output: 3.84,
-                cacheRead: 0.145,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 384000,
-        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -8228,23 +8374,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "north-mini-code-free": {
-            id: "north-mini-code-free",
-            name: "North Mini Code 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,
-        },
         "qwen3.5-plus": {
             id: "qwen3.5-plus",
             name: "Qwen3.5 Plus",
@@ -9108,7 +9237,7 @@ export const MODELS = {
                 cacheRead: 0.135,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 163840,
             maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3.1": {
@@ -9550,12 +9679,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.35,
+                output: 0.36,
                 cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 8192,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9856,9 +9985,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 1,
-                cacheRead: 0.05,
+                input: 0.27,
+                output: 1.08,
+                cacheRead: 0.054,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -10247,13 +10376,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
-                output: 3.39,
-                cacheRead: 0.14,
+                input: 0.68,
+                output: 3.41,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
+        },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
         },
         "nex-agi/nex-n2-pro:free": {
             id: "nex-agi/nex-n2-pro:free",
@@ -10425,6 +10571,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
+        "nvidia/nemotron-nano-9b-v2": {
+            id: "nvidia/nemotron-nano-9b-v2",
+            name: "NVIDIA: Nemotron Nano 9B V2",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.04,
+                output: 0.16,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
         "nvidia/nemotron-nano-9b-v2:free": {
             id: "nvidia/nemotron-nano-9b-v2:free",
             name: "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -12163,13 +12326,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
-                cacheRead: 0.05,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12248,10 +12411,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
-                output: 1.28,
-                cacheRead: 0.064,
-                cacheWrite: 0.4,
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.08,
+                cacheWrite: 0.5,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12511,6 +12674,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "z-ai/glm-4-32b": {
+            id: "z-ai/glm-4-32b",
+            name: "Z.ai: GLM 4 32B ",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.1,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
         "z-ai/glm-4.5": {
             id: "z-ai/glm-4.5",
             name: "Z.ai: GLM 4.5",
@@ -12545,6 +12725,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131070,
         },
+        "z-ai/glm-4.5-air:free": {
+            id: "z-ai/glm-4.5-air:free",
+            name: "Z.ai: GLM 4.5 Air (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 96000,
+        },
         "z-ai/glm-4.5v": {
             id: "z-ai/glm-4.5v",
             name: "Z.ai: GLM 4.5V",
@@ -12590,11 +12787,11 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.9,
-                cacheRead: 0.055,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 32768,
+            maxTokens: 24000,
         },
         "z-ai/glm-4.7": {
             id: "z-ai/glm-4.7",
@@ -12661,7 +12858,7 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 202752,
             maxTokens: 131072,
         },
         "z-ai/glm-5.1": {
@@ -12681,22 +12878,22 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 4096,
         },
-        "~anthropic/claude-fable-latest": {
-            id: "~anthropic/claude-fable-latest",
-            name: "Anthropic: Claude Fable Latest",
+        "z-ai/glm-5v-turbo": {
+            id: "z-ai/glm-5v-turbo",
+            name: "Z.ai: GLM 5V Turbo",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
         "~anthropic/claude-haiku-latest": {
             id: "~anthropic/claude-haiku-latest",
@@ -12792,13 +12989,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
-                output: 3.39,
-                cacheRead: 0.14,
+                input: 0.68,
+                output: 3.41,
+                cacheRead: 0.34,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12836,9 +13033,9 @@ export const MODELS = {
         },
     },
     "together": {
-        "MiniMaxAI/MiniMax-M2.7": {
-            id: "MiniMaxAI/MiniMax-M2.7",
-            name: "MiniMax-M2.7",
+        "MiniMaxAI/MiniMax-M2.5": {
+            id: "MiniMaxAI/MiniMax-M2.5",
+            name: "MiniMax-M2.5",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -12852,26 +13049,27 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 204800,
             maxTokens: 131072,
         },
-        "Qwen/Qwen2.5-7B-Instruct-Turbo": {
-            id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
-            name: "Qwen 2.5 7B Instruct Turbo",
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
             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 },
-            reasoning: false,
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
             input: ["text"],
             cost: {
                 input: 0.3,
-                output: 0.3,
-                cacheRead: 0,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 32768,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
         "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
             id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
@@ -12879,8 +13077,9 @@ export const MODELS = {
             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 },
-            reasoning: false,
+            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: 0.2,
@@ -12891,28 +13090,46 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "Qwen/Qwen3.5-397B-A17B": {
-            id: "Qwen/Qwen3.5-397B-A17B",
-            name: "Qwen3.5 397B A17B",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+            id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
+            name: "Qwen3 Coder 480B A35B Instruct",
+            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 },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3-Coder-Next-FP8": {
+            id: "Qwen/Qwen3-Coder-Next-FP8",
+            name: "Qwen3 Coder Next FP8",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.6,
-                output: 3.6,
+                input: 0.5,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 130000,
+            maxTokens: 262144,
         },
-        "Qwen/Qwen3.5-9B": {
-            id: "Qwen/Qwen3.5-9B",
-            name: "Qwen3.5 9B",
+        "Qwen/Qwen3.5-397B-A17B": {
+            id: "Qwen/Qwen3.5-397B-A17B",
+            name: "Qwen3.5 397B A17B",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -12921,13 +13138,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.17,
-                output: 0.25,
+                input: 0.6,
+                output: 3.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 130000,
         },
         "Qwen/Qwen3.6-Plus": {
             id: "Qwen/Qwen3.6-Plus",
@@ -12954,8 +13171,9 @@ export const MODELS = {
             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 },
-            reasoning: false,
+            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: 2.5,
@@ -12966,6 +13184,44 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 500000,
         },
+        "deepseek-ai/DeepSeek-V3": {
+            id: "deepseek-ai/DeepSeek-V3",
+            name: "DeepSeek-V3",
+            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: 1.25,
+                output: 1.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "deepseek-ai/DeepSeek-V3-1": {
+            id: "deepseek-ai/DeepSeek-V3-1",
+            name: "DeepSeek V3.1",
+            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: 1.7,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "deepseek-ai/DeepSeek-V4-Pro": {
             id: "deepseek-ai/DeepSeek-V4-Pro",
             name: "DeepSeek V4 Pro",
@@ -12977,8 +13233,8 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
+                input: 2.1,
+                output: 4.4,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -13014,8 +13270,8 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.39,
-                output: 0.97,
+                input: 0.2,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13040,6 +13296,25 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "moonshotai/Kimi-K2.5": {
+            id: "moonshotai/Kimi-K2.5",
+            name: "Kimi K2.5",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 2.8,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "moonshotai/Kimi-K2.6": {
             id: "moonshotai/Kimi-K2.6",
             name: "Kimi K2.6",
@@ -13097,44 +13372,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "openai/gpt-oss-20b": {
-            id: "openai/gpt-oss-20b",
-            name: "GPT OSS 20B",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null },
-            input: ["text"],
-            cost: {
-                input: 0.05,
-                output: 0.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "zai-org/GLM-5": {
-            id: "zai-org/GLM-5",
-            name: "GLM-5",
-            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: 1,
-                output: 3.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
         "zai-org/GLM-5.1": {
             id: "zai-org/GLM-5.1",
             name: "GLM-5.1",
@@ -14712,6 +14949,40 @@ export const MODELS = {
             contextWindow: 262114,
             maxTokens: 262114,
         },
+        "moonshotai/kimi-k2-thinking-turbo": {
+            id: "moonshotai/kimi-k2-thinking-turbo",
+            name: "Kimi K2 Thinking Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 262114,
+            maxTokens: 262114,
+        },
+        "moonshotai/kimi-k2-turbo": {
+            id: "moonshotai/kimi-k2-turbo",
+            name: "Kimi K2 Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 16384,
+        },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -16212,24 +16483,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "mimo-v2.5-pro-ultraspeed": {
-            id: "mimo-v2.5-pro-ultraspeed",
-            name: "MiMo-V2.5-Pro-UltraSpeed",
-            api: "openai-completions",
-            provider: "xiaomi",
-            baseUrl: "https://api.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.305,
-                output: 2.61,
-                cacheRead: 0.0108,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
     },
     "xiaomi-token-plan-ams": {
         "mimo-v2-flash": {
@@ -16322,24 +16575,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "mimo-v2.5-pro-ultraspeed": {
-            id: "mimo-v2.5-pro-ultraspeed",
-            name: "MiMo-V2.5-Pro-UltraSpeed",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-ams",
-            baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.305,
-                output: 2.61,
-                cacheRead: 0.0108,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
     },
     "xiaomi-token-plan-cn": {
         "mimo-v2-flash": {
@@ -16432,24 +16667,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "mimo-v2.5-pro-ultraspeed": {
-            id: "mimo-v2.5-pro-ultraspeed",
-            name: "MiMo-V2.5-Pro-UltraSpeed",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-cn",
-            baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.305,
-                output: 2.61,
-                cacheRead: 0.0108,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
     },
     "xiaomi-token-plan-sgp": {
         "mimo-v2-flash": {
@@ -16542,24 +16759,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "mimo-v2.5-pro-ultraspeed": {
-            id: "mimo-v2.5-pro-ultraspeed",
-            name: "MiMo-V2.5-Pro-UltraSpeed",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-sgp",
-            baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.305,
-                output: 2.61,
-                cacheRead: 0.0108,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
     },
     "zai": {
         "glm-4.5-air": {