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
14pub use capabilities::{
15 ModelCatalogEntry, catalog_provider_keys, model_catalog_entry, supported_models_for_provider,
16};
17
18/// Centralized enum for all supported model identifiers
19#[cfg_attr(feature = "schema", derive(schemars::JsonSchema))]
20#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Hash, Serialize, Deserialize)]
21pub enum ModelId {
22 // Gemini models
23 /// Gemini 3.1 Pro Preview - Latest Gemini 3.1 Pro flagship
24 Gemini31ProPreview,
25 /// Gemini 3.1 Pro Preview Custom Tools - Optimized for custom tools & bash
26 Gemini31ProPreviewCustomTools,
27 /// Gemini 3.1 Flash Lite Preview - Most cost-efficient model, offering fastest performance for high-frequency, lightweight tasks
28 Gemini31FlashLitePreview,
29 /// Gemini 3 Flash Preview - Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding
30 #[default]
31 Gemini3FlashPreview,
32
33 // OpenAI models
34 /// GPT-5 - Latest most capable OpenAI model (2025-08-07)
35 GPT5,
36 /// GPT-5.2 - Latest flagship general-purpose OpenAI model (2025-12-11)
37 GPT52,
38 /// GPT-5.2 Codex - Code-focused GPT-5.2 variant optimized for agentic coding with xhigh reasoning support
39 GPT52Codex,
40 /// GPT-5.4 - Mainline frontier GPT model for general-purpose and coding work
41 GPT54,
42 /// GPT-5.4 Pro - Higher-compute GPT-5.4 variant for difficult problems
43 GPT54Pro,
44 /// GPT-5.4 Nano - Lightweight GPT-5.4 variant optimized for speed and cost-efficiency
45 GPT54Nano,
46 /// GPT-5.4 Mini - Compact GPT-5.4 variant for cost-effective tasks with reduced reasoning overhead
47 GPT54Mini,
48 /// GPT-5.3 Codex - Code-focused GPT-5.3 variant optimized for agentic coding with reasoning effort support (low, medium, high, xhigh)
49 GPT53Codex,
50 /// GPT-5.1 Codex - Code-focused GPT-5.1 variant optimized for agentic coding
51 GPT51Codex,
52 /// GPT-5.1 Codex Max - Higher-compute GPT-5.1 Codex variant for longer-running engineering tasks
53 GPT51CodexMax,
54 /// GPT-5 Mini - Latest efficient OpenAI model (2025-08-07)
55 GPT5Mini,
56 /// GPT-5 Nano - Latest most cost-effective OpenAI model (2025-08-07)
57 GPT5Nano,
58 /// GPT-5 Codex - Code-focused GPT-5 variant optimized for agentic coding
59 GPT5Codex,
60 /// GPT-OSS 20B - OpenAI's open-source 20B parameter model using harmony
61 OpenAIGptOss20b,
62 /// GPT-OSS 120B - OpenAI's open-source 120B parameter model using harmony
63 OpenAIGptOss120b,
64
65 // Anthropic models
66 /// Claude Opus 4.6 - Next-gen flagship Anthropic model with extended thinking
67 ClaudeOpus46,
68 /// Claude Sonnet 4.6 - Balanced flagship Anthropic model with extended thinking
69 ClaudeSonnet46,
70 /// Claude Haiku 4.5 - Latest efficient Anthropic model (2025-10-15)
71 ClaudeHaiku45,
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 /// Qwen3.5-397B-A17B via Together inference provider on Hugging Face router
96 HuggingFaceQwen35397BA17BTogether,
97 /// Step 3.5 Flash via Hugging Face router
98 HuggingFaceStep35Flash,
99
100 /// GLM-5 - Flagship Z.ai foundation model for complex systems
101 ZaiGlm5,
102
103 // Moonshot models
104 /// Kimi K2.5 - Moonshot.ai's flagship reasoning model
105 MoonshotKimiK25,
106
107 // Ollama models
108 /// GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally
109 OllamaGptOss20b,
110 /// GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud
111 OllamaGptOss20bCloud,
112 /// GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud
113 OllamaGptOss120bCloud,
114 /// Qwen3 1.7B - Qwen3 1.7B model served via Ollama
115 OllamaQwen317b,
116 /// Qwen3 Coder Next - Coding-optimized Qwen3 Next model served via Ollama locally
117 OllamaQwen3CoderNext,
118 /// DeepSeek V3.2 Cloud - DeepSeek V3.2 reasoning deployment via Ollama Cloud
119 OllamaDeepseekV32Cloud,
120 /// Qwen3 Next 80B Cloud - Next-generation Qwen3 80B via Ollama Cloud
121 OllamaQwen3Next80bCloud,
122 /// MiniMax-M2 Cloud - Cloud-hosted MiniMax-M2 model served via Ollama Cloud
123 OllamaMinimaxM2Cloud,
124 /// GLM-5 Cloud - Cloud-hosted GLM-5 model served via Ollama Cloud
125 OllamaGlm5Cloud,
126 /// MiniMax-M2.5 Cloud - Cloud-hosted MiniMax-M2.5 model served via Ollama Cloud
127 OllamaMinimaxM25Cloud,
128 /// Gemini 3 Flash Preview Cloud - Google Gemini 3 Flash Preview via Ollama Cloud
129 OllamaGemini3FlashPreviewCloud,
130 /// Nemotron 3 Super Cloud - NVIDIA Nemotron 3 Super 120B via Ollama Cloud
131 OllamaNemotron3SuperCloud,
132
133 // MiniMax models
134 /// MiniMax-M2.7 - Recursive self-improvement flagship with 204.8K context
135 MinimaxM27,
136 /// MiniMax-M2.5 - Latest MiniMax model with further improvements in reasoning and coding
137 MinimaxM25,
138
139 // OpenRouter models
140 /// Qwen3 32B - Dense 32B Qwen3 deployment
141 OpenRouterQwen332b,
142 /// Qwen3 30B A3B - Active-parameter 30B Qwen3 model
143 OpenRouterQwen330bA3b,
144 /// Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B
145 OpenRouterQwen330bA3bInstruct2507,
146 /// Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release
147 OpenRouterQwen330bA3bThinking2507,
148 /// Qwen3 14B - Lightweight Qwen3 14B model
149 OpenRouterQwen314b,
150 /// Qwen3 8B - Compact Qwen3 8B deployment
151 OpenRouterQwen38b,
152 /// Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model
153 OpenRouterQwen3Next80bA3bInstruct,
154 /// Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release
155 OpenRouterQwen3Next80bA3bThinking,
156 /// Qwen3.5-397B-A17B - Native vision-language model with linear attention and sparse MoE, 1M context window
157 OpenRouterQwen35Plus0215,
158 /// Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows
159 OpenRouterQwen3Coder,
160 /// Qwen3 Coder Plus - Premium Qwen3 coding model with long context
161 OpenRouterQwen3CoderPlus,
162 /// Qwen3 Coder Flash - Latency optimised Qwen3 coding model
163 OpenRouterQwen3CoderFlash,
164 /// Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment
165 OpenRouterQwen3Coder30bA3bInstruct,
166 /// Qwen3 Coder Next - Next-generation Qwen3 coding model with enhanced reasoning
167 OpenRouterQwen3CoderNext,
168 /// DeepSeek V3.2 Chat - Official chat model via OpenRouter
169 OpenRouterDeepseekChat,
170 /// DeepSeek V3.2 - Standard model with thinking support via OpenRouter
171 OpenRouterDeepSeekV32,
172 /// DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter
173 OpenRouterDeepseekReasoner,
174 /// DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)
175 OpenRouterDeepSeekV32Speciale,
176 /// DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing
177 OpenRouterDeepSeekV32Exp,
178 /// DeepSeek Chat v3.1 - Advanced DeepSeek model via OpenRouter
179 OpenRouterDeepSeekChatV31,
180 /// DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought
181 OpenRouterDeepSeekR1,
182 /// OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter
183 OpenRouterOpenAIGptOss120b,
184 /// OpenAI gpt-oss-120b:free - Open-weight 120B reasoning model free tier via OpenRouter
185 OpenRouterOpenAIGptOss120bFree,
186 /// OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter
187 OpenRouterOpenAIGptOss20b,
188 /// OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter
189 OpenRouterOpenAIGpt5,
190 /// OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use
191 OpenRouterOpenAIGpt5Chat,
192
193 /// Gemini 3.1 Pro Preview - Google's latest Gemini 3.1 Pro model via OpenRouter
194 OpenRouterGoogleGemini31ProPreview,
195
196 /// Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing
197 OpenRouterAnthropicClaudeSonnet45,
198 /// Claude Sonnet 4.6 - Anthropic Claude Sonnet 4.6 listing
199 OpenRouterAnthropicClaudeSonnet46,
200 /// Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing
201 OpenRouterAnthropicClaudeHaiku45,
202 /// Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter
203 OpenRouterMistralaiMistralLarge2512,
204 /// DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter
205 OpenRouterNexAgiDeepseekV31NexN1,
206 /// Step 3.5 Flash (free) - StepFun's most capable open-source reasoning model via OpenRouter
207 OpenRouterStepfunStep35FlashFree,
208 /// Nemotron 3 Super (free) - NVIDIA's 120B hybrid MoE model via OpenRouter
209 OpenRouterNvidiaNemotron3Super120bA12bFree,
210 /// GLM-5 - Z.AI GLM-5 flagship foundation model via OpenRouter
211 OpenRouterZaiGlm5,
212 /// MiniMax-M2.5 - MiniMax flagship model via OpenRouter
213 OpenRouterMinimaxM25,
214}