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 3.1 Pro Preview - Latest Gemini 3.1 Pro flagship
20 Gemini31ProPreview,
21 /// Gemini 3.1 Pro Preview Custom Tools - Optimized for custom tools & bash
22 Gemini31ProPreviewCustomTools,
23 /// Gemini 3.1 Flash Lite Preview - Most cost-efficient model, offering fastest performance for high-frequency, lightweight tasks
24 Gemini31FlashLitePreview,
25 /// Gemini 3 Flash Preview - Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding
26 #[default]
27 Gemini3FlashPreview,
28
29 // OpenAI models
30 /// GPT-5 - Latest most capable OpenAI model (2025-08-07)
31 GPT5,
32 /// GPT-5.2 - Latest flagship general-purpose OpenAI model (2025-12-11)
33 GPT52,
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-5.3 Codex - Code-focused GPT-5.3 variant optimized for agentic coding with reasoning effort support (low, medium, high, xhigh)
39 GPT53Codex,
40 /// GPT-OSS 20B - OpenAI's open-source 20B parameter model using harmony
41 OpenAIGptOss20b,
42 /// GPT-OSS 120B - OpenAI's open-source 120B parameter model using harmony
43 OpenAIGptOss120b,
44
45 // Anthropic models
46 /// Claude Opus 4.6 - Next-gen flagship Anthropic model with extended thinking
47 ClaudeOpus46,
48 /// Claude Sonnet 4.6 - Balanced flagship Anthropic model with extended thinking
49 ClaudeSonnet46,
50 /// Claude Haiku 4.5 - Latest efficient Anthropic model (2025-10-15)
51 ClaudeHaiku45,
52
53 // DeepSeek models
54 /// DeepSeek V3.2 Chat - Fast non-thinking mode
55 DeepSeekChat,
56 /// DeepSeek V3.2 Reasoner - Thinking mode with structured reasoning output
57 DeepSeekReasoner,
58 // Hugging Face models
59 /// DeepSeek V3.2 via Hugging Face router
60 HuggingFaceDeepseekV32,
61 /// OpenAI GPT-OSS 20B via Hugging Face router
62 HuggingFaceOpenAIGptOss20b,
63 /// OpenAI GPT-OSS 120B via Hugging Face router
64 HuggingFaceOpenAIGptOss120b,
65 /// DeepSeek V3.2 via Novita on Hugging Face router
66 HuggingFaceDeepseekV32Novita,
67 /// Xiaomi MiMo-V2-Flash via Novita on Hugging Face router
68 HuggingFaceXiaomiMimoV2FlashNovita,
69 /// MiniMax M2.5 via Novita on Hugging Face router
70 HuggingFaceMinimaxM25Novita,
71 /// Z.AI GLM-5 via Novita on Hugging Face router
72 HuggingFaceGlm5Novita,
73 /// Qwen3-Coder-Next via Novita inference provider on Hugging Face router
74 HuggingFaceQwen3CoderNextNovita,
75 /// Qwen3.5-397B-A17B via Together inference provider on Hugging Face router
76 HuggingFaceQwen35397BA17BTogether,
77 /// Step 3.5 Flash via Hugging Face router
78 HuggingFaceStep35Flash,
79
80 /// GLM-5 - Flagship Z.ai foundation model for complex systems
81 ZaiGlm5,
82
83 // Moonshot models
84 /// Kimi K2.5 - Moonshot.ai's flagship reasoning model
85 MoonshotKimiK25,
86
87 // Ollama models
88 /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
89 OllamaGptOss20b,
90 /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
91 OllamaGptOss20bCloud,
92 /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
93 OllamaGptOss120bCloud,
94 /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
95 OllamaQwen317b,
96 /// Qwen3 Coder Next - Coding-optimized Qwen3 Next model served via Ollama locally
97 OllamaQwen3CoderNext,
98 /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
99 OllamaDeepseekV32Cloud,
100 /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
101 OllamaQwen3Next80bCloud,
102 /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
103 OllamaMinimaxM2Cloud,
104 /// GLM-5 Cloud - Cloud-hosted GLM-5 model served via Ollama Cloud
105 OllamaGlm5Cloud,
106 /// MiniMax-M2.5 Cloud - Cloud-hosted MiniMax-M2.5 model served via Ollama Cloud
107 OllamaMinimaxM25Cloud,
108 /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
109 OllamaGemini3FlashPreviewCloud,
110
111 // MiniMax models
112 /// MiniMax-M2.5 - Latest MiniMax model with further improvements in reasoning and coding
113 MinimaxM25,
114
115 // OpenRouter models
116 /// Qwen3 32B - Dense 32B Qwen3 deployment
117 OpenRouterQwen332b,
118 /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
119 OpenRouterQwen330bA3b,
120 /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
121 OpenRouterQwen330bA3bInstruct2507,
122 /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
123 OpenRouterQwen330bA3bThinking2507,
124 /// Qwen3 14B - Lightweight Qwen3 14B model
125 OpenRouterQwen314b,
126 /// Qwen3 8B - Compact Qwen3 8B deployment
127 OpenRouterQwen38b,
128 /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
129 OpenRouterQwen3Next80bA3bInstruct,
130 /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
131 OpenRouterQwen3Next80bA3bThinking,
132 /// Qwen3.5-397B-A17B - Native vision-language model with linear attention and sparse MoE, 1M context window
133 OpenRouterQwen35Plus0215,
134 /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
135 OpenRouterQwen3Coder,
136 /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
137 OpenRouterQwen3CoderPlus,
138 /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
139 OpenRouterQwen3CoderFlash,
140 /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
141 OpenRouterQwen3Coder30bA3bInstruct,
142 /// Qwen3 Coder Next - Next-generation Qwen3 coding model with enhanced reasoning
143 OpenRouterQwen3CoderNext,
144 /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
145 OpenRouterDeepseekChat,
146 /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
147 OpenRouterDeepSeekV32,
148 /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
149 OpenRouterDeepseekReasoner,
150 /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
151 OpenRouterDeepSeekV32Speciale,
152 /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
153 OpenRouterDeepSeekV32Exp,
154 /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
155 OpenRouterDeepSeekChatV31,
156 /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
157 OpenRouterDeepSeekR1,
158 /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
159 OpenRouterOpenAIGptOss120b,
160 /// OpenAI gpt-oss-120b:free - Open-weight 120B reasoning model free tier via OpenRouter
161 OpenRouterOpenAIGptOss120bFree,
162 /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
163 OpenRouterOpenAIGptOss20b,
164 /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
165 OpenRouterOpenAIGpt5,
166 /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
167 OpenRouterOpenAIGpt5Chat,
168
169 /// Gemini 3.1 Pro Preview - Google's latest Gemini 3.1 Pro model via OpenRouter
170 OpenRouterGoogleGemini31ProPreview,
171
172 /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
173 OpenRouterAnthropicClaudeSonnet45,
174 /// Claude Sonnet 4.6 - Anthropic Claude Sonnet 4.6 listing
175 OpenRouterAnthropicClaudeSonnet46,
176 /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
177 OpenRouterAnthropicClaudeHaiku45,
178 /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
179 OpenRouterMistralaiMistralLarge2512,
180 /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
181 OpenRouterNexAgiDeepseekV31NexN1,
182 /// Step 3.5 Flash (free) - StepFun's most capable open-source reasoning model via OpenRouter
183 OpenRouterStepfunStep35FlashFree,
184 /// GLM-5 - Z.AI GLM-5 flagship foundation model via OpenRouter
185 OpenRouterZaiGlm5,
186 /// MiniMax-M2.5 - MiniMax flagship model via OpenRouter
187 OpenRouterMinimaxM25,
188}