Models & pricing
One key serves every model below, from Stockholm, Sweden (eu-se-1). Pass the API model name in the
model field of the matching endpoint. Prices are per-use, in
EUR. Every new account includes 3M free serverless tokens every 30 days.
Available on the serverless API
| Model | Endpoint | API model name | Context | Price |
|---|---|---|---|---|
| Qwen3.8 27B | /v1/chat/completions | qwen3.8-27b | 262,144 | €0.12 / 1M in · €0.62 / 1M out |
| GLM-5.3-Flash | /v1/chat/completions | glm-5.3-flash | 262,144 | €0.12 / 1M in · €0.62 / 1M out |
| MiMo-V2.6-Flash | /v1/chat/completions | mimo-v2.6-flash | 262,144 | €0.12 / 1M in · €0.62 / 1M out |
| Qwen3.8 Flash Next | /v1/chat/completions | qwen3.8-flash-next | 500,000 | €0.12 / 1M in · €0.62 / 1M out |
| Xev | /v1/systemone | xev-latest | 200,000 chars | €0.022 / 1M in · output free |
| Qwen3 Embedding | /v1/embeddings | qwen3-embed | 32,768 | €0.008 / 1M |
| BGE Reranker v2 M3 | /v1/rerank | bge-reranker-v2-m3 | 4,096 | €0.01 / 1M |
| ERNIE Image Turbo | /v1/images/generations | ernie-image-turbo | €0.05 / image | |
| FLUX.2 Klein 4B | /v1/images/edits | flux2-klein-4b | €0.06 / edit | |
| Whisper | /v1/audio/transcriptions | whisper | €0.005 / minute | |
| Piper | /v1/audio/speech | piper | €2.95 / 1M characters | |
| MiniMax Music 3 | /v1/audio/music | minimax-music3 | €0.04 / 10 seconds | |
| OCR, every EU language | /v1/ocr | ocr-eu | €0.003 / page |
Chat prices are launch pricing. Each linked page carries the model's specs, benchmarks and data-handling details; the API pages in these docs (chat, embeddings, images, audio, documents) carry the request and response shapes.
Running a model on your own machine? The catalogue shows the models that fit a card ("Runs on a card with", for example 24 GB), and each model page names the smallest card that runs it.
How we price
Every model has one published price, in euros, billed by use, with no subscription and no minimum. The table above is the current list.
Committed volume: talk to an engineer.
Available as managed deployment
These models are validated on AxForge hardware and deployed on a dedicated NVIDIA DGX Spark for your traffic only: an OpenAI-compatible endpoint on your own machine, operated by AxForge. Hardware from €0.69/hour; managed service quoted per deployment.
| Model | Type | Context |
|---|---|---|
| Qwen3.6 35B A3B | LLM (MoE, 3B active) | 65,536 |
| Qwen3 30B A3B | LLM (MoE) | 65,536 |
| Gemma-4 26B | LLM, vision-capable | 262,144 |
| Mistral Small 3.2 | LLM | 32,768 |
| SDXL | Image generation | |
| Qwen-Image | Image generation & editing |
Want one of these, or a different open model on dedicated hardware? Request deployment, or rent the DGX Spark yourself with full SSH access.