airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
5da07eae4ce831f5c706cc235d9aafa9e1b03219
CLIProxyAPI/internal/registry/model_definitions_static_data.go
hkfires c44793789b feat(thinking): add adaptive thinking support for Claude models 
Add support for Claude's "adaptive" and "auto" thinking modes using `output_config.effort`. Introduce support for new effort level "max" in adaptive thinking. Update thinking logic, validate model capabilities, and extend converters and handling to ensure compatibility with adaptive modes. Adjust static model data with supported levels and refine handling across translators and executors.
2026-03-03 09:05:31 +08:00

1004 lines
47 KiB
Go
Raw Blame History

// Package registry provides model definitions for various AI service providers.
// This file stores the static model metadata catalog.
package registry
// GetClaudeModels returns the standard Claude model definitions
func GetClaudeModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "claude-haiku-4-5-20251001",
Object: "model",
Created: 1759276800, // 2025-10-01
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Haiku",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: false},
},
{
ID: "claude-sonnet-4-5-20250929",
Object: "model",
Created: 1759104000, // 2025-09-29
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Sonnet",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: false},
},
{
ID: "claude-sonnet-4-6",
Object: "model",
Created: 1771372800, // 2026-02-17
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.6 Sonnet",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: false, Levels: []string{"low", "medium", "high"}},
},
{
ID: "claude-opus-4-6",
Object: "model",
Created: 1770318000, // 2026-02-05
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.6 Opus",
Description: "Premium model combining maximum intelligence with practical performance",
ContextLength: 1000000,
MaxCompletionTokens: 128000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: false, Levels: []string{"low", "medium", "high", "max"}},
},
{
ID: "claude-opus-4-5-20251101",
Object: "model",
Created: 1761955200, // 2025-11-01
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Opus",
Description: "Premium model combining maximum intelligence with practical performance",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: false},
},
{
ID: "claude-opus-4-1-20250805",
Object: "model",
Created: 1722945600, // 2025-08-05
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.1 Opus",
ContextLength: 200000,
MaxCompletionTokens: 32000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: false, DynamicAllowed: false},
},
{
ID: "claude-opus-4-20250514",
Object: "model",
Created: 1715644800, // 2025-05-14
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4 Opus",
ContextLength: 200000,
MaxCompletionTokens: 32000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: false, DynamicAllowed: false},
},
{
ID: "claude-sonnet-4-20250514",
Object: "model",
Created: 1715644800, // 2025-05-14
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4 Sonnet",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: false, DynamicAllowed: false},
},
{
ID: "claude-3-7-sonnet-20250219",
Object: "model",
Created: 1708300800, // 2025-02-19
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 3.7 Sonnet",
ContextLength: 128000,
MaxCompletionTokens: 8192,
Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: false, DynamicAllowed: false},
},
{
ID: "claude-3-5-haiku-20241022",
Object: "model",
Created: 1729555200, // 2024-10-22
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 3.5 Haiku",
ContextLength: 128000,
MaxCompletionTokens: 8192,
// Thinking: not supported for Haiku models
},
}
}
// GetGeminiModels returns the standard Gemini model definitions
func GetGeminiModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3.1-pro-preview",
Object: "model",
Created: 1771459200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3.1-pro-preview",
Version: "3.1",
DisplayName: "Gemini 3.1 Pro Preview",
Description: "Gemini 3.1 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3-flash-preview",
Object: "model",
Created: 1765929600,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-flash-preview",
Version: "3.0",
DisplayName: "Gemini 3 Flash Preview",
Description: "Gemini 3 Flash Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}},
},
{
ID: "gemini-3-pro-image-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-image-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Image Preview",
Description: "Gemini 3 Pro Image Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
}
}
func GetGeminiVertexModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3-flash-preview",
Object: "model",
Created: 1765929600,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-flash-preview",
Version: "3.0",
DisplayName: "Gemini 3 Flash Preview",
Description: "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}},
},
{
ID: "gemini-3.1-pro-preview",
Object: "model",
Created: 1771459200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3.1-pro-preview",
Version: "3.1",
DisplayName: "Gemini 3.1 Pro Preview",
Description: "Gemini 3.1 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3-pro-image-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-image-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Image Preview",
Description: "Gemini 3 Pro Image Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
// Imagen image generation models - use :predict action
{
ID: "imagen-4.0-generate-001",
Object: "model",
Created: 1750000000,
OwnedBy: "google",
Type: "gemini",
Name: "models/imagen-4.0-generate-001",
Version: "4.0",
DisplayName: "Imagen 4.0 Generate",
Description: "Imagen 4.0 image generation model",
SupportedGenerationMethods: []string{"predict"},
},
{
ID: "imagen-4.0-ultra-generate-001",
Object: "model",
Created: 1750000000,
OwnedBy: "google",
Type: "gemini",
Name: "models/imagen-4.0-ultra-generate-001",
Version: "4.0",
DisplayName: "Imagen 4.0 Ultra Generate",
Description: "Imagen 4.0 Ultra high-quality image generation model",
SupportedGenerationMethods: []string{"predict"},
},
{
ID: "imagen-3.0-generate-002",
Object: "model",
Created: 1740000000,
OwnedBy: "google",
Type: "gemini",
Name: "models/imagen-3.0-generate-002",
Version: "3.0",
DisplayName: "Imagen 3.0 Generate",
Description: "Imagen 3.0 image generation model",
SupportedGenerationMethods: []string{"predict"},
},
{
ID: "imagen-3.0-fast-generate-001",
Object: "model",
Created: 1740000000,
OwnedBy: "google",
Type: "gemini",
Name: "models/imagen-3.0-fast-generate-001",
Version: "3.0",
DisplayName: "Imagen 3.0 Fast Generate",
Description: "Imagen 3.0 fast image generation model",
SupportedGenerationMethods: []string{"predict"},
},
{
ID: "imagen-4.0-fast-generate-001",
Object: "model",
Created: 1750000000,
OwnedBy: "google",
Type: "gemini",
Name: "models/imagen-4.0-fast-generate-001",
Version: "4.0",
DisplayName: "Imagen 4.0 Fast Generate",
Description: "Imagen 4.0 fast image generation model",
SupportedGenerationMethods: []string{"predict"},
},
}
}
// GetGeminiCLIModels returns the standard Gemini model definitions
func GetGeminiCLIModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Our most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3.1-pro-preview",
Object: "model",
Created: 1771459200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3.1-pro-preview",
Version: "3.1",
DisplayName: "Gemini 3.1 Pro Preview",
Description: "Gemini 3.1 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
},
{
ID: "gemini-3-flash-preview",
Object: "model",
Created: 1765929600,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-flash-preview",
Version: "3.0",
DisplayName: "Gemini 3 Flash Preview",
Description: "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}},
},
}
}
// GetAIStudioModels returns the Gemini model definitions for AI Studio integrations
func GetAIStudioModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-3.1-pro-preview",
Object: "model",
Created: 1771459200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3.1-pro-preview",
Version: "3.1",
DisplayName: "Gemini 3.1 Pro Preview",
Description: "Gemini 3.1 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-3-flash-preview",
Object: "model",
Created: 1765929600,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-flash-preview",
Version: "3.0",
DisplayName: "Gemini 3 Flash Preview",
Description: "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-pro-latest",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-pro-latest",
Version: "2.5",
DisplayName: "Gemini Pro Latest",
Description: "Latest release of Gemini Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-flash-latest",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-latest",
Version: "2.5",
DisplayName: "Gemini Flash Latest",
Description: "Latest release of Gemini Flash",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-flash-lite-latest",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-lite-latest",
Version: "2.5",
DisplayName: "Gemini Flash-Lite Latest",
Description: "Latest release of Gemini Flash-Lite",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
// {
// ID: "gemini-2.5-flash-image-preview",
// Object: "model",
// Created: 1756166400,
// OwnedBy: "google",
// Type: "gemini",
// Name: "models/gemini-2.5-flash-image-preview",
// Version: "2.5",
// DisplayName: "Gemini 2.5 Flash Image Preview",
// Description: "State-of-the-art image generation and editing model.",
// InputTokenLimit: 1048576,
// OutputTokenLimit: 8192,
// SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
// // image models don't support thinkingConfig; leave Thinking nil
// },
{
ID: "gemini-2.5-flash-image",
Object: "model",
Created: 1759363200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-image",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Image",
Description: "State-of-the-art image generation and editing model.",
InputTokenLimit: 1048576,
OutputTokenLimit: 8192,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
// image models don't support thinkingConfig; leave Thinking nil
},
}
}
// GetOpenAIModels returns the standard OpenAI model definitions
func GetOpenAIModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gpt-5",
Object: "model",
Created: 1754524800,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-08-07",
DisplayName: "GPT 5",
Description: "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"minimal", "low", "medium", "high"}},
},
{
ID: "gpt-5-codex",
Object: "model",
Created: 1757894400,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-09-15",
DisplayName: "GPT 5 Codex",
Description: "Stable version of GPT 5 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5-codex-mini",
Object: "model",
Created: 1762473600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-11-07",
DisplayName: "GPT 5 Codex Mini",
Description: "Stable version of GPT 5 Codex Mini: cheaper, faster, but less capable version of GPT 5 Codex.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5",
Description: "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"none", "low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5.1 Codex",
Description: "Stable version of GPT 5.1 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex-mini",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5.1 Codex Mini",
Description: "Stable version of GPT 5.1 Codex Mini: cheaper, faster, but less capable version of GPT 5.1 Codex.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex-max",
Object: "model",
Created: 1763424000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-max",
DisplayName: "GPT 5.1 Codex Max",
Description: "Stable version of GPT 5.1 Codex Max",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
},
{
ID: "gpt-5.2",
Object: "model",
Created: 1765440000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.2",
DisplayName: "GPT 5.2",
Description: "Stable version of GPT 5.2",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"none", "low", "medium", "high", "xhigh"}},
},
{
ID: "gpt-5.2-codex",
Object: "model",
Created: 1765440000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.2",
DisplayName: "GPT 5.2 Codex",
Description: "Stable version of GPT 5.2 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
},
{
ID: "gpt-5.3-codex",
Object: "model",
Created: 1770307200,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.3",
DisplayName: "GPT 5.3 Codex",
Description: "Stable version of GPT 5.3 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
},
{
ID: "gpt-5.3-codex-spark",
Object: "model",
Created: 1770912000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.3",
DisplayName: "GPT 5.3 Codex Spark",
Description: "Ultra-fast coding model.",
ContextLength: 128000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
},
}
}
// GetQwenModels returns the standard Qwen model definitions
func GetQwenModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "qwen3-coder-plus",
Object: "model",
Created: 1753228800,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Coder Plus",
Description: "Advanced code generation and understanding model",
ContextLength: 32768,
MaxCompletionTokens: 8192,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
{
ID: "qwen3-coder-flash",
Object: "model",
Created: 1753228800,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Coder Flash",
Description: "Fast code generation model",
ContextLength: 8192,
MaxCompletionTokens: 2048,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
{
ID: "coder-model",
Object: "model",
Created: 1771171200,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.5",
DisplayName: "Qwen 3.5 Plus",
Description: "efficient hybrid model with leading coding performance",
ContextLength: 1048576,
MaxCompletionTokens: 65536,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
{
ID: "vision-model",
Object: "model",
Created: 1758672000,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Vision Model",
Description: "Vision model model",
ContextLength: 32768,
MaxCompletionTokens: 2048,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
}
}
// iFlowThinkingSupport is a shared ThinkingSupport configuration for iFlow models
// that support thinking mode via chat_template_kwargs.enable_thinking (boolean toggle).
// Uses level-based configuration so standard normalization flows apply before conversion.
var iFlowThinkingSupport = &ThinkingSupport{
Levels: []string{"none", "auto", "minimal", "low", "medium", "high", "xhigh"},
}
// GetIFlowModels returns supported models for iFlow OAuth accounts.
func GetIFlowModels() []*ModelInfo {
entries := []struct {
ID string
DisplayName string
Description string
Created int64
Thinking *ThinkingSupport
}{
{ID: "qwen3-coder-plus", DisplayName: "Qwen3-Coder-Plus", Description: "Qwen3 Coder Plus code generation", Created: 1753228800},
{ID: "qwen3-max", DisplayName: "Qwen3-Max", Description: "Qwen3 flagship model", Created: 1758672000},
{ID: "qwen3-vl-plus", DisplayName: "Qwen3-VL-Plus", Description: "Qwen3 multimodal vision-language", Created: 1758672000},
{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400, Thinking: iFlowThinkingSupport},
{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400, Thinking: iFlowThinkingSupport},
{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental", Created: 1759104000, Thinking: iFlowThinkingSupport},
{ID: "deepseek-v3.1", DisplayName: "DeepSeek-V3.1-Terminus", Description: "DeepSeek V3.1 Terminus", Created: 1756339200, Thinking: iFlowThinkingSupport},
{ID: "deepseek-r1", DisplayName: "DeepSeek-R1", Description: "DeepSeek reasoning model R1", Created: 1737331200},
{ID: "deepseek-v3", DisplayName: "DeepSeek-V3-671B", Description: "DeepSeek V3 671B", Created: 1734307200},
{ID: "qwen3-32b", DisplayName: "Qwen3-32B", Description: "Qwen3 32B", Created: 1747094400},
{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600},
{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
{ID: "iflow-rome-30ba3b", DisplayName: "iFlow-ROME", Description: "iFlow Rome 30BA3B model", Created: 1736899200},
}
models := make([]*ModelInfo, 0, len(entries))
for _, entry := range entries {
models = append(models, &ModelInfo{
ID: entry.ID,
Object: "model",
Created: entry.Created,
OwnedBy: "iflow",
Type: "iflow",
DisplayName: entry.DisplayName,
Description: entry.Description,
Thinking: entry.Thinking,
})
}
return models
}
// AntigravityModelConfig captures static antigravity model overrides, including
// Thinking budget limits and provider max completion tokens.
type AntigravityModelConfig struct {
Thinking *ThinkingSupport
MaxCompletionTokens int
}
// GetAntigravityModelConfig returns static configuration for antigravity models.
// Keys use upstream model names returned by the Antigravity models endpoint.
func GetAntigravityModelConfig() map[string]*AntigravityModelConfig {
return map[string]*AntigravityModelConfig{
"gemini-2.5-flash": {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}},
"gemini-2.5-flash-lite": {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}},
"gemini-3-pro-high": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}},
"gemini-3-pro-low": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}},
"gemini-3.1-pro-high": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}},
"gemini-3.1-pro-low": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}},
"gemini-3.1-flash-image": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "high"}}},
"gemini-3-flash": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}}},
"claude-opus-4-6-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 64000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-sonnet-4-6": {Thinking: &ThinkingSupport{Min: 1024, Max: 64000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"gpt-oss-120b-medium": {},
}
}
// GetKimiModels returns the standard Kimi (Moonshot AI) model definitions
func GetKimiModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "kimi-k2",
Object: "model",
Created: 1752192000, // 2025-07-11
OwnedBy: "moonshot",
Type: "kimi",
DisplayName: "Kimi K2",
Description: "Kimi K2 - Moonshot AI's flagship coding model",
ContextLength: 131072,
MaxCompletionTokens: 32768,
},
{
ID: "kimi-k2-thinking",
Object: "model",
Created: 1762387200, // 2025-11-06
OwnedBy: "moonshot",
Type: "kimi",
DisplayName: "Kimi K2 Thinking",
Description: "Kimi K2 Thinking - Extended reasoning model",
ContextLength: 131072,
MaxCompletionTokens: 32768,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kimi-k2.5",
Object: "model",
Created: 1769472000, // 2026-01-26
OwnedBy: "moonshot",
Type: "kimi",
DisplayName: "Kimi K2.5",
Description: "Kimi K2.5 - Latest Moonshot AI coding model with improved capabilities",
ContextLength: 131072,
MaxCompletionTokens: 32768,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
}
}
Reference in New Issue View Git Blame Copy Permalink