baai
BAAI: bge-large-en-v1.5
baai/bge-large-en-v1.5
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
BAAI's bge-large-en-v1.5 is a text embedding model that, per the OpenRouter catalog, maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, with text input, embedding output, and a 512-token context window. The Hugging Face model card reports MTEB evaluation results spanning retrieval, classification, clustering, reranking, and semantic textual similarity tasks, indicating measured rather than merely claimed performance across standard English benchmarks. The card is tagged for sentence-transformers, feature extraction, and sentence similarity. It is an embeddings-only model and does not generate text.[1][2]
Strengths
- The Hugging Face model card publishes measured MTEB results across many English tasks, including retrieval, classification, clustering, reranking, and semantic similarity, giving broad benchmark coverage rather than vendor claims alone.[2]
- According to the OpenRouter catalog, it produces 1024-dimensional dense embeddings described as suited to semantic search, document retrieval, and downstream NLP tasks.[1]
- The model card is tagged for the sentence-transformers ecosystem and feature-extraction use, which typically eases integration into standard embedding pipelines.[2]
Limitations
- The catalog describes it as an English model; performance in other languages is not covered by this evidence.[1]
- A 512-token context window means longer texts require chunking or truncation before embedding.[1]
- Evidence gaps remain: license terms, parameter count, and hardware needs are absent from this pack, and the retrieved model card text is truncated, so validate on your own workload before adopting.[1][2]
Where to use it
- Worth considering for English semantic search and document retrieval, matching both the catalog's stated optimization and the measured MTEB retrieval results.[1][2]
- A candidate for sentence-similarity and feature-extraction pipelines that consume dense English embeddings.[1][2]
- May serve as an embedding stage in retrieval-augmented systems where passages fit the 512-token context.[1]
Sources
- [1] OpenRouter catalog · BAAI: bge-large-en-v1.5Sources checked: Nov 13, 2026
- [2] Model documentation · BAAI: bge-large-en-v1.5Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks...
Specifications
- Model ID
- baai/bge-large-en-v1.5
- Canonical ID
- baai/bge-large-en-v1.5-20251117
- Creator
- baai
- Added to OpenRouter
- 18.11.2025
- Context length
- 512
- Modality
- text->embeddings
- Input modalities
- text
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.010 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfra | 512 | $0.010 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.