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-5.2 Codex - Code-focused GPT-5.2 variant optimized for agentic coding with xhigh reasoning support
35 GPT52Codex,
36 /// GPT-5.4 - Mainline frontier GPT model for general-purpose and coding work
37 GPT54,
38 /// GPT-5.4 Pro - Higher-compute GPT-5.4 variant for difficult problems
39 GPT54Pro,
40 /// GPT-5.3 Codex - Code-focused GPT-5.3 variant optimized for agentic coding with reasoning effort support (low, medium, high, xhigh)
41 GPT53Codex,
42 /// GPT-5.1 Codex - Code-focused GPT-5.1 variant optimized for agentic coding
43 GPT51Codex,
44 /// GPT-5.1 Codex Max - Higher-compute GPT-5.1 Codex variant for longer-running engineering tasks
45 GPT51CodexMax,
46 /// GPT-5 Mini - Latest efficient OpenAI model (2025-08-07)
47 GPT5Mini,
48 /// GPT-5 Nano - Latest most cost-effective OpenAI model (2025-08-07)
49 GPT5Nano,
50 /// GPT-5 Codex - Code-focused GPT-5 variant optimized for agentic coding
51 GPT5Codex,
52 /// GPT-OSS 20B - OpenAI's open-source 20B parameter model using harmony
53 OpenAIGptOss20b,
54 /// GPT-OSS 120B - OpenAI's open-source 120B parameter model using harmony
55 OpenAIGptOss120b,
56
57 // Anthropic models
58 /// Claude Opus 4.6 - Next-gen flagship Anthropic model with extended thinking
59 ClaudeOpus46,
60 /// Claude Sonnet 4.6 - Balanced flagship Anthropic model with extended thinking
61 ClaudeSonnet46,
62 /// Claude Haiku 4.5 - Latest efficient Anthropic model (2025-10-15)
63 ClaudeHaiku45,
64
65 // DeepSeek models
66 /// DeepSeek V3.2 Chat - Fast non-thinking mode
67 DeepSeekChat,
68 /// DeepSeek V3.2 Reasoner - Thinking mode with structured reasoning output
69 DeepSeekReasoner,
70 // Hugging Face models
71 /// DeepSeek V3.2 via Hugging Face router
72 HuggingFaceDeepseekV32,
73 /// OpenAI GPT-OSS 20B via Hugging Face router
74 HuggingFaceOpenAIGptOss20b,
75 /// OpenAI GPT-OSS 120B via Hugging Face router
76 HuggingFaceOpenAIGptOss120b,
77 /// DeepSeek V3.2 via Novita on Hugging Face router
78 HuggingFaceDeepseekV32Novita,
79 /// Xiaomi MiMo-V2-Flash via Novita on Hugging Face router
80 HuggingFaceXiaomiMimoV2FlashNovita,
81 /// MiniMax M2.5 via Novita on Hugging Face router
82 HuggingFaceMinimaxM25Novita,
83 /// Z.AI GLM-5 via Novita on Hugging Face router
84 HuggingFaceGlm5Novita,
85 /// Qwen3-Coder-Next via Novita inference provider on Hugging Face router
86 HuggingFaceQwen3CoderNextNovita,
87 /// Qwen3.5-397B-A17B via Together inference provider on Hugging Face router
88 HuggingFaceQwen35397BA17BTogether,
89 /// Step 3.5 Flash via Hugging Face router
90 HuggingFaceStep35Flash,
91
92 /// GLM-5 - Flagship Z.ai foundation model for complex systems
93 ZaiGlm5,
94
95 // Moonshot models
96 /// Kimi K2.5 - Moonshot.ai's flagship reasoning model
97 MoonshotKimiK25,
98
99 // Ollama models
100 /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
101 OllamaGptOss20b,
102 /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
103 OllamaGptOss20bCloud,
104 /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
105 OllamaGptOss120bCloud,
106 /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
107 OllamaQwen317b,
108 /// Qwen3 Coder Next - Coding-optimized Qwen3 Next model served via Ollama locally
109 OllamaQwen3CoderNext,
110 /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
111 OllamaDeepseekV32Cloud,
112 /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
113 OllamaQwen3Next80bCloud,
114 /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
115 OllamaMinimaxM2Cloud,
116 /// GLM-5 Cloud - Cloud-hosted GLM-5 model served via Ollama Cloud
117 OllamaGlm5Cloud,
118 /// MiniMax-M2.5 Cloud - Cloud-hosted MiniMax-M2.5 model served via Ollama Cloud
119 OllamaMinimaxM25Cloud,
120 /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
121 OllamaGemini3FlashPreviewCloud,
122 /// Nemotron 3 Super Cloud - NVIDIA Nemotron 3 Super 120B via Ollama Cloud
123 OllamaNemotron3SuperCloud,
124
125 // MiniMax models
126 /// MiniMax-M2.5 - Latest MiniMax model with further improvements in reasoning and coding
127 MinimaxM25,
128
129 // OpenRouter models
130 /// Qwen3 32B - Dense 32B Qwen3 deployment
131 OpenRouterQwen332b,
132 /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
133 OpenRouterQwen330bA3b,
134 /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
135 OpenRouterQwen330bA3bInstruct2507,
136 /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
137 OpenRouterQwen330bA3bThinking2507,
138 /// Qwen3 14B - Lightweight Qwen3 14B model
139 OpenRouterQwen314b,
140 /// Qwen3 8B - Compact Qwen3 8B deployment
141 OpenRouterQwen38b,
142 /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
143 OpenRouterQwen3Next80bA3bInstruct,
144 /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
145 OpenRouterQwen3Next80bA3bThinking,
146 /// Qwen3.5-397B-A17B - Native vision-language model with linear attention and sparse MoE, 1M context window
147 OpenRouterQwen35Plus0215,
148 /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
149 OpenRouterQwen3Coder,
150 /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
151 OpenRouterQwen3CoderPlus,
152 /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
153 OpenRouterQwen3CoderFlash,
154 /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
155 OpenRouterQwen3Coder30bA3bInstruct,
156 /// Qwen3 Coder Next - Next-generation Qwen3 coding model with enhanced reasoning
157 OpenRouterQwen3CoderNext,
158 /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
159 OpenRouterDeepseekChat,
160 /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
161 OpenRouterDeepSeekV32,
162 /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
163 OpenRouterDeepseekReasoner,
164 /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
165 OpenRouterDeepSeekV32Speciale,
166 /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
167 OpenRouterDeepSeekV32Exp,
168 /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
169 OpenRouterDeepSeekChatV31,
170 /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
171 OpenRouterDeepSeekR1,
172 /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
173 OpenRouterOpenAIGptOss120b,
174 /// OpenAI gpt-oss-120b:free - Open-weight 120B reasoning model free tier via OpenRouter
175 OpenRouterOpenAIGptOss120bFree,
176 /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
177 OpenRouterOpenAIGptOss20b,
178 /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
179 OpenRouterOpenAIGpt5,
180 /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
181 OpenRouterOpenAIGpt5Chat,
182
183 /// Gemini 3.1 Pro Preview - Google's latest Gemini 3.1 Pro model via OpenRouter
184 OpenRouterGoogleGemini31ProPreview,
185
186 /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
187 OpenRouterAnthropicClaudeSonnet45,
188 /// Claude Sonnet 4.6 - Anthropic Claude Sonnet 4.6 listing
189 OpenRouterAnthropicClaudeSonnet46,
190 /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
191 OpenRouterAnthropicClaudeHaiku45,
192 /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
193 OpenRouterMistralaiMistralLarge2512,
194 /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
195 OpenRouterNexAgiDeepseekV31NexN1,
196 /// Step 3.5 Flash (free) - StepFun's most capable open-source reasoning model via OpenRouter
197 OpenRouterStepfunStep35FlashFree,
198 /// Nemotron 3 Super (free) - NVIDIA's 120B hybrid MoE model via OpenRouter
199 OpenRouterNvidiaNemotron3Super120bA12bFree,
200 /// GLM-5 - Z.AI GLM-5 flagship foundation model via OpenRouter
201 OpenRouterZaiGlm5,
202 /// MiniMax-M2.5 - MiniMax flagship model via OpenRouter
203 OpenRouterMinimaxM25,
204}