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    /// MoonshotAI Kimi K2.5 via Novita on Hugging Face router
78    HuggingFaceKimiK25Novita,
79    /// MiniMax M2.1 via Novita on Hugging Face router - Enhanced reasoning
80    HuggingFaceMinimaxM21Novita,
81    /// DeepSeek V3.2 via Novita on Hugging Face router
82    HuggingFaceDeepseekV32Novita,
83    /// Xiaomi MiMo-V2-Flash via Novita on Hugging Face router
84    HuggingFaceXiaomiMimoV2FlashNovita,
85
86    // xAI models
87    /// Grok-4 - Flagship xAI model with advanced reasoning
88    XaiGrok4,
89    /// Grok-4 Mini - Efficient xAI model variant
90    XaiGrok4Mini,
91    /// Grok-4 Code - Code-focused Grok deployment
92    XaiGrok4Code,
93    /// Grok-4 Code Latest - Latest Grok code model with enhanced reasoning tools
94    XaiGrok4CodeLatest,
95    /// Grok-4 Vision - Multimodal Grok model
96    XaiGrok4Vision,
97
98    // Z.AI models
99    /// GLM-4-Plus - Flagship GLM model with top-tier reasoning
100    ZaiGlm4Plus,
101    /// GLM-4-Plus Deep Thinking - Flagship GLM with forced reasoning
102    ZaiGlm4PlusDeepThinking,
103    /// GLM-4.7 - Latest flagship GLM reasoning model
104    ZaiGlm47,
105    /// GLM-4.7 Deep Thinking - GLM-4.7 with forced reasoning
106    ZaiGlm47DeepThinking,
107    /// GLM-4.7 Flash - Lightweight GLM-4.7 model optimized for agentic coding
108    ZaiGlm47Flash,
109    /// GLM-4.6 - Previous flagship GLM reasoning model
110    ZaiGlm46,
111    /// GLM-4.6 Deep Thinking - GLM-4.6 with forced reasoning
112    ZaiGlm46DeepThinking,
113    /// GLM-4.6V - Vision-capable GLM release
114    ZaiGlm46V,
115    /// GLM-4.6V-Flash - Latency-optimised vision GLM
116    ZaiGlm46VFlash,
117    /// GLM-4.6V-FlashX - Hybrid vision GLM variant
118    ZaiGlm46VFlashX,
119    /// GLM-4.5 - Balanced GLM release for general tasks
120    ZaiGlm45,
121    /// GLM-4.5 Deep Thinking - GLM-4.5 with forced reasoning
122    ZaiGlm45DeepThinking,
123    /// GLM-4.5-Air - Efficient GLM variant
124    ZaiGlm45Air,
125    /// GLM-4.5-X - Enhanced capability GLM variant
126    ZaiGlm45X,
127    /// GLM-4.5-AirX - Hybrid efficient GLM variant
128    ZaiGlm45Airx,
129    /// GLM-4.5-Flash - Low-latency GLM variant
130    ZaiGlm45Flash,
131    /// GLM-4.5V - Vision-capable GLM release
132    ZaiGlm45V,
133    /// GLM-4-32B-0414-128K - Legacy long-context GLM deployment
134    ZaiGlm432b0414128k,
135
136    // Moonshot models
137    /// Kimi K2.5 - Versatile multimodal model with reasoning support
138    MoonshotKimiK25,
139
140    // Ollama models
141    /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
142    OllamaGptOss20b,
143    /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
144    OllamaGptOss20bCloud,
145    /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
146    OllamaGptOss120bCloud,
147    /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
148    OllamaQwen317b,
149    /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
150    OllamaDeepseekV32Cloud,
151    /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
152    OllamaQwen3Next80bCloud,
153    /// Mistral Large 3 675B Cloud - Mistral Large 3 reasoning model via Ollama Cloud
154    OllamaMistralLarge3675bCloud,
155    /// Kimi K2 Thinking Cloud - MoonshotAI Kimi K2 thinking model via Ollama Cloud
156    OllamaKimiK2ThinkingCloud,
157    /// Qwen3 Coder 480B Cloud - Cloud-hosted Qwen3 Coder model served via Ollama Cloud
158    OllamaQwen3Coder480bCloud,
159    /// GLM-4.6 Cloud - Cloud-hosted GLM-4.6 model served via Ollama Cloud
160    OllamaGlm46Cloud,
161    /// Gemini 3 Pro Preview Latest Cloud - Google Gemini 3 Pro Preview via Ollama Cloud
162    OllamaGemini3ProPreviewLatestCloud,
163    /// Devstral 2 123B Cloud - Mistral Devstral 2 123B model via Ollama Cloud
164    OllamaDevstral2123bCloud,
165    /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
166    OllamaMinimaxM2Cloud,
167    /// GLM-4.7 Cloud - Cloud-hosted GLM-4.7 model served via Ollama Cloud
168    OllamaGlm47Cloud,
169    /// MiniMax-M2.1 Cloud - Cloud-hosted MiniMax-M2.1 model served via Ollama Cloud
170    OllamaMinimaxM21Cloud,
171    /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
172    OllamaGemini3FlashPreviewCloud,
173    /// Nemotron-3-Nano 30B Cloud - NVIDIA Nemotron-3-Nano 30B via Ollama Cloud
174    OllamaNemotron3Nano30bCloud,
175
176    // MiniMax models
177    /// MiniMax-M2.1 - Latest MiniMax model with enhanced code understanding and reasoning
178    MinimaxM21,
179    /// MiniMax-M2.1-lightning - Fast version of MiniMax-M2.1
180    MinimaxM21Lightning,
181    /// MiniMax-M2 - MiniMax reasoning-focused model
182    MinimaxM2,
183
184    // LM Studio models
185    /// Meta Llama 3 8B Instruct served locally via LM Studio
186    LmStudioMetaLlama38BInstruct,
187    /// Meta Llama 3.1 8B Instruct served locally via LM Studio
188    LmStudioMetaLlama318BInstruct,
189    /// Qwen2.5 7B Instruct served locally via LM Studio
190    LmStudioQwen257BInstruct,
191    /// Gemma 2 2B IT served locally via LM Studio
192    LmStudioGemma22BIt,
193    /// Gemma 2 9B IT served locally via LM Studio
194    LmStudioGemma29BIt,
195    /// Phi-3.1 Mini 4K Instruct served locally via LM Studio
196    LmStudioPhi31Mini4kInstruct,
197
198    // OpenRouter models
199    /// Grok Code Fast 1 - Fast OpenRouter coding model powered by xAI Grok
200    OpenRouterGrokCodeFast1,
201    /// Grok 4 Fast - Reasoning-focused Grok endpoint with transparent traces
202    OpenRouterGrok4Fast,
203    /// Grok 4.1 Fast - Enhanced Grok 4.1 fast inference with improved reasoning
204    OpenRouterGrok41Fast,
205    /// Grok 4 - Flagship Grok 4 endpoint exposed through OpenRouter
206    OpenRouterGrok4,
207    /// GLM 4.6 - Z.AI GLM 4.6 long-context reasoning model
208    OpenRouterZaiGlm46,
209    /// Kimi K2 0905 - MoonshotAI Kimi K2 0905 MoE release optimised for coding agents
210    OpenRouterMoonshotaiKimiK20905,
211    /// Kimi K2 Thinking - MoonshotAI reasoning-tier Kimi K2 release optimized for long-horizon agents
212    OpenRouterMoonshotaiKimiK2Thinking,
213    /// Qwen3 Max - Flagship Qwen3 mixture for general reasoning
214    OpenRouterQwen3Max,
215    /// Qwen3 235B A22B - Mixture-of-experts Qwen3 235B general model
216    OpenRouterQwen3235bA22b,
217    /// Qwen3 235B A22B Instruct 2507 - Instruction-tuned Qwen3 235B A22B
218    OpenRouterQwen3235bA22b2507,
219    /// Qwen3 235B A22B Thinking 2507 - Deliberative Qwen3 235B A22B reasoning release
220    OpenRouterQwen3235bA22bThinking2507,
221    /// Qwen3 32B - Dense 32B Qwen3 deployment
222    OpenRouterQwen332b,
223    /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
224    OpenRouterQwen330bA3b,
225    /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
226    OpenRouterQwen330bA3bInstruct2507,
227    /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
228    OpenRouterQwen330bA3bThinking2507,
229    /// Qwen3 14B - Lightweight Qwen3 14B model
230    OpenRouterQwen314b,
231    /// Qwen3 8B - Compact Qwen3 8B deployment
232    OpenRouterQwen38b,
233    /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
234    OpenRouterQwen3Next80bA3bInstruct,
235    /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
236    OpenRouterQwen3Next80bA3bThinking,
237    /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
238    OpenRouterQwen3Coder,
239    /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
240    OpenRouterQwen3CoderPlus,
241    /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
242    OpenRouterQwen3CoderFlash,
243    /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
244    OpenRouterQwen3Coder30bA3bInstruct,
245    /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
246    OpenRouterDeepseekChat,
247    /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
248    OpenRouterDeepSeekV32,
249    /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
250    OpenRouterDeepseekReasoner,
251    /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
252    OpenRouterDeepSeekV32Speciale,
253    /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
254    OpenRouterDeepSeekV32Exp,
255    /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
256    OpenRouterDeepSeekChatV31,
257    /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
258    OpenRouterDeepSeekR1,
259    /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
260    OpenRouterOpenAIGptOss120b,
261    /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
262    OpenRouterOpenAIGptOss20b,
263    /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
264    OpenRouterOpenAIGpt5,
265    /// OpenAI GPT-5 Codex - OpenRouter listing for GPT-5 Codex
266    OpenRouterOpenAIGpt5Codex,
267    /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
268    OpenRouterOpenAIGpt5Chat,
269    /// OpenAI GPT-4o Search Preview - GPT-4o search preview endpoint via OpenRouter
270    OpenRouterOpenAIGpt4oSearchPreview,
271    /// OpenAI GPT-4o Mini Search Preview - GPT-4o mini search preview endpoint
272    OpenRouterOpenAIGpt4oMiniSearchPreview,
273    /// OpenAI ChatGPT-4o Latest - ChatGPT 4o latest listing via OpenRouter
274    OpenRouterOpenAIChatgpt4oLatest,
275    /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
276    OpenRouterAnthropicClaudeSonnet45,
277    /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
278    OpenRouterAnthropicClaudeHaiku45,
279    /// Claude Opus 4.1 - Anthropic Claude Opus 4.1 listing
280    OpenRouterAnthropicClaudeOpus41,
281    /// Amazon Nova 2 Lite - Amazon Nova 2 Lite model via OpenRouter
282    OpenRouterAmazonNova2LiteV1,
283    /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
284    OpenRouterMistralaiMistralLarge2512,
285    /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
286    OpenRouterNexAgiDeepseekV31NexN1,
287    /// OpenAI GPT-5.1 - OpenAI GPT-5.1 model accessed through OpenRouter
288    OpenRouterOpenAIGpt51,
289    /// OpenAI GPT-5.1-Codex - OpenRouter listing for GPT-5.1 Codex
290    OpenRouterOpenAIGpt51Codex,
291    /// OpenAI GPT-5.1-Codex-Max - OpenRouter listing for GPT-5.1 Codex Max
292    OpenRouterOpenAIGpt51CodexMax,
293    /// OpenAI GPT-5.1-Codex-Mini - OpenRouter listing for GPT-5.1 Codex Mini
294    OpenRouterOpenAIGpt51CodexMini,
295    /// OpenAI GPT-5.1 Chat - Chat optimised GPT-5.1 endpoint without tool use
296    OpenRouterOpenAIGpt51Chat,
297    /// OpenAI GPT-5.2 - OpenAI GPT-5.2 model accessed through OpenRouter
298    OpenRouterOpenAIGpt52,
299    /// OpenAI GPT-5.2 Chat - Chat optimised GPT-5.2 endpoint without tool use
300    OpenRouterOpenAIGpt52Chat,
301    /// OpenAI GPT-5.2-Codex - OpenRouter listing for GPT-5.2 Codex
302    OpenRouterOpenAIGpt52Codex,
303    /// OpenAI GPT-5.2 Pro - Professional tier GPT-5.2 model accessed through OpenRouter
304    OpenRouterOpenAIGpt52Pro,
305    /// OpenAI o1-pro - OpenAI o1-pro advanced reasoning model via OpenRouter
306    OpenRouterOpenAIO1Pro,
307    /// GLM 4.6V - Z.AI GLM 4.6V enhanced vision model
308    OpenRouterZaiGlm46V,
309    /// GLM 4.7 - Z.AI GLM 4.7 next-generation reasoning model
310    OpenRouterZaiGlm47,
311    /// GLM 4.7 Flash - Z.AI GLM-4.7-Flash lightweight model via OpenRouter
312    OpenRouterZaiGlm47Flash,
313}
vtcode_config/models/model_id.rs

vtcode_config/models/
model_id.rs
