vtcode_config/models/model_id.rs
1use serde::{Deserialize, Serialize};
2
3mod as_str;
4mod capabilities;
5mod collection;
6mod defaults;
7mod description;
8mod display;
9mod format;
10mod openrouter;
11mod parse;
12mod provider;
13
14/// Centralized enum for all supported model identifiers
15#[cfg_attr(feature = "schema", derive(schemars::JsonSchema))]
16#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Hash, Serialize, Deserialize)]
17pub enum ModelId {
18 // Gemini models
19 /// Gemini 2.5 Flash Preview - Latest fast model with advanced capabilities
20 #[default]
21 Gemini25FlashPreview,
22 /// Gemini 2.5 Flash - Legacy alias for flash preview
23 Gemini25Flash,
24 /// Gemini 2.5 Flash Lite - Legacy alias for flash preview (lite)
25 Gemini25FlashLite,
26 /// Gemini 2.5 Pro - Latest most capable Gemini model
27 Gemini25Pro,
28 /// Gemini 3 Pro Preview - Preview of next-generation Gemini model
29 Gemini3ProPreview,
30
31 // OpenAI models
32 /// GPT-5 - Latest most capable OpenAI model (2025-08-07)
33 GPT5,
34 /// GPT-5 Codex - Code-focused GPT-5 variant using the Responses API
35 GPT5Codex,
36 /// GPT-5 Mini - Latest efficient OpenAI model (2025-08-07)
37 GPT5Mini,
38 /// GPT-5 Nano - Latest most cost-effective OpenAI model (2025-08-07)
39 GPT5Nano,
40 /// Codex Mini Latest - Latest Codex model for code generation (2025-05-16)
41 CodexMiniLatest,
42 /// GPT-OSS 20B - OpenAI's open-source 20B parameter model using harmony
43 OpenAIGptOss20b,
44 /// GPT-OSS 120B - OpenAI's open-source 120B parameter model using harmony
45 OpenAIGptOss120b,
46
47 // Anthropic models
48 /// Claude Opus 4.5 - Latest flagship Anthropic model with exceptional reasoning (2025-11-01)
49 ClaudeOpus45,
50 /// Claude Opus 4.1 - Previous most capable Anthropic model (2025-08-05)
51 ClaudeOpus41,
52 /// Claude Sonnet 4.5 - Latest balanced Anthropic model (2025-10-15)
53 ClaudeSonnet45,
54 /// Claude Haiku 4.5 - Latest efficient Anthropic model (2025-10-15)
55 ClaudeHaiku45,
56 /// Claude Sonnet 4 - Previous balanced Anthropic model (2025-05-14)
57 ClaudeSonnet4,
58
59 // DeepSeek models
60 /// DeepSeek V3.2 Chat - Fast non-thinking mode
61 DeepSeekChat,
62 /// DeepSeek V3.2 Reasoner - Thinking mode with structured reasoning output
63 DeepSeekReasoner,
64 // Hugging Face models
65 /// DeepSeek V3.2 via Hugging Face router
66 HuggingFaceDeepseekV32,
67 /// OpenAI GPT-OSS 20B via Hugging Face router
68 HuggingFaceOpenAIGptOss20b,
69 /// OpenAI GPT-OSS 120B via Hugging Face router
70 HuggingFaceOpenAIGptOss120b,
71 /// Z.AI GLM-4.7 via Hugging Face router
72 HuggingFaceGlm47,
73 /// Z.AI GLM-4.7-Flash via Novita on Hugging Face router
74 HuggingFaceGlm47FlashNovita,
75 /// MoonshotAI Kimi K2 Thinking via Hugging Face router
76 HuggingFaceKimiK2Thinking,
77 /// MiniMax M2.1 via Novita on Hugging Face router - Enhanced reasoning
78 HuggingFaceMinimaxM21Novita,
79 /// DeepSeek V3.2 via Novita on Hugging Face router
80 HuggingFaceDeepseekV32Novita,
81 /// Xiaomi MiMo-V2-Flash via Novita on Hugging Face router
82 HuggingFaceXiaomiMimoV2FlashNovita,
83
84 // xAI models
85 /// Grok-4 - Flagship xAI model with advanced reasoning
86 XaiGrok4,
87 /// Grok-4 Mini - Efficient xAI model variant
88 XaiGrok4Mini,
89 /// Grok-4 Code - Code-focused Grok deployment
90 XaiGrok4Code,
91 /// Grok-4 Code Latest - Latest Grok code model with enhanced reasoning tools
92 XaiGrok4CodeLatest,
93 /// Grok-4 Vision - Multimodal Grok model
94 XaiGrok4Vision,
95
96 // Z.AI models
97 /// GLM-4-Plus - Flagship GLM model with top-tier reasoning
98 ZaiGlm4Plus,
99 /// GLM-4-Plus Deep Thinking - Flagship GLM with forced reasoning
100 ZaiGlm4PlusDeepThinking,
101 /// GLM-4.7 - Latest flagship GLM reasoning model
102 ZaiGlm47,
103 /// GLM-4.7 Deep Thinking - GLM-4.7 with forced reasoning
104 ZaiGlm47DeepThinking,
105 /// GLM-4.7 Flash - Lightweight GLM-4.7 model optimized for agentic coding
106 ZaiGlm47Flash,
107 /// GLM-4.6 - Previous flagship GLM reasoning model
108 ZaiGlm46,
109 /// GLM-4.6 Deep Thinking - GLM-4.6 with forced reasoning
110 ZaiGlm46DeepThinking,
111 /// GLM-4.6V - Vision-capable GLM release
112 ZaiGlm46V,
113 /// GLM-4.6V-Flash - Latency-optimised vision GLM
114 ZaiGlm46VFlash,
115 /// GLM-4.6V-FlashX - Hybrid vision GLM variant
116 ZaiGlm46VFlashX,
117 /// GLM-4.5 - Balanced GLM release for general tasks
118 ZaiGlm45,
119 /// GLM-4.5 Deep Thinking - GLM-4.5 with forced reasoning
120 ZaiGlm45DeepThinking,
121 /// GLM-4.5-Air - Efficient GLM variant
122 ZaiGlm45Air,
123 /// GLM-4.5-X - Enhanced capability GLM variant
124 ZaiGlm45X,
125 /// GLM-4.5-AirX - Hybrid efficient GLM variant
126 ZaiGlm45Airx,
127 /// GLM-4.5-Flash - Low-latency GLM variant
128 ZaiGlm45Flash,
129 /// GLM-4.5V - Vision-capable GLM release
130 ZaiGlm45V,
131 /// GLM-4-32B-0414-128K - Legacy long-context GLM deployment
132 ZaiGlm432b0414128k,
133
134 // Ollama models
135 /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
136 OllamaGptOss20b,
137 /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
138 OllamaGptOss20bCloud,
139 /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
140 OllamaGptOss120bCloud,
141 /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
142 OllamaQwen317b,
143 /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
144 OllamaDeepseekV32Cloud,
145 /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
146 OllamaQwen3Next80bCloud,
147 /// Mistral Large 3 675B Cloud - Mistral Large 3 reasoning model via Ollama Cloud
148 OllamaMistralLarge3675bCloud,
149 /// Kimi K2 Thinking Cloud - MoonshotAI Kimi K2 thinking model via Ollama Cloud
150 OllamaKimiK2ThinkingCloud,
151 /// Qwen3 Coder 480B Cloud - Cloud-hosted Qwen3 Coder model served via Ollama Cloud
152 OllamaQwen3Coder480bCloud,
153 /// GLM-4.6 Cloud - Cloud-hosted GLM-4.6 model served via Ollama Cloud
154 OllamaGlm46Cloud,
155 /// Gemini 3 Pro Preview Latest Cloud - Google Gemini 3 Pro Preview via Ollama Cloud
156 OllamaGemini3ProPreviewLatestCloud,
157 /// Devstral 2 123B Cloud - Mistral Devstral 2 123B model via Ollama Cloud
158 OllamaDevstral2123bCloud,
159 /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
160 OllamaMinimaxM2Cloud,
161 /// GLM-4.7 Cloud - Cloud-hosted GLM-4.7 model served via Ollama Cloud
162 OllamaGlm47Cloud,
163 /// MiniMax-M2.1 Cloud - Cloud-hosted MiniMax-M2.1 model served via Ollama Cloud
164 OllamaMinimaxM21Cloud,
165 /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
166 OllamaGemini3FlashPreviewCloud,
167 /// Nemotron-3-Nano 30B Cloud - NVIDIA Nemotron-3-Nano 30B via Ollama Cloud
168 OllamaNemotron3Nano30bCloud,
169
170 // MiniMax models
171 /// MiniMax-M2.1 - Latest MiniMax model with enhanced code understanding and reasoning
172 MinimaxM21,
173 /// MiniMax-M2.1-lightning - Fast version of MiniMax-M2.1
174 MinimaxM21Lightning,
175 /// MiniMax-M2 - MiniMax reasoning-focused model
176 MinimaxM2,
177
178 // LM Studio models
179 /// Meta Llama 3 8B Instruct served locally via LM Studio
180 LmStudioMetaLlama38BInstruct,
181 /// Meta Llama 3.1 8B Instruct served locally via LM Studio
182 LmStudioMetaLlama318BInstruct,
183 /// Qwen2.5 7B Instruct served locally via LM Studio
184 LmStudioQwen257BInstruct,
185 /// Gemma 2 2B IT served locally via LM Studio
186 LmStudioGemma22BIt,
187 /// Gemma 2 9B IT served locally via LM Studio
188 LmStudioGemma29BIt,
189 /// Phi-3.1 Mini 4K Instruct served locally via LM Studio
190 LmStudioPhi31Mini4kInstruct,
191
192 // OpenRouter models
193 /// Grok Code Fast 1 - Fast OpenRouter coding model powered by xAI Grok
194 OpenRouterGrokCodeFast1,
195 /// Grok 4 Fast - Reasoning-focused Grok endpoint with transparent traces
196 OpenRouterGrok4Fast,
197 /// Grok 4.1 Fast - Enhanced Grok 4.1 fast inference with improved reasoning
198 OpenRouterGrok41Fast,
199 /// Grok 4 - Flagship Grok 4 endpoint exposed through OpenRouter
200 OpenRouterGrok4,
201 /// GLM 4.6 - Z.AI GLM 4.6 long-context reasoning model
202 OpenRouterZaiGlm46,
203 /// Kimi K2 0905 - MoonshotAI Kimi K2 0905 MoE release optimised for coding agents
204 OpenRouterMoonshotaiKimiK20905,
205 /// Kimi K2 Thinking - MoonshotAI reasoning-tier Kimi K2 release optimized for long-horizon agents
206 OpenRouterMoonshotaiKimiK2Thinking,
207 /// Qwen3 Max - Flagship Qwen3 mixture for general reasoning
208 OpenRouterQwen3Max,
209 /// Qwen3 235B A22B - Mixture-of-experts Qwen3 235B general model
210 OpenRouterQwen3235bA22b,
211 /// Qwen3 235B A22B Instruct 2507 - Instruction-tuned Qwen3 235B A22B
212 OpenRouterQwen3235bA22b2507,
213 /// Qwen3 235B A22B Thinking 2507 - Deliberative Qwen3 235B A22B reasoning release
214 OpenRouterQwen3235bA22bThinking2507,
215 /// Qwen3 32B - Dense 32B Qwen3 deployment
216 OpenRouterQwen332b,
217 /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
218 OpenRouterQwen330bA3b,
219 /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
220 OpenRouterQwen330bA3bInstruct2507,
221 /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
222 OpenRouterQwen330bA3bThinking2507,
223 /// Qwen3 14B - Lightweight Qwen3 14B model
224 OpenRouterQwen314b,
225 /// Qwen3 8B - Compact Qwen3 8B deployment
226 OpenRouterQwen38b,
227 /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
228 OpenRouterQwen3Next80bA3bInstruct,
229 /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
230 OpenRouterQwen3Next80bA3bThinking,
231 /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
232 OpenRouterQwen3Coder,
233 /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
234 OpenRouterQwen3CoderPlus,
235 /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
236 OpenRouterQwen3CoderFlash,
237 /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
238 OpenRouterQwen3Coder30bA3bInstruct,
239 /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
240 OpenRouterDeepseekChat,
241 /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
242 OpenRouterDeepSeekV32,
243 /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
244 OpenRouterDeepseekReasoner,
245 /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
246 OpenRouterDeepSeekV32Speciale,
247 /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
248 OpenRouterDeepSeekV32Exp,
249 /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
250 OpenRouterDeepSeekChatV31,
251 /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
252 OpenRouterDeepSeekR1,
253 /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
254 OpenRouterOpenAIGptOss120b,
255 /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
256 OpenRouterOpenAIGptOss20b,
257 /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
258 OpenRouterOpenAIGpt5,
259 /// OpenAI GPT-5 Codex - OpenRouter listing for GPT-5 Codex
260 OpenRouterOpenAIGpt5Codex,
261 /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
262 OpenRouterOpenAIGpt5Chat,
263 /// OpenAI GPT-4o Search Preview - GPT-4o search preview endpoint via OpenRouter
264 OpenRouterOpenAIGpt4oSearchPreview,
265 /// OpenAI GPT-4o Mini Search Preview - GPT-4o mini search preview endpoint
266 OpenRouterOpenAIGpt4oMiniSearchPreview,
267 /// OpenAI ChatGPT-4o Latest - ChatGPT 4o latest listing via OpenRouter
268 OpenRouterOpenAIChatgpt4oLatest,
269 /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
270 OpenRouterAnthropicClaudeSonnet45,
271 /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
272 OpenRouterAnthropicClaudeHaiku45,
273 /// Claude Opus 4.1 - Anthropic Claude Opus 4.1 listing
274 OpenRouterAnthropicClaudeOpus41,
275 /// Amazon Nova 2 Lite - Amazon Nova 2 Lite model via OpenRouter
276 OpenRouterAmazonNova2LiteV1,
277 /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
278 OpenRouterMistralaiMistralLarge2512,
279 /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
280 OpenRouterNexAgiDeepseekV31NexN1,
281 /// OpenAI GPT-5.1 - OpenAI GPT-5.1 model accessed through OpenRouter
282 OpenRouterOpenAIGpt51,
283 /// OpenAI GPT-5.1-Codex - OpenRouter listing for GPT-5.1 Codex
284 OpenRouterOpenAIGpt51Codex,
285 /// OpenAI GPT-5.1-Codex-Max - OpenRouter listing for GPT-5.1 Codex Max
286 OpenRouterOpenAIGpt51CodexMax,
287 /// OpenAI GPT-5.1-Codex-Mini - OpenRouter listing for GPT-5.1 Codex Mini
288 OpenRouterOpenAIGpt51CodexMini,
289 /// OpenAI GPT-5.1 Chat - Chat optimised GPT-5.1 endpoint without tool use
290 OpenRouterOpenAIGpt51Chat,
291 /// OpenAI GPT-5.2 - OpenAI GPT-5.2 model accessed through OpenRouter
292 OpenRouterOpenAIGpt52,
293 /// OpenAI GPT-5.2 Chat - Chat optimised GPT-5.2 endpoint without tool use
294 OpenRouterOpenAIGpt52Chat,
295 /// OpenAI GPT-5.2-Codex - OpenRouter listing for GPT-5.2 Codex
296 OpenRouterOpenAIGpt52Codex,
297 /// OpenAI GPT-5.2 Pro - Professional tier GPT-5.2 model accessed through OpenRouter
298 OpenRouterOpenAIGpt52Pro,
299 /// OpenAI o1-pro - OpenAI o1-pro advanced reasoning model via OpenRouter
300 OpenRouterOpenAIO1Pro,
301 /// GLM 4.6V - Z.AI GLM 4.6V enhanced vision model
302 OpenRouterZaiGlm46V,
303 /// GLM 4.7 - Z.AI GLM 4.7 next-generation reasoning model
304 OpenRouterZaiGlm47,
305 /// GLM 4.7 Flash - Z.AI GLM-4.7-Flash lightweight model via OpenRouter
306 OpenRouterZaiGlm47Flash,
307}