AxForge offering
When this offering is available: Image generation through the OpenAI-compatible /v1/images/generations endpoint, served from hardware AxForge owns in Stockholm. Dense, legible in-image text for posters, infographics and UI-style layouts that actually read, with zero prompt retention.
Check the console for current access, prices and availability.
Why AxForge
| Text that reads | Dense, long-form, layout-sensitive text inside the image is the model's signature capability: posters, infographics, UI-style images and multi-panel layouts where every word has to read. |
|---|---|
| Won a seed-matched bake-off | AxForge benchmarked candidates on its own hardware with identical prompts and seeds. ERNIE Image Turbo won the structured and text-heavy cases decisively, under Apache 2.0, at a third of the memory of the previous model. |
| Zero prompt retention | Prompts and generated images are processed in memory in Stockholm, Sweden. Not logged, not retained, never used for training. Only request metadata is kept for billing and operations. |
Specifications
| Model | ERNIE Image Turbo: 8B diffusion transformer, 8-step turbo |
|---|---|
| API model name | ernie-image-turbo |
| Endpoint | POST /v1/images/generations |
| Signature capability | Dense, long-form, layout-sensitive text inside the image: posters, infographics, UI-style images, multi-panel layouts |
| License | Apache 2.0 (open weights) |
| Quantization | fp8 |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Stockholm, Sweden (eu-se-1) |
| Price | €0.05 / image |
ERNIE Image Turbo 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 | POST /v1/images/generations with model ernie-image-turbo, a size such as 1024x1024 and your prompt. |
| 5 | Treat generation as an asynchronous call with a generous client timeout. It is seconds-scale. |
| 6 | Need to edit the result? Send it to FLUX.2 Klein on /v1/images/edits. |
FAQ
When available, check current pricing in the console. €0.05 per image. No subscription, no minimum.
Generation is seconds-scale, not instant. It is an 8-step turbo pipeline with prompt enhancement. Treat it as an asynchronous call with a generous client timeout. AxForge has not published its own tuned timing numbers yet.
Yes. It is the standard /v1/images/generations shape at https://api.axforge.ai/v1, with the model name ernie-image-turbo.
Yes. Dense, long-form, layout-sensitive text is the model's signature capability: posters, infographics, UI-style images and multi-panel layouts where every word has to read.
Candidates were benchmarked on AxForge hardware with identical prompts and seeds. ERNIE Image Turbo won the structured and text-heavy cases decisively, under the Apache 2.0 license, at a third of the memory of the previous model. The image-editing offering uses FLUX.2 Klein 4B when available.
No. Prompts and completions are processed in memory in Sweden, never persisted or used for training. Only request metadata is kept for billing and operations.