mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-05 23:24:05 +08:00
47ecc2a231
## Summary - Verify and populate `content_length` (context window) and `max_output` (max generation tokens) for all **478 chat/vision models** across **47 provider configs** - Data sourced from **official API documentation** via 12 parallel agents + targeted web verification - Update Go test assertions to match verified values Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
61 lines
1.3 KiB
JSON
61 lines
1.3 KiB
JSON
{
|
|
"name": "Replicate",
|
|
"rank": 981,
|
|
"url": {
|
|
"default": "https://api.replicate.com"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "v1/predictions",
|
|
"models": "v1/models"
|
|
},
|
|
"class": "replicate",
|
|
"models": [
|
|
{
|
|
"name": "meta/llama-4-maverick-instruct",
|
|
"content_length": 1048576,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/llama-4-scout-instruct",
|
|
"content_length": 10485760,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/meta-llama-3-70b-instruct",
|
|
"content_length": 8000,
|
|
"max_output": 8000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta/meta-llama-3-8b-instruct",
|
|
"content_length": 8000,
|
|
"max_output": 8000,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "replicate/all-mpnet-base-v2:b6b7585c9640cd7a9572c6e129c9549d79c9c31f0d3fdce7baac7c67ca38f305",
|
|
"max_tokens": 384,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
},
|
|
{
|
|
"name": "ibm-granite/granite-embedding-278m-multilingual:1f76d42a05f120e12272746d5a2d86b525c13420773f795a4cbef9117d8685f1",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
]
|
|
}
|
|
]
|
|
}
|