Compare

Bge-M3 vs Bge-Reranker-Base

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Bge-M3
baai/bge-m3
Bge-Reranker-Base
baai/bge-reranker-base
Provider
BAAI
BAAI
Family
BGE
BGE
Modality
embedding
rerank
Context window
60,000 tok
Max output
Released
2024-05-22
2025-02-14
License
Open-weight
Open-weight
Input price
$0.012 /1M
$0.0010 /1M
Output price
$0.0000 /1M
$0.0000 /1M
Tools
Streaming
Vision
JSON mode
Reasoning
Prompt caching
Batch API
Try it
View model →
View model →
Bge-M3
baai/bge-m3
Full spec →

Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.

Strengths
  • Multi-lingual (100+ languages)
  • Strong on retrieval
  • Open-weight
Use cases
RAGSemantic searchClustering
Bge-Reranker-Base
baai/bge-reranker-base
Full spec →

Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.

Strengths
  • High-precision result ordering
  • Cross-encoder quality
Use cases
Two-stage retrievalRAG result ordering

Compare with another

Bge-M3 vs Bge-Small-EN-V1.5
baai/bge-m3 · baai/bge-small-en-v1.5
Bge-Base-EN-V1.5 vs Bge-M3
baai/bge-base-en-v1.5 · baai/bge-m3
Bge-Large-EN-V1.5 vs Bge-M3
baai/bge-large-en-v1.5 · baai/bge-m3
Bge-Reranker-Base vs Bge-Small-EN-V1.5
baai/bge-reranker-base · baai/bge-small-en-v1.5
Bge-Base-EN-V1.5 vs Bge-Reranker-Base
baai/bge-base-en-v1.5 · baai/bge-reranker-base
Bge-Large-EN-V1.5 vs Bge-Reranker-Base
baai/bge-large-en-v1.5 · baai/bge-reranker-base
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Bge-M3
client.chat.completions.create(
    model="baai/bge-m3",
    messages=[{"role":"user","content":"hello"}],
)

# Bge-Reranker-Base
client.chat.completions.create(
    model="baai/bge-reranker-base",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →