bge-m3 by Cloudflare Workers AI
Every Cloudflare account gets 10,000 neurons a day free across all Workers AI models, reset at 00:00 UTC. Create an API token with Workers AI permission and call the OpenAI-compatible endpoint with your account ID.
Using this model in production?
We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps. Book a free 30-minute call.
Frequently asked
Is bge-m3 free?
Yes. Cloudflare Workers AI offers it as Free API tier with these limits: 10K neurons/day (shared). No credit card is required.
Can I use bge-m3 commercially?
Commercial terms are not clearly documented. Check the provider's current terms before shipping.
How do I start using bge-m3?
Get a free API key from the provider dashboard. Set the base URL to https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1 and the model to @cf/baai/bge-m3. Every Cloudflare account gets 10,000 neurons a day free across all Workers AI models, reset at 00:00 UTC. Create an API token with Workers AI permission and call the OpenAI-compatible endpoint with your account ID.
Free monthly update
The monthly free-models update
What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.
Related free models
- + 90 more models (NVIDIA NIM) · Prototyping only · rate limits not published
- Qwen3 Embedding 8B (Scaleway) · First 1M tokens free (shared) · then paid
- bge-multilingual-gemma2 (being retired, EOL Jan 21 2027) (OVHcloud AI Endpoints) · 2 RPM per IP (no key)
- bge-m3 (OVHcloud AI Endpoints) · 2 RPM per IP (no key)
- Qwen3-Embedding-8B (OVHcloud AI Endpoints) · 2 RPM per IP (no key)
- bge-multilingual-gemma2 (Scaleway) · First 1M tokens free (shared) · then paid