AxForge offering
When this offering is available: Qwen3 Embedding behind the OpenAI-compatible /v1/embeddings endpoint, served from hardware AxForge owns in Stockholm. Change base_url, keep your SDK, embed GDPR-sensitive documents in the EU, with zero prompt retention.
Check the console for current access, prices and availability.
Why AxForge
| OpenAI-compatible /v1/embeddings | The standard embeddings shape, so the official OpenAI SDKs work by changing base_url to https://api.axforge.ai/v1 and using the model name qwen3-embed. |
|---|---|
| 1024 dimensions, 32,768-token inputs | Long chunks embed in one call. Pair qwen3-embed for retrieval with Qwen3.8 27B for generation (same API, same key, same EU region) for RAG entirely inside the EU. |
| Built for GDPR-sensitive documents | EU region, EU-hosted hardware and zero prompt retention: every document you send is processed in memory in Stockholm, never persisted, never used for training. |
Specifications
| Model | Qwen3 Embedding: text embedding model, Qwen3 family |
|---|---|
| API model name | qwen3-embed |
| Vector dimensions | 1024 |
| Context window | 32,768 tokens |
| Endpoint | POST /v1/embeddings |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Stockholm, Sweden (eu-se-1) |
| Price | €0.015 / 1M tokens (launch pricing) |
Qwen3 Embedding catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Confirm this offering is available in the console before following the API setup steps below; otherwise add a public request. A request does not activate an endpoint. |
|---|---|
| 2 | Sign in to AxForge. Your API key is created in the console. |
| 3 | Set base_url to https://api.axforge.ai/v1 in the OpenAI SDK you already use. |
| 4 | Call embeddings.create with model qwen3-embed and your text chunks. |
| 5 | Store the 1024-dimensional vectors and pair retrieval with Qwen3.8 27B for generation. |
| 6 | Watch usage in the console; every new account starts with free tokens. |
FAQ
Yes. It is the standard /v1/embeddings shape, so the official OpenAI SDKs work by changing base_url to https://api.axforge.ai/v1. The model name is qwen3-embed.
1024-dimensional vectors, with a 32,768-token context window per input.
In Stockholm, Sweden (eu-se-1), on hardware AxForge owns and operates. TLS terminates in the EU.
Yes, that is exactly what it is built for. EU region, EU-hosted hardware, and zero prompt retention: inputs are processed in memory and never persisted or used for training.
When available, check current pricing in the console. Launch pricing is €0.015 per million input tokens. For committed volume, talk to an engineer.
Yes. Pair qwen3-embed for retrieval with Qwen3.8 27B for generation. Same API, same key, same EU region.