93 lines
3.1 KiB
JSON
93 lines
3.1 KiB
JSON
[
|
|
{
|
|
"model": "gemini-1.5-flash",
|
|
"object": "model",
|
|
"name": "Gemini 1.5 Flash",
|
|
"version": "1.0",
|
|
"description": "Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks.",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-1.5-flash-8b",
|
|
"object": "model",
|
|
"name": "Gemini 1.5 Flash-8B",
|
|
"version": "1.0",
|
|
"description": "Gemini 1.5 Flash-8B is a small model designed for lower intelligence tasks.",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-1.5-pro",
|
|
"object": "model",
|
|
"name": "Gemini 1.5 Pro",
|
|
"version": "1.0",
|
|
"description": "Gemini 1.5 Pro is a mid-size multimodal model that is optimized for a wide-range of reasoning tasks. 1.5 Pro can process large amounts of data at once, including 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages of text. ",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-2.5-pro-preview-05-06",
|
|
"object": "model",
|
|
"name": "Gemini 2.5 Pro Preview",
|
|
"version": "1.0",
|
|
"description": "Gemini 2.5 Pro is our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context. Gemini 2.5 Pro rate limits are more restricted since it is an experimental / preview model.",
|
|
"inference_params": {
|
|
"max_tokens": 65536,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-2.5-flash-preview-04-17",
|
|
"object": "model",
|
|
"name": "Our best model in terms of price-performance, offering well-rounded capabilities. Gemini 2.5 Flash rate limits are more restricted since it is an experimental / preview model.",
|
|
"version": "1.0",
|
|
"description": "Gemini 2.5 Flash preview",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-2.0-flash",
|
|
"object": "model",
|
|
"name": "Gemini 2.0 Flash",
|
|
"version": "1.0",
|
|
"description": "Gemini 2.0 Flash delivers next-gen features and improved capabilities, including superior speed, native tool use, multimodal generation, and a 1M token context window.",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
},
|
|
{
|
|
"model": "gemini-2.0-flash-lite",
|
|
"object": "model",
|
|
"name": "Gemini 2.0 Flash-Lite",
|
|
"version": "1.0",
|
|
"description": "A Gemini 2.0 Flash model optimized for cost efficiency and low latency.",
|
|
"inference_params": {
|
|
"max_tokens": 8192,
|
|
"temperature": 0.6,
|
|
"stream": true
|
|
},
|
|
"engine": "google_gemini"
|
|
}
|
|
] |