Files
CLIProxyAPI/internal/registry/models/models.json
Luis Pater 09179a707f feat(registry): add "max" level and remove deprecated Gemini models
- Added a new "max" level to model `thinking.levels` for enhanced customization.
- Removed deprecated Gemini 3 Pro (High/Low) models and associated fields from the registry.
- Simplified `thinking` attribute structure for `grok-build-0.1` and `grok-composer-2.5-fast` models.

Closes: #3901
2026-06-20 14:22:29 +08:00

1975 lines
51 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"claude": [
{
"id": "claude-haiku-4-5-20251001",
"object": "model",
"created": 1759276800,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.5 Haiku",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true
}
},
{
"id": "claude-sonnet-4-5-20250929",
"object": "model",
"created": 1759104000,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.5 Sonnet",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true
}
},
{
"id": "claude-sonnet-4-6",
"object": "model",
"created": 1771372800,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.6 Sonnet",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true,
"levels": [
"low",
"medium",
"high",
"max"
]
}
},
{
"id": "claude-opus-4-6",
"object": "model",
"created": 1770318000,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.6 Opus",
"description": "Premium model combining maximum intelligence with practical performance",
"context_length": 1000000,
"max_completion_tokens": 128000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true,
"levels": [
"low",
"medium",
"high",
"max"
]
}
},
{
"id": "claude-opus-4-7",
"object": "model",
"created": 1776297600,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude Opus 4.7",
"description": "Premium model combining maximum intelligence with practical performance",
"context_length": 1000000,
"max_completion_tokens": 128000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true,
"levels": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
},
{
"id": "claude-opus-4-8",
"object": "model",
"created": 1779984000,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude Opus 4.8",
"description": "Premium model combining maximum intelligence with practical performance",
"context_length": 1000000,
"max_completion_tokens": 128000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true,
"levels": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
},
{
"id": "claude-fable-5",
"object": "model",
"created": 1781049600,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude Fable 5",
"description": "Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work",
"context_length": 1000000,
"max_completion_tokens": 128000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true,
"levels": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
},
{
"id": "claude-opus-4-5-20251101",
"object": "model",
"created": 1761955200,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.5 Opus",
"description": "Premium model combining maximum intelligence with practical performance",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 128000,
"zero_allowed": true
}
},
{
"id": "claude-opus-4-1-20250805",
"object": "model",
"created": 1722945600,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4.1 Opus",
"context_length": 200000,
"max_completion_tokens": 32000,
"thinking": {
"min": 1024,
"max": 128000
}
},
{
"id": "claude-opus-4-20250514",
"object": "model",
"created": 1715644800,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4 Opus",
"context_length": 200000,
"max_completion_tokens": 32000,
"thinking": {
"min": 1024,
"max": 128000
}
},
{
"id": "claude-sonnet-4-20250514",
"object": "model",
"created": 1715644800,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 4 Sonnet",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 128000
}
},
{
"id": "claude-3-7-sonnet-20250219",
"object": "model",
"created": 1708300800,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 3.7 Sonnet",
"context_length": 128000,
"max_completion_tokens": 8192,
"thinking": {
"min": 1024,
"max": 128000
}
},
{
"id": "claude-3-5-haiku-20241022",
"object": "model",
"created": 1729555200,
"owned_by": "anthropic",
"type": "claude",
"display_name": "Claude 3.5 Haiku",
"context_length": 128000,
"max_completion_tokens": 8192
}
],
"gemini": [
{
"id": "gemini-2.5-pro",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Pro",
"name": "models/gemini-2.5-pro",
"version": "2.5",
"description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash",
"name": "models/gemini-2.5-flash",
"version": "001",
"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": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash-lite",
"object": "model",
"created": 1753142400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash Lite",
"name": "models/gemini-2.5-flash-lite",
"version": "2.5",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-3-pro-preview",
"object": "model",
"created": 1737158400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Pro Preview",
"name": "models/gemini-3-pro-preview",
"version": "3.0",
"description": "Gemini 3 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"high"
]
}
},
{
"id": "gemini-3.1-pro-preview",
"object": "model",
"created": 1771459200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Pro Preview",
"name": "models/gemini-3.1-pro-preview",
"version": "3.1",
"description": "Gemini 3.1 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-flash-image-preview",
"object": "model",
"created": 1771459200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Flash Image Preview",
"name": "models/gemini-3.1-flash-image-preview",
"version": "3.1",
"description": "Gemini 3.1 Flash Image Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"high"
]
}
},
{
"id": "gemini-3-flash-preview",
"object": "model",
"created": 1765929600,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Flash Preview",
"name": "models/gemini-3-flash-preview",
"version": "3.0",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-flash-lite-preview",
"object": "model",
"created": 1776288000,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Flash Lite Preview",
"name": "models/gemini-3.1-flash-lite-preview",
"version": "3.1",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"high"
]
}
},
{
"id": "gemini-3-pro-image-preview",
"object": "model",
"created": 1737158400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Pro Image Preview",
"name": "models/gemini-3-pro-image-preview",
"version": "3.0",
"description": "Gemini 3 Pro Image Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"high"
]
}
},
{
"id": "gemini-3.5-flash",
"object": "model",
"created": 1779235200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.5 Flash",
"name": "models/gemini-3.5-flash",
"version": "3.5",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
}
],
"vertex": [
{
"id": "gemini-2.5-pro",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Pro",
"name": "models/gemini-2.5-pro",
"version": "2.5",
"description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash",
"name": "models/gemini-2.5-flash",
"version": "001",
"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": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash-image",
"object": "model",
"created": 1763596800,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash Image",
"name": "models/gemini-2.5-flash-image",
"version": "001",
"description": "Our state-of-the-art image generation and editing model.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash-lite",
"object": "model",
"created": 1753142400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash Lite",
"name": "models/gemini-2.5-flash-lite",
"version": "2.5",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-3-pro-preview",
"object": "model",
"created": 1737158400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Pro Preview",
"name": "models/gemini-3-pro-preview",
"version": "3.0",
"description": "Gemini 3 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"high"
]
}
},
{
"id": "gemini-3-flash-preview",
"object": "model",
"created": 1765929600,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Flash Preview",
"name": "models/gemini-3-flash-preview",
"version": "3.0",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-pro-preview",
"object": "model",
"created": 1771459200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Pro Preview",
"name": "models/gemini-3.1-pro-preview",
"version": "3.1",
"description": "Gemini 3.1 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-flash-image-preview",
"object": "model",
"created": 1771459200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Flash Image Preview",
"name": "models/gemini-3.1-flash-image-preview",
"version": "3.1",
"description": "Gemini 3.1 Flash Image Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"high"
]
}
},
{
"id": "gemini-3.1-flash-lite-preview",
"object": "model",
"created": 1776288000,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Flash Lite Preview",
"name": "models/gemini-3.1-flash-lite-preview",
"version": "3.1",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3-pro-image-preview",
"object": "model",
"created": 1737158400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Pro Image Preview",
"name": "models/gemini-3-pro-image-preview",
"version": "3.0",
"description": "Gemini 3 Pro Image Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"low",
"high"
]
}
},
{
"id": "imagen-4.0-generate-001",
"object": "model",
"created": 1750000000,
"owned_by": "google",
"type": "gemini",
"display_name": "Imagen 4.0 Generate",
"name": "models/imagen-4.0-generate-001",
"version": "4.0",
"description": "Imagen 4.0 image generation model",
"supportedGenerationMethods": [
"predict"
]
},
{
"id": "imagen-4.0-ultra-generate-001",
"object": "model",
"created": 1750000000,
"owned_by": "google",
"type": "gemini",
"display_name": "Imagen 4.0 Ultra Generate",
"name": "models/imagen-4.0-ultra-generate-001",
"version": "4.0",
"description": "Imagen 4.0 Ultra high-quality image generation model",
"supportedGenerationMethods": [
"predict"
]
},
{
"id": "imagen-3.0-generate-002",
"object": "model",
"created": 1740000000,
"owned_by": "google",
"type": "gemini",
"display_name": "Imagen 3.0 Generate",
"name": "models/imagen-3.0-generate-002",
"version": "3.0",
"description": "Imagen 3.0 image generation model",
"supportedGenerationMethods": [
"predict"
]
},
{
"id": "imagen-3.0-fast-generate-001",
"object": "model",
"created": 1740000000,
"owned_by": "google",
"type": "gemini",
"display_name": "Imagen 3.0 Fast Generate",
"name": "models/imagen-3.0-fast-generate-001",
"version": "3.0",
"description": "Imagen 3.0 fast image generation model",
"supportedGenerationMethods": [
"predict"
]
},
{
"id": "imagen-4.0-fast-generate-001",
"object": "model",
"created": 1750000000,
"owned_by": "google",
"type": "gemini",
"display_name": "Imagen 4.0 Fast Generate",
"name": "models/imagen-4.0-fast-generate-001",
"version": "4.0",
"description": "Imagen 4.0 fast image generation model",
"supportedGenerationMethods": [
"predict"
]
},
{
"id": "gemini-3.5-flash",
"object": "model",
"created": 1779235200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.5 Flash",
"name": "models/gemini-3.5-flash",
"version": "3.5",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
}
],
"aistudio": [
{
"id": "gemini-2.5-pro",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Pro",
"name": "models/gemini-2.5-pro",
"version": "2.5",
"description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash",
"name": "models/gemini-2.5-flash",
"version": "001",
"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": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash-lite",
"object": "model",
"created": 1753142400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash Lite",
"name": "models/gemini-2.5-flash-lite",
"version": "2.5",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-3-pro-preview",
"object": "model",
"created": 1737158400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Pro Preview",
"name": "models/gemini-3-pro-preview",
"version": "3.0",
"description": "Gemini 3 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-3.1-pro-preview",
"object": "model",
"created": 1771459200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Pro Preview",
"name": "models/gemini-3.1-pro-preview",
"version": "3.1",
"description": "Gemini 3.1 Pro Preview",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-3-flash-preview",
"object": "model",
"created": 1765929600,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3 Flash Preview",
"name": "models/gemini-3-flash-preview",
"version": "3.0",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-3.1-flash-lite-preview",
"object": "model",
"created": 1776288000,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.1 Flash Lite Preview",
"name": "models/gemini-3.1-flash-lite-preview",
"version": "3.1",
"description": "Our smallest and most cost effective model, built for at scale usage.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-pro-latest",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini Pro Latest",
"name": "models/gemini-pro-latest",
"version": "2.5",
"description": "Latest release of Gemini Pro",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true
}
},
{
"id": "gemini-flash-latest",
"object": "model",
"created": 1750118400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini Flash Latest",
"name": "models/gemini-flash-latest",
"version": "2.5",
"description": "Latest release of Gemini Flash",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-flash-lite-latest",
"object": "model",
"created": 1753142400,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini Flash-Lite Latest",
"name": "models/gemini-flash-lite-latest",
"version": "2.5",
"description": "Latest release of Gemini Flash-Lite",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 512,
"max": 24576,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-2.5-flash-image",
"object": "model",
"created": 1759363200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 2.5 Flash Image",
"name": "models/gemini-2.5-flash-image",
"version": "2.5",
"description": "State-of-the-art image generation and editing model.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
]
},
{
"id": "gemini-3.5-flash",
"object": "model",
"created": 1779235200,
"owned_by": "google",
"type": "gemini",
"display_name": "Gemini 3.5 Flash",
"name": "models/gemini-3.5-flash",
"version": "3.5",
"description": "Our most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent"
],
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
}
],
"codex-free": [
{
"id": "gpt-5.4-mini",
"object": "model",
"created": 1773705600,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4 Mini",
"version": "gpt-5.4-mini",
"description": "GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.",
"context_length": 400000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.5",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.5",
"version": "gpt-5.5",
"description": "Frontier model for complex coding, research, and real-world work.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "codex-auto-review",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "Codex Auto Review",
"version": "Codex Auto Review",
"description": "Automatic approval review model for Codex.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
}
],
"codex-team": [
{
"id": "gpt-5.4",
"object": "model",
"created": 1772668800,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4",
"version": "gpt-5.4",
"description": "Stable version of GPT 5.4",
"context_length": 1050000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.4-mini",
"object": "model",
"created": 1773705600,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4 Mini",
"version": "gpt-5.4-mini",
"description": "GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.",
"context_length": 400000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.5",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.5",
"version": "gpt-5.5",
"description": "Frontier model for complex coding, research, and real-world work.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "codex-auto-review",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "Codex Auto Review",
"version": "Codex Auto Review",
"description": "Automatic approval review model for Codex.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
}
],
"codex-plus": [
{
"id": "gpt-5.3-codex-spark",
"object": "model",
"created": 1770912000,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.3 Codex Spark",
"version": "gpt-5.3",
"description": "Ultra-fast coding model.",
"context_length": 128000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.4",
"object": "model",
"created": 1772668800,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4",
"version": "gpt-5.4",
"description": "Stable version of GPT 5.4",
"context_length": 1050000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.4-mini",
"object": "model",
"created": 1773705600,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4 Mini",
"version": "gpt-5.4-mini",
"description": "GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.",
"context_length": 400000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.5",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.5",
"version": "gpt-5.5",
"description": "Frontier model for complex coding, research, and real-world work.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "codex-auto-review",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "Codex Auto Review",
"version": "Codex Auto Review",
"description": "Automatic approval review model for Codex.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
}
],
"codex-pro": [
{
"id": "gpt-5.3-codex-spark",
"object": "model",
"created": 1770912000,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.3 Codex Spark",
"version": "gpt-5.3",
"description": "Ultra-fast coding model.",
"context_length": 128000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.4",
"object": "model",
"created": 1772668800,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4",
"version": "gpt-5.4",
"description": "Stable version of GPT 5.4",
"context_length": 1050000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.4-mini",
"object": "model",
"created": 1773705600,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.4 Mini",
"version": "gpt-5.4-mini",
"description": "GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.",
"context_length": 400000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "gpt-5.5",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "GPT 5.5",
"version": "gpt-5.5",
"description": "Frontier model for complex coding, research, and real-world work.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
},
{
"id": "codex-auto-review",
"object": "model",
"created": 1776902400,
"owned_by": "openai",
"type": "openai",
"display_name": "Codex Auto Review",
"version": "Codex Auto Review",
"description": "Automatic approval review model for Codex.",
"context_length": 272000,
"max_completion_tokens": 128000,
"supported_parameters": [
"tools"
],
"thinking": {
"levels": [
"low",
"medium",
"high",
"xhigh"
]
}
}
],
"kimi": [
{
"id": "kimi-k2",
"object": "model",
"created": 1752192000,
"owned_by": "moonshot",
"type": "kimi",
"display_name": "Kimi K2",
"description": "Kimi K2 - Moonshot AI's flagship coding model",
"context_length": 131072,
"max_completion_tokens": 32768
},
{
"id": "kimi-k2-thinking",
"object": "model",
"created": 1762387200,
"owned_by": "moonshot",
"type": "kimi",
"display_name": "Kimi K2 Thinking",
"description": "Kimi K2 Thinking - Extended reasoning model",
"context_length": 131072,
"max_completion_tokens": 32768,
"thinking": {
"min": 1024,
"max": 32000,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "kimi-k2.5",
"object": "model",
"created": 1769472000,
"owned_by": "moonshot",
"type": "kimi",
"display_name": "Kimi K2.5",
"description": "Kimi K2.5 - Latest Moonshot AI coding model with improved capabilities",
"context_length": 131072,
"max_completion_tokens": 32768,
"thinking": {
"min": 1024,
"max": 32000,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "kimi-k2.6",
"object": "model",
"created": 1776729600,
"owned_by": "moonshot",
"type": "kimi",
"display_name": "Kimi K2.6",
"description": "Kimi K2.6 - Latest Moonshot AI coding model with improved capabilities",
"context_length": 262144,
"max_completion_tokens": 65536,
"thinking": {
"min": 1024,
"max": 32000,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "kimi-k2.7-code",
"object": "model",
"created": 1780396800,
"owned_by": "moonshot",
"type": "kimi",
"display_name": "Kimi K2.7 Code",
"description": "Kimi K2.7 Code - Moonshot AI's latest coding-focused model",
"context_length": 262144,
"max_completion_tokens": 65536,
"thinking": {
"min": 1024,
"max": 32000,
"zero_allowed": false,
"dynamic_allowed": true
}
}
],
"antigravity": [
{
"id": "claude-opus-4-6-thinking",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Claude Opus 4.6 (Thinking)",
"name": "claude-opus-4-6-thinking",
"description": "Claude Opus 4.6 (Thinking)",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 64000,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "claude-sonnet-4-6",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Claude Sonnet 4.6 (Thinking)",
"name": "claude-sonnet-4-6",
"description": "Claude Sonnet 4.6 (Thinking)",
"context_length": 200000,
"max_completion_tokens": 64000,
"thinking": {
"min": 1024,
"max": 64000,
"zero_allowed": true,
"dynamic_allowed": true
}
},
{
"id": "gemini-3-flash",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3 Flash",
"name": "gemini-3-flash",
"description": "Gemini 3 Flash",
"context_length": 1048576,
"max_completion_tokens": 65536,
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3-flash-agent",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.5 Flash",
"name": "gemini-3-flash-agent",
"description": "Gemini 3.5 Flash",
"context_length": 1048576,
"max_completion_tokens": 65536,
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-flash-image",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.1 Flash Image",
"name": "gemini-3.1-flash-image",
"description": "Gemini 3.1 Flash Image",
"thinking": {
"min": 128,
"max": 32768,
"dynamic_allowed": true,
"levels": [
"minimal",
"high"
]
}
},
{
"id": "gemini-pro-agent",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.1 Pro (High)",
"name": "gemini-pro-agent",
"description": "Gemini 3.1 Pro (High)",
"context_length": 1048576,
"max_completion_tokens": 65535,
"thinking": {
"min": 1,
"max": 65535,
"dynamic_allowed": true,
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.1-pro-low",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.1 Pro (Low)",
"name": "gemini-3.1-pro-low",
"description": "Gemini 3.1 Pro (Low)",
"context_length": 1048576,
"max_completion_tokens": 65535,
"thinking": {
"min": 1,
"max": 65535,
"dynamic_allowed": true,
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "gpt-oss-120b-medium",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "GPT-OSS 120B (Medium)",
"name": "gpt-oss-120b-medium",
"description": "GPT-OSS 120B (Medium)",
"context_length": 114000,
"max_completion_tokens": 32768
},
{
"id": "gemini-3.1-flash-lite",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.1 Flash Lite",
"name": "gemini-3.1-flash-lite",
"description": "Gemini 3.1 Flash Lite",
"context_length": 1048576,
"max_completion_tokens": 65535,
"thinking": {
"min": 1,
"max": 65535,
"zero_allowed": true,
"dynamic_allowed": true,
"levels": [
"minimal",
"low",
"medium",
"high"
]
}
},
{
"id": "gemini-3.5-flash-low",
"object": "model",
"owned_by": "antigravity",
"type": "antigravity",
"display_name": "Gemini 3.5 Flash (Low)",
"name": "gemini-3.5-flash-low",
"description": "Gemini 3.5 Flash (Low)",
"context_length": 1048576,
"max_completion_tokens": 65535,
"thinking": {
"min": 1,
"max": 65535,
"dynamic_allowed": true,
"levels": [
"low",
"medium",
"high"
]
}
}
],
"xai": [
{
"id": "grok-build-0.1",
"object": "model",
"created": 1779321600,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok Build 0.1",
"name": "grok-build-0.1",
"description": "Grok Build 0.1 is xAIs fast coding model trained specifically for agentic software engineering workflows.",
"context_length": 256000,
"max_completion_tokens": 256000
},
{
"id": "grok-4.3",
"object": "model",
"created": 1775606400,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 4.3",
"name": "grok-4.3",
"description": "xAI Grok 4.3 model for the Responses API.",
"context_length": 1000000,
"max_completion_tokens": 65536,
"thinking": {
"zero_allowed": true,
"levels": [
"none",
"low",
"medium",
"high"
]
}
},
{
"id": "grok-4.20-0309-reasoning",
"object": "model",
"created": 1773014400,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 4.20 0309 Reasoning",
"name": "grok-4.20-0309-reasoning",
"description": "xAI Grok 4.20 0309 reasoning model for the Responses API.",
"context_length": 2000000,
"max_completion_tokens": 65536
},
{
"id": "grok-4.20-0309-non-reasoning",
"object": "model",
"created": 1773014400,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 4.20 0309 Non Reasoning",
"name": "grok-4.20-0309-non-reasoning",
"description": "xAI Grok 4.20 0309 non-reasoning model for the Responses API.",
"context_length": 2000000,
"max_completion_tokens": 65536
},
{
"id": "grok-4.20-multi-agent-0309",
"object": "model",
"created": 1773014400,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 4.20 Multi Agent 0309",
"name": "grok-4.20-multi-agent-0309",
"description": "xAI Grok 4.20 multi-agent model for the Responses API.",
"context_length": 2000000,
"max_completion_tokens": 65536,
"thinking": {
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "grok-3-mini",
"object": "model",
"created": 1740960000,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 3 Mini",
"name": "grok-3-mini",
"description": "xAI Grok 3 Mini model for the Responses API.",
"context_length": 131072,
"max_completion_tokens": 32768,
"thinking": {
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "grok-3-mini-fast",
"object": "model",
"created": 1740960000,
"owned_by": "xai",
"type": "xai",
"display_name": "Grok 3 Mini Fast",
"name": "grok-3-mini-fast",
"description": "xAI Grok 3 Mini Fast model for the Responses API.",
"context_length": 131072,
"max_completion_tokens": 32768,
"thinking": {
"levels": [
"low",
"medium",
"high"
]
}
},
{
"id": "grok-composer-2.5-fast",
"object": "model",
"created": 1740960000,
"owned_by": "xai",
"type": "xai",
"display_name": "Composer 2.5 Fast",
"name": "grok-composer-2.5-fast",
"description": "xAI Composer 2.5 Fast model for the Responses API.",
"context_length": 200000,
"max_completion_tokens": 32768
}
]
}