ESM-2 650M (Protein Embeddings)

EmbeddingsUnavailable

by Metaesm2-650m-protein-embeddings

Meta AI 650M-parameter protein language model trained on UniRef50 sequences. Feed it an amino-acid sequence and the per-residue hidden states act as learned protein embeddings, used for structure prediction, variant-effect and function tasks. This 33-layer checkpoint is the common balance of quality and cost in the ESM-2 family.

See alternatives Compare

Status: Unavailable
Context: 1,024 tokens
Input → output: Text → Vector
Developer: Meta
Updated: 23 September 2026

ESM-2 650M (Protein Embeddings) 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 ESM-2 650M (Protein Embeddings) 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 ESM-2 650M (Protein Embeddings) vs. OpenAI text-embedding-3-small

Playground

Try ESM-2 650M (Protein Embeddings)

Input & output

Currently unavailable

Currently unavailable.

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

Protein Sequence

0 / 1,024

Amino-acid sequence (single-letter codes) 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 ESM-2 650M (Protein Embeddings)

TL;DRAs of 23 September 2026

ESM-2 650M (Protein Embeddings) is a model by Meta in the Embeddings category. ESM-2 650M (Protein Embeddings) is currently not available on Railwail. The context window holds 1,024 tokens.

ESM-2 is a transformer protein language model from Meta AI (FAIR) trained with masked language modeling over millions of protein sequences from UniRef. Its internal representations capture structural and functional properties of proteins, which is why ESM-2 embeddings power downstream tools including ESMFold structure prediction. The 650M t33 checkpoint sits between the small research models and the 3B/15B versions. Run through the Hugging Face feature-extraction pipeline on an amino-acid string to obtain per-residue embedding vectors (1280 dims), which are typically mean-pooled for a whole-protein embedding.

Pricing

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

API

Call ESM-2 650M (Protein Embeddings) with your Railwail API key. Use this model ID in the request:

esm2-650m-protein-embeddingsAPI documentation Get an API key

Currently unavailable

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

Specifications

Model ID: esm2-650m-protein-embeddings
Developer: Meta
Category: Embeddings
Input: Text
Output: Vector
Context window: 1,024 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
Amino-acid sequence (single-letter codes) to embed
Type: Text
Default: –
Allowed values: up to 1,024 characters

Use cases

Related guides

Embedding Models for Search & Science

All models in Embeddings

Frequently asked questions

What is ESM-2 650M (Protein Embeddings)?

ESM-2 650M (Protein Embeddings) is a model by Meta in the Embeddings category. It is listed on Railwail but cannot be run at the moment.

How much does ESM-2 650M (Protein Embeddings) cost on Railwail?

ESM-2 650M (Protein Embeddings) 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 ESM-2 650M (Protein Embeddings)?

The context window of ESM-2 650M (Protein Embeddings) holds 1,024 tokens.

How fast is ESM-2 650M (Protein Embeddings)?

There are not enough measured runs of ESM-2 650M (Protein Embeddings) on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is ESM-2 650M (Protein Embeddings) better than OpenAI text-embedding-3-large?

That depends on the task. ESM-2 650M (Protein Embeddings) (Meta) 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 ESM-2 650M (Protein Embeddings) and OpenAI text-embedding-3-large

Can I use ESM-2 650M (Protein Embeddings) 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