Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for baai

BAAI: bge-m3

baai/bge-m3

Model weights

The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.

Modalities
Price
$0.01/M tokens
Context
8K
Released
Nov 18, 2025
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

Text Embedding ModelsCollectionEmbedding Model RankingsRanking
Latency
$0.012.05s
100.00%
$0.010.34s
100.00%
ProviderInput /M
LatencyUptime
  • Favicon for Parasail
    Input $0.01
    Latency 2.05sUptime 100.00%
  • Favicon for DeepInfra
    Input $0.01
    Latency 0.34sUptime 100.00%
Latency
0.34s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.99%

Availability over the last 3 days

Last 72 hours
Availability 99.99%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.99%
Without Routing
91.62%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for https://observant.io/
Observant
new
1.81Btokens
2.
Favicon for https://equibles.local/
Equibles-Self-Hosted
new
1.38Btokens
3.
Favicon for https://gbrain.ai/
GBrain
new
1.32Btokens
4.
Favicon for https://ds.jarviz.ru/
Gradient
new
1.29Btokens
5.
Favicon for https://eliza.local/
eliza-trainer
new
862Mtokens
Rest of OpenRouter
4.94B
Top 5 Apps
323M

Frequently asked questions

The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.

bge-m3 costs $0.01/M tokens.

bge-m3 accepts up to 8,194 tokens per input. Longer text has to be split into multiple inputs.

bge-m3 accepts text as input and returns embedding vectors.

bge-m3 is served by 2 providers on OpenRouter: Parasail and DeepInfra. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

bge-m3 was released on November 18, 2025.

More models from baai

bge-base-en-v1.5

The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features improved similarity-score distribution and stronger retrieval performance out of the box.

Embeddings$0.005/M tokens
bge-large-en-v1.5

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 in English.

Embeddings$0.01/M tokens