feat(ai): complete models runtime migration

2026-06-23 15:29:17 +02:00
parent 470a4736a3
commit 129eb460cd
47 changed files with 1502 additions and 576 deletions
@@ -4,6 +4,24 @@
 import type { Model } from "../types.ts";

 export const HUGGINGFACE_MODELS = {
+	"MiniMaxAI/MiniMax-M2": {
+		id: "MiniMaxAI/MiniMax-M2",
+		name: "MiniMax-M2",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.3,
+			output: 1.2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 204800,
+		maxTokens: 128000,
+	} satisfies Model<"openai-completions">,
 	"MiniMaxAI/MiniMax-M2.1": {
 		id: "MiniMaxAI/MiniMax-M2.1",
 		name: "MiniMax-M2.1",
@@ -58,6 +76,42 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 204800,
 		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
+	"MiniMaxAI/MiniMax-M3": {
+		id: "MiniMaxAI/MiniMax-M3",
+		name: "MiniMax-M3",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.3,
+			output: 1.2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 524288,
+		maxTokens: 128000,
+	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3-235B-A22B": {
+		id: "Qwen/Qwen3-235B-A22B",
+		name: "Qwen3 235B-A22B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.2,
+			output: 0.8,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 40960,
+		maxTokens: 16384,
+	} satisfies Model<"openai-completions">,
 	"Qwen/Qwen3-235B-A22B-Thinking-2507": {
 		id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
 		name: "Qwen3-235B-A22B-Thinking-2507",
@@ -76,6 +130,42 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3-32B": {
+		id: "Qwen/Qwen3-32B",
+		name: "Qwen3 32B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.29,
+			output: 0.59,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 16384,
+	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
+		id: "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+		name: "Qwen3-Coder 30B-A3B Instruct",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: false,
+		input: ["text"],
+		cost: {
+			input: 0.07,
+			output: 0.26,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
 	"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
 		id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
 		name: "Qwen3-Coder-480B-A35B-Instruct",
@@ -148,6 +238,60 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3.5-122B-A10B": {
+		id: "Qwen/Qwen3.5-122B-A10B",
+		name: "Qwen3.5 122B-A10B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.4,
+			output: 3.2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3.5-27B": {
+		id: "Qwen/Qwen3.5-27B",
+		name: "Qwen3.5 27B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.3,
+			output: 2.4,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3.5-35B-A3B": {
+		id: "Qwen/Qwen3.5-35B-A3B",
+		name: "Qwen3.5 35B-A3B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.25,
+			output: 2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
 	"Qwen/Qwen3.5-397B-A17B": {
 		id: "Qwen/Qwen3.5-397B-A17B",
 		name: "Qwen3.5-397B-A17B",
@@ -166,6 +310,42 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 32768,
 	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3.5-9B": {
+		id: "Qwen/Qwen3.5-9B",
+		name: "Qwen3.5 9B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.17,
+			output: 0.25,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
+	"Qwen/Qwen3.6-35B-A3B": {
+		id: "Qwen/Qwen3.6-35B-A3B",
+		name: "Qwen3.6 35B-A3B",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.15,
+			output: 0.95,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 65536,
+	} satisfies Model<"openai-completions">,
 	"XiaomiMiMo/MiMo-V2-Flash": {
 		id: "XiaomiMiMo/MiMo-V2-Flash",
 		name: "MiMo-V2-Flash",
@@ -184,6 +364,24 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 4096,
 	} satisfies Model<"openai-completions">,
+	"deepseek-ai/DeepSeek-R1": {
+		id: "deepseek-ai/DeepSeek-R1",
+		name: "DeepSeek-R1",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.7,
+			output: 2.5,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 64000,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
 	"deepseek-ai/DeepSeek-R1-0528": {
 		id: "deepseek-ai/DeepSeek-R1-0528",
 		name: "DeepSeek-R1-0528",
@@ -220,6 +418,24 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 163840,
 		maxTokens: 65536,
 	} satisfies Model<"openai-completions">,
+	"deepseek-ai/DeepSeek-V4-Flash": {
+		id: "deepseek-ai/DeepSeek-V4-Flash",
+		name: "DeepSeek V4 Flash",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.14,
+			output: 0.28,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 1048576,
+		maxTokens: 384000,
+	} satisfies Model<"openai-completions">,
 	"deepseek-ai/DeepSeek-V4-Pro": {
 		id: "deepseek-ai/DeepSeek-V4-Pro",
 		name: "DeepSeek V4 Pro",
@@ -238,6 +454,60 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 1048576,
 		maxTokens: 393216,
 	} satisfies Model<"openai-completions">,
+	"google/gemma-4-26B-A4B-it": {
+		id: "google/gemma-4-26B-A4B-it",
+		name: "Gemma 4 26B A4B IT",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.13,
+			output: 0.4,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
+	"google/gemma-4-31B-it": {
+		id: "google/gemma-4-31B-it",
+		name: "Gemma 4 31B IT",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.14,
+			output: 0.4,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 32768,
+	} satisfies Model<"openai-completions">,
+	"meta-llama/Llama-3.3-70B-Instruct": {
+		id: "meta-llama/Llama-3.3-70B-Instruct",
+		name: "Llama-3.3-70B-Instruct",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: false,
+		input: ["text"],
+		cost: {
+			input: 0.59,
+			output: 0.79,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 4096,
+	} satisfies Model<"openai-completions">,
 	"moonshotai/Kimi-K2-Instruct": {
 		id: "moonshotai/Kimi-K2-Instruct",
 		name: "Kimi-K2-Instruct",
@@ -328,6 +598,114 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 262144,
 	} satisfies Model<"openai-completions">,
+	"moonshotai/Kimi-K2.7-Code": {
+		id: "moonshotai/Kimi-K2.7-Code",
+		name: "Kimi K2.7 Code",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.95,
+			output: 4,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 262144,
+	} satisfies Model<"openai-completions">,
+	"stepfun-ai/Step-3.5-Flash": {
+		id: "stepfun-ai/Step-3.5-Flash",
+		name: "Step 3.5 Flash",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.1,
+			output: 0.3,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 256000,
+	} satisfies Model<"openai-completions">,
+	"zai-org/GLM-4.5": {
+		id: "zai-org/GLM-4.5",
+		name: "GLM-4.5",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.6,
+			output: 2.2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 98304,
+	} satisfies Model<"openai-completions">,
+	"zai-org/GLM-4.5-Air": {
+		id: "zai-org/GLM-4.5-Air",
+		name: "GLM-4.5-Air",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.13,
+			output: 0.85,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 131072,
+		maxTokens: 98304,
+	} satisfies Model<"openai-completions">,
+	"zai-org/GLM-4.5V": {
+		id: "zai-org/GLM-4.5V",
+		name: "GLM-4.5V",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 0.6,
+			output: 1.8,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 65536,
+		maxTokens: 16384,
+	} satisfies Model<"openai-completions">,
+	"zai-org/GLM-4.6": {
+		id: "zai-org/GLM-4.6",
+		name: "GLM-4.6",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.55,
+			output: 2.2,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 204800,
+		maxTokens: 131072,
+	} satisfies Model<"openai-completions">,
 	"zai-org/GLM-4.7": {
 		id: "zai-org/GLM-4.7",
 		name: "GLM-4.7",
@@ -400,4 +778,22 @@ export const HUGGINGFACE_MODELS = {
 		contextWindow: 202752,
 		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
+	"zai-org/GLM-5.2": {
+		id: "zai-org/GLM-5.2",
+		name: "GLM-5.2",
+		api: "openai-completions",
+		provider: "huggingface",
+		baseUrl: "https://router.huggingface.co/v1",
+		compat: {"supportsDeveloperRole":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 1.4,
+			output: 4.4,
+			cacheRead: 0,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 131072,
+	} satisfies Model<"openai-completions">,
 } as const;