刚试了一下，api 也支持 3 个新模型
gemini api 支持模型
{
"models": [
{
"name": "models/chat-bison-001",
"version": "001",
"displayName": "PaLM 2 Chat (Legacy)",
"description": "A legacy text-only model optimized for chat conversations",
"inputTokenLimit": 4096,
"outputTokenLimit": 1024,
"supportedGenerationMethods": [
"generateMessage",
"countMessageTokens"
],
"temperature": 0.25,
"topP": 0.95,
"topK": 40
},
{
"name": "models/text-bison-001",
"version": "001",
"displayName": "PaLM 2 (Legacy)",
"description": "A legacy model that understands text and generates text as an output",
"inputTokenLimit": 8196,
"outputTokenLimit": 1024,
"supportedGenerationMethods": [
"generateText",
"countTextTokens",
"createTunedTextModel"
],
"temperature": 0.7,
"topP": 0.95,
"topK": 40
},
{
"name": "models/embedding-gecko-001",
"version": "001",
"displayName": "Embedding Gecko",
"description": "Obtain a distributed representation of a text.",
"inputTokenLimit": 1024,
"outputTokenLimit": 1,
"supportedGenerationMethods": [
"embedText",
"countTextTokens"
]
},
{
"name": "models/gemini-1.0-pro-latest",
"version": "001",
"displayName": "Gemini 1.0 Pro Latest",
"description": "The best model for scaling across a wide range of tasks. This is the latest model.",
"inputTokenLimit": 30720,
"outputTokenLimit": 2048,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 0.9,
"topP": 1
},
{
"name": "models/gemini-1.0-pro",
"version": "001",
"displayName": "Gemini 1.0 Pro",
"description": "The best model for scaling across a wide range of tasks",
"inputTokenLimit": 30720,
"outputTokenLimit": 2048,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 0.9,
"topP": 1
},
{
"name": "models/gemini-pro",
"version": "001",
"displayName": "Gemini 1.0 Pro",
"description": "The best model for scaling across a wide range of tasks",
"inputTokenLimit": 30720,
"outputTokenLimit": 2048,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 0.9,
"topP": 1
},
{
"name": "models/gemini-1.0-pro-001",
"version": "001",
"displayName": "Gemini 1.0 Pro 001 (Tuning)",
"description": "The best model for scaling across a wide range of tasks. This is a stable model that supports tuning.",
"inputTokenLimit": 30720,
"outputTokenLimit": 2048,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createTunedModel"
],
"temperature": 0.9,
"topP": 1
},
{
"name": "models/gemini-1.0-pro-vision-latest",
"version": "001",
"displayName": "Gemini 1.0 Pro Vision",
"description": "The best image understanding model to handle a broad range of applications",
"inputTokenLimit": 12288,
"outputTokenLimit": 4096,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 0.4,
"topP": 1,
"topK": 32
},
{
"name": "models/gemini-pro-vision",
"version": "001",
"displayName": "Gemini 1.0 Pro Vision",
"description": "The best image understanding model to handle a broad range of applications",
"inputTokenLimit": 12288,
"outputTokenLimit": 4096,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 0.4,
"topP": 1,
"topK": 32
},
{
"name": "models/gemini-1.5-pro-latest",
"version": "001",
"displayName": "Gemini 1.5 Pro Latest",
"description": "Mid-size multimodal model that supports up to 2 million tokens",
"inputTokenLimit": 2097152,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-pro-001",
"version": "001",
"displayName": "Gemini 1.5 Pro 001",
"description": "Mid-size multimodal model that supports up to 2 million tokens",
"inputTokenLimit": 2097152,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-pro",
"version": "001",
"displayName": "Gemini 1.5 Pro",
"description": "Mid-size multimodal model that supports up to 2 million tokens",
"inputTokenLimit": 2097152,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-pro-exp-0801",
"version": "exp-0801",
"displayName": "Gemini 1.5 Pro Experimental 0801",
"description": "Mid-size multimodal model that supports up to 2 million tokens",
"inputTokenLimit": 2097152,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-pro-exp-0827",
"version": "exp-0827",
"displayName": "Gemini 1.5 Pro Experimental 0827",
"description": "Mid-size multimodal model that supports up to 2 million tokens",
"inputTokenLimit": 2097152,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash-latest",
"version": "001",
"displayName": "Gemini 1.5 Flash Latest",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash-001",
"version": "001",
"displayName": "Gemini 1.5 Flash 001",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createCachedContent"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash-001-tuning",
"version": "001",
"displayName": "Gemini 1.5 Flash 001 Tuning",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 16384,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens",
"createTunedModel"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash",
"version": "001",
"displayName": "Gemini 1.5 Flash",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash-exp-0827",
"version": "exp-0827",
"displayName": "Gemini 1.5 Flash Experimental 0827",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/gemini-1.5-flash-8b-exp-0827",
"version": "001",
"displayName": "Gemini 1.5 Flash 8B Experimental 0827",
"description": "Fast and versatile multimodal model for scaling across diverse tasks",
"inputTokenLimit": 1048576,
"outputTokenLimit": 8192,
"supportedGenerationMethods": [
"generateContent",
"countTokens"
],
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2
},
{
"name": "models/embedding-001",
"version": "001",
"displayName": "Embedding 001",
"description": "Obtain a distributed representation of a text.",
"inputTokenLimit": 2048,
"outputTokenLimit": 1,
"supportedGenerationMethods": [
"embedContent"
]
},
{
"name": "models/text-embedding-004",
"version": "004",
"displayName": "Text Embedding 004",
"description": "Obtain a distributed representation of a text.",
"inputTokenLimit": 2048,
"outputTokenLimit": 1,
"supportedGenerationMethods": [
"embedContent"
]
},
{
"name": "models/aqa",
"version": "001",
"displayName": "Model that performs Attributed Question Answering.",
"description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
"inputTokenLimit": 7168,
"outputTokenLimit": 1024,
"supportedGenerationMethods": [
"generateAnswer"
],
"temperature": 0.2,
"topP": 1,
"topK": 40
}
]
}