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 3 Pro Preview - Preview of next-generation Gemini model
20 Gemini3ProPreview,
21 /// Gemini 3 Flash Preview - Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding
22 #[default]
23 Gemini3FlashPreview,
24
25 // OpenAI models
26 /// GPT-5 - Latest most capable OpenAI model (2025-08-07)
27 GPT5,
28 /// GPT-5.2 - Latest flagship general-purpose OpenAI model (2025-12-11)
29 GPT52,
30 /// GPT-5.2 Codex - Code-focused GPT-5.2 variant optimized for agentic coding
31 GPT52Codex,
32 /// GPT-5 Codex - Code-focused GPT-5 variant using the Responses API
33 GPT5Codex,
34 /// GPT-5 Mini - Latest efficient OpenAI model (2025-08-07)
35 GPT5Mini,
36 /// GPT-5 Nano - Latest most cost-effective OpenAI model (2025-08-07)
37 GPT5Nano,
38 /// GPT-5.1 - Enhanced latest most capable OpenAI model with improved reasoning (2025-11-14)
39 GPT51,
40 /// GPT-5.1 Codex - Code-focused GPT-5.1 variant using the Responses API
41 GPT51Codex,
42 /// GPT-5.1 Codex Max - Maximum context code-focused GPT-5.1 variant
43 GPT51CodexMax,
44 /// GPT-5.1 Mini - Enhanced efficient OpenAI model with improved capabilities (2025-11-14)
45 GPT51Mini,
46 /// Codex Mini Latest - Latest Codex model for code generation (2025-05-16)
47 CodexMiniLatest,
48 /// GPT-OSS 20B - OpenAI's open-source 20B parameter model using harmony
49 OpenAIGptOss20b,
50 /// GPT-OSS 120B - OpenAI's open-source 120B parameter model using harmony
51 OpenAIGptOss120b,
52
53 // Anthropic models
54 /// Claude Opus 4.6 - Next-gen flagship Anthropic model with extended thinking
55 ClaudeOpus46,
56 /// Claude Opus 4.5 - Latest flagship Anthropic model with exceptional reasoning (2025-11-01)
57 ClaudeOpus45,
58 /// Claude Opus 4.1 - Previous most capable Anthropic model (2025-08-05)
59 ClaudeOpus41,
60 /// Claude Sonnet 4.5 - Latest balanced Anthropic model (2025-10-15)
61 ClaudeSonnet45,
62 /// Claude Haiku 4.5 - Latest efficient Anthropic model (2025-10-15)
63 ClaudeHaiku45,
64 /// Claude Sonnet 4 - Previous balanced Anthropic model (2025-05-14)
65 ClaudeSonnet4,
66 /// Claude Opus 4 - Previous flagship model (2025-05-14)
67 ClaudeOpus4,
68 /// Claude Sonnet 3.7 - Latest Claude 3 Sonnet (2025-02-19)
69 ClaudeSonnet37,
70 /// Claude Haiku 3.5 - Latest Claude 3 Haiku (2024-10-22)
71 ClaudeHaiku35,
72
73 // DeepSeek models
74 /// DeepSeek V3.2 Chat - Fast non-thinking mode
75 DeepSeekChat,
76 /// DeepSeek V3.2 Reasoner - Thinking mode with structured reasoning output
77 DeepSeekReasoner,
78 // Hugging Face models
79 /// DeepSeek V3.2 via Hugging Face router
80 HuggingFaceDeepseekV32,
81 /// OpenAI GPT-OSS 20B via Hugging Face router
82 HuggingFaceOpenAIGptOss20b,
83 /// OpenAI GPT-OSS 120B via Hugging Face router
84 HuggingFaceOpenAIGptOss120b,
85 /// DeepSeek V3.2 via Novita on Hugging Face router
86 HuggingFaceDeepseekV32Novita,
87 /// Xiaomi MiMo-V2-Flash via Novita on Hugging Face router
88 HuggingFaceXiaomiMimoV2FlashNovita,
89 /// MiniMax M2.5 via Novita on Hugging Face router
90 HuggingFaceMinimaxM25Novita,
91 /// Z.AI GLM-5 via Novita on Hugging Face router
92 HuggingFaceGlm5Novita,
93 /// Qwen3-Coder-Next via Novita inference provider on Hugging Face router
94 HuggingFaceQwen3CoderNextNovita,
95
96 // xAI models
97 /// Grok-4 - Flagship xAI model with advanced reasoning
98 XaiGrok4,
99 /// Grok-4 Mini - Efficient xAI model variant
100 XaiGrok4Mini,
101 /// Grok-4 Code - Code-focused Grok deployment
102 XaiGrok4Code,
103 /// Grok-4 Code Latest - Latest Grok code model with enhanced reasoning tools
104 XaiGrok4CodeLatest,
105 /// Grok-4 Vision - Multimodal Grok model
106 XaiGrok4Vision,
107
108 /// GLM-5 - Flagship Z.ai foundation model for complex systems
109 ZaiGlm5,
110
111 // Moonshot models
112 /// MiniMax-M2.5 - MiniMax model served via Moonshot API
113 MoonshotMinimaxM25,
114 /// Qwen3-Coder-Next - Qwen3 Coder Next model served via Moonshot API
115 MoonshotQwen3CoderNext,
116
117 // Ollama models
118 /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
119 OllamaGptOss20b,
120 /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
121 OllamaGptOss20bCloud,
122 /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
123 OllamaGptOss120bCloud,
124 /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
125 OllamaQwen317b,
126 /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
127 OllamaDeepseekV32Cloud,
128 /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
129 OllamaQwen3Next80bCloud,
130 /// Mistral Large 3 675B Cloud - Mistral Large 3 reasoning model via Ollama Cloud
131 OllamaMistralLarge3675bCloud,
132 /// Qwen3 Coder 480B Cloud - Cloud-hosted Qwen3 Coder model served via Ollama Cloud
133 OllamaQwen3Coder480bCloud,
134 /// Gemini 3 Pro Preview Latest Cloud - Google Gemini 3 Pro Preview via Ollama Cloud
135 OllamaGemini3ProPreviewLatestCloud,
136 /// Devstral 2 123B Cloud - Mistral Devstral 2 123B model via Ollama Cloud
137 OllamaDevstral2123bCloud,
138 /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
139 OllamaMinimaxM2Cloud,
140 /// GLM-5 Cloud - Cloud-hosted GLM-5 model served via Ollama Cloud
141 OllamaGlm5Cloud,
142 /// MiniMax-M2.5 Cloud - Cloud-hosted MiniMax-M2.5 model served via Ollama Cloud
143 OllamaMinimaxM25Cloud,
144 /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
145 OllamaGemini3FlashPreviewCloud,
146 /// Nemotron-3-Nano 30B Cloud - NVIDIA Nemotron-3-Nano 30B via Ollama Cloud
147 OllamaNemotron3Nano30bCloud,
148
149 // MiniMax models
150 /// MiniMax-M2.5 - Latest MiniMax model with further improvements in reasoning and coding
151 MinimaxM25,
152 /// MiniMax-M2 - MiniMax reasoning-focused model
153 MinimaxM2,
154
155 // LM Studio models
156 /// Meta Llama 3 8B Instruct served locally via LM Studio
157 LmStudioMetaLlama38BInstruct,
158 /// Meta Llama 3.1 8B Instruct served locally via LM Studio
159 LmStudioMetaLlama318BInstruct,
160 /// Qwen2.5 7B Instruct served locally via LM Studio
161 LmStudioQwen257BInstruct,
162 /// Gemma 2 2B IT served locally via LM Studio
163 LmStudioGemma22BIt,
164 /// Gemma 2 9B IT served locally via LM Studio
165 LmStudioGemma29BIt,
166 /// Phi-3.1 Mini 4K Instruct served locally via LM Studio
167 LmStudioPhi31Mini4kInstruct,
168
169 // OpenRouter models
170 /// Grok Code Fast 1 - Fast OpenRouter coding model powered by xAI Grok
171 OpenRouterGrokCodeFast1,
172 /// Grok 4 Fast - Reasoning-focused Grok endpoint with transparent traces
173 OpenRouterGrok4Fast,
174 /// Grok 4.1 Fast - Enhanced Grok 4.1 fast inference with improved reasoning
175 OpenRouterGrok41Fast,
176 /// Grok 4 - Flagship Grok 4 endpoint exposed through OpenRouter
177 OpenRouterGrok4,
178 /// Qwen3 Max - Flagship Qwen3 mixture for general reasoning
179 OpenRouterQwen3Max,
180 /// Qwen3 235B A22B - Mixture-of-experts Qwen3 235B general model
181 OpenRouterQwen3235bA22b,
182 /// Qwen3 235B A22B Instruct 2507 - Instruction-tuned Qwen3 235B A22B
183 OpenRouterQwen3235bA22b2507,
184 /// Qwen3 235B A22B Thinking 2507 - Deliberative Qwen3 235B A22B reasoning release
185 OpenRouterQwen3235bA22bThinking2507,
186 /// Qwen3 32B - Dense 32B Qwen3 deployment
187 OpenRouterQwen332b,
188 /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
189 OpenRouterQwen330bA3b,
190 /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
191 OpenRouterQwen330bA3bInstruct2507,
192 /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
193 OpenRouterQwen330bA3bThinking2507,
194 /// Qwen3 14B - Lightweight Qwen3 14B model
195 OpenRouterQwen314b,
196 /// Qwen3 8B - Compact Qwen3 8B deployment
197 OpenRouterQwen38b,
198 /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
199 OpenRouterQwen3Next80bA3bInstruct,
200 /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
201 OpenRouterQwen3Next80bA3bThinking,
202 /// Qwen3.5-397B-A17B - Native vision-language model with linear attention and sparse MoE, 1M context window
203 OpenRouterQwen35Plus0215,
204 /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
205 OpenRouterQwen3Coder,
206 /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
207 OpenRouterQwen3CoderPlus,
208 /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
209 OpenRouterQwen3CoderFlash,
210 /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
211 OpenRouterQwen3Coder30bA3bInstruct,
212 /// Qwen3 Coder Next - Next-generation Qwen3 coding model with enhanced reasoning
213 OpenRouterQwen3CoderNext,
214 /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
215 OpenRouterDeepseekChat,
216 /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
217 OpenRouterDeepSeekV32,
218 /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
219 OpenRouterDeepseekReasoner,
220 /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
221 OpenRouterDeepSeekV32Speciale,
222 /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
223 OpenRouterDeepSeekV32Exp,
224 /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
225 OpenRouterDeepSeekChatV31,
226 /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
227 OpenRouterDeepSeekR1,
228 /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
229 OpenRouterOpenAIGptOss120b,
230 /// OpenAI gpt-oss-120b:free - Open-weight 120B reasoning model free tier via OpenRouter
231 OpenRouterOpenAIGptOss120bFree,
232 /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
233 OpenRouterOpenAIGptOss20b,
234 /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
235 OpenRouterOpenAIGpt5,
236 /// OpenAI GPT-5 Codex - OpenRouter listing for GPT-5 Codex
237 OpenRouterOpenAIGpt5Codex,
238 /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
239 OpenRouterOpenAIGpt5Chat,
240
241 /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
242 OpenRouterAnthropicClaudeSonnet45,
243 /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
244 OpenRouterAnthropicClaudeHaiku45,
245 /// Claude Opus 4.1 - Anthropic Claude Opus 4.1 listing
246 OpenRouterAnthropicClaudeOpus41,
247 /// Amazon Nova 2 Lite - Amazon Nova 2 Lite model via OpenRouter
248 OpenRouterAmazonNova2LiteV1,
249 /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
250 OpenRouterMistralaiMistralLarge2512,
251 /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
252 OpenRouterNexAgiDeepseekV31NexN1,
253 /// OpenAI GPT-5.1 - OpenAI GPT-5.1 model accessed through OpenRouter
254 OpenRouterOpenAIGpt51,
255 /// OpenAI GPT-5.1-Codex - OpenRouter listing for GPT-5.1 Codex
256 OpenRouterOpenAIGpt51Codex,
257 /// OpenAI GPT-5.1-Codex-Max - OpenRouter listing for GPT-5.1 Codex Max
258 OpenRouterOpenAIGpt51CodexMax,
259 /// OpenAI GPT-5.1-Codex-Mini - OpenRouter listing for GPT-5.1 Codex Mini
260 OpenRouterOpenAIGpt51CodexMini,
261 /// OpenAI GPT-5.1 Chat - Chat optimised GPT-5.1 endpoint without tool use
262 OpenRouterOpenAIGpt51Chat,
263 /// OpenAI GPT-5.2 - OpenAI GPT-5.2 model accessed through OpenRouter
264 OpenRouterOpenAIGpt52,
265 /// OpenAI GPT-5.2 Chat - Chat optimised GPT-5.2 endpoint without tool use
266 OpenRouterOpenAIGpt52Chat,
267 /// OpenAI GPT-5.2-Codex - OpenRouter listing for GPT-5.2 Codex
268 OpenRouterOpenAIGpt52Codex,
269 /// OpenAI GPT-5.2 Pro - Professional tier GPT-5.2 model accessed through OpenRouter
270 OpenRouterOpenAIGpt52Pro,
271 /// OpenAI o1-pro - OpenAI o1-pro advanced reasoning model via OpenRouter
272 OpenRouterOpenAIO1Pro,
273 /// Step 3.5 Flash (free) - StepFun's most capable open-source reasoning model via OpenRouter
274 OpenRouterStepfunStep35FlashFree,
275 /// GLM-5 - Z.AI GLM-5 flagship foundation model via OpenRouter
276 OpenRouterZaiGlm5,
277 /// MoonshotAI: Kimi K2 0905 - MoonshotAI Kimi K2 0905 MoE release optimised for coding agents
278 OpenRouterMoonshotaiKimiK20905,
279 /// MoonshotAI: Kimi K2 Thinking - MoonshotAI reasoning-tier Kimi K2 release optimized for long-horizon agents
280 OpenRouterMoonshotaiKimiK2Thinking,
281 /// MoonshotAI: Kimi K2.5 - MoonshotAI Kimi K2.5 multimodal model with long-context and reasoning capabilities via OpenRouter
282 OpenRouterMoonshotaiKimiK25,
283 /// MiniMax-M2.5 - MiniMax flagship model via OpenRouter
284 OpenRouterMinimaxM25,
285}