support@biolm.ai
+916-209-0473
Usage-Based Pricing. Pay only for what you use, by the second. Each of our model deployments has been optimized at the software and hardware levels, ensuring you get maximum throughput at the lowest cost.
| Model | Cost (USD/sec) |
|---|---|
| Loading pricing data... | |
curl --location https://biolm.ai/api/v2/esm1v-n1/predict/ \
--header "Authorization: Token $BIOLMAI_TOKEN" \
--header "Content-Type: application/json" \
--data '{"items":[{"sequence":"QERLEUTGR<mask>SLYNIVAT"}]}'{
"results": [
[
{
"token": 4,
"token_str": "L",
"score": 0.10017549991607666,
"sequence": "Q E R L E U T G R L S L Y N I V A T"
},
{
"token": 8,
"token_str": "S",
"score": 0.07921414822340012,
"sequence": "Q E R L E U T G R S S L Y N I V A T"
},
{
"token": 10,
"token_str": "R",
"score": 0.0782080590724945,
"sequence": "Q E R L E U T G R R S L Y N I V A T"
}
]
]
}Finetuning New Models. At the heart of each project is training task-specific classifiers, regressors, and more. For leading LLMs, we provide finetuning pipelines with DeepSpeed, PB2 or ASHA, and the ability to hyperopt for various metrics like precision, recall, f1, loss, or accuracy. Or you can use our embeddings APIs to train models like XGBoost on a variety of features.
Guides
Loading...
Our APIs
Loading...
