BiomedBERT (PubMedBERT abstract)

EmbeddingsUnavailable

by Microsoftbiomedbert-base-uncased-abstract

Microsoft BiomedBERT (formerly PubMedBERT) pretrained from scratch on PubMed abstracts with a domain-specific vocabulary, rather than adapting a general model. As a feature extractor it gives 768-dim biomedical embeddings and set the original state of the art on the BLURB biomedical NLP benchmark.

See alternatives Compare

Status: Unavailable
Context: 512 tokens
Input → output: Text → Vector
Developer: Microsoft
Updated: 23 September 2026

BiomedBERT (PubMedBERT abstract) is currently unavailable

You can still read the details on this page. Pick one of the available alternatives below to run a comparable model right away.

Go to alternatives

Comparable models

All in this category

OpenAI text-embedding-3-largeOpenAI
OpenAI's highest-quality embedding model. Returns 3072-dim vectors by default and supports reducing dimensions via the dimensions parameter. Outperforms text-embedding-3-small and the older ada-002 on MTEB and multilingual MIRACL retrieval benchmarks, for cases where accuracy matters more than cost.
US$0.156/1M in
Compare BiomedBERT (PubMedBERT abstract) vs. OpenAI text-embedding-3-large
OpenAI text-embedding-3-smallOpenAI
OpenAI's small, low-cost embedding model. Returns 1536-dim vectors by default and supports shortening output dimensions via the dimensions parameter without retraining. Replaced text-embedding-ada-002 with better retrieval quality at a fraction of the price, and is the default choice for general-purpose semantic search and RAG.
US$0.024/1M in
Compare BiomedBERT (PubMedBERT abstract) vs. OpenAI text-embedding-3-small

Playground

Try BiomedBERT (PubMedBERT abstract)

Input & output

Currently unavailable

Currently unavailable.

The playground is disabled. You can find comparable models in the same category: Browse alternatives

Text

0 / 4,000

Biomedical text to embed

Compare with (optional)

Runs the model twice (billed twice).

⌘/Ctrl + Enter

Output

The vector appears here.

This run

No price – currently unavailable.

New here?

10 free credits (US$0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.

About BiomedBERT (PubMedBERT abstract)

TL;DRAs of 23 September 2026

BiomedBERT (PubMedBERT abstract) is a model by Microsoft in the Embeddings category. BiomedBERT (PubMedBERT abstract) is currently not available on Railwail. The context window holds 512 tokens.

BiomedBERT, originally released as PubMedBERT, was trained from random initialization purely on biomedical text from PubMed, with its vocabulary learned from that same corpus. Microsoft's research showed that domain-specific pretraining from scratch beats continual pretraining of general BERT for biomedicine, and the model topped the BLURB benchmark. This abstract-only checkpoint is the most widely used variant. Through the Hugging Face feature-extraction pipeline it returns contextual token embeddings; mean-pool or take [CLS] for sentence and document vectors.

Pricing

Currently unavailable. There is no price for this model at the moment, so it cannot be run.

API

Call BiomedBERT (PubMedBERT abstract) with your Railwail API key. Use this model ID in the request:

biomedbert-base-uncased-abstractAPI documentation Get an API key

Currently unavailable

The model has no verified price or is deactivated; API calls are refused.

Specifications

Model ID: biomedbert-base-uncased-abstract
Developer: Microsoft
Category: Embeddings
Input: Text
Output: Vector
Context window: 512 tokens
Catalog entry updated: 23 September 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

ParameterTypeDefaultAllowed values

inputsrequired
Biomedical text to embed
Type: Text
Default: –
Allowed values: up to 4,000 characters

Use cases

Related guides

Embedding Models for Search & Science

All models in Embeddings

Frequently asked questions

What is BiomedBERT (PubMedBERT abstract)?

BiomedBERT (PubMedBERT abstract) is a model by Microsoft in the Embeddings category. It is listed on Railwail but cannot be run at the moment.

How much does BiomedBERT (PubMedBERT abstract) cost on Railwail?

BiomedBERT (PubMedBERT abstract) cannot be run on Railwail at the moment, so there is no current price. Available alternatives with prices are listed further down this page.

What is the context window of BiomedBERT (PubMedBERT abstract)?

The context window of BiomedBERT (PubMedBERT abstract) holds 512 tokens.

How fast is BiomedBERT (PubMedBERT abstract)?

There are not enough measured runs of BiomedBERT (PubMedBERT abstract) on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is BiomedBERT (PubMedBERT abstract) better than OpenAI text-embedding-3-large?

That depends on the task. BiomedBERT (PubMedBERT abstract) (Microsoft) and OpenAI text-embedding-3-large (OpenAI) are both models in the Embeddings category. The comparison page shows their prices and specifications side by side.

Compare BiomedBERT (PubMedBERT abstract) and OpenAI text-embedding-3-large

Can I use BiomedBERT (PubMedBERT abstract) right now?

Currently unavailable. The page stays online; available alternatives from the same category are listed further down.

All models through one API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.

Get API key Browse all models