Low-cost inference · EU-owned hardware

Cheap LLM inference — without the asterisks

Cheap usually costs you something else: your data, your region, or an unlabeled quantization. Our LLM API is priced by a public rule against the market — and the EU residency, zero retention and named hardware come with it.

€0.29 / 1M input · €1.77 / 1M output — Qwen3.8 27B eu-se-1 · Stockholm api.axforge.ai/v1
Get an API key Talk to an engineer Launch pricing. Keys are allocated from the waiting list. Prices exclude VAT.

The claim

A cheapest claim you can check

For Qwen3.8 27B, we checked every provider listed for the same model on 2026-08-26: our €0.29/€1.77 per 1M is below every one of them.

One model, one date, checkable — and a standing rule that keeps it true: 80% of the lowest market price, tracked continuously against the market.

The mechanism

Why it stays cheap: the 80% rule

We price inference aggressively low: our target is 80% of the lowest current price from a proper inference supplier for the same model, tracked continuously. Found better pricing at a proper inference supplier? Tell us and we’ll look into lowering ours.

A proper inference supplier is a provider operating and standing behind managed inference for the model — decentralized compute marketplaces don't count. Because the target tracks the market instead of a promotional calendar, the low price is a standing rule, not a launch stunt. The full price list is at /pricing/.

Prices

What the shared API costs

CapabilityModelPrice
Chat — input tokensQwen3.8 27B€0.29 / 1M tokens
Chat — output tokensQwen3.8 27B€1.77 / 1M tokens
EmbeddingsQwen3 Embedding€0.015 / 1M tokens
Image generationERNIE Image Turbo€0.02 / image
Image editing · speech-to-text · text-to-speech · musicSee the price listOn request

EUR, exclusive of VAT, pay-as-you-go — no subscription, no minimum. Every API response reports usage, so the bill is reconcilable to the token.

No trade-off

What cheap does not cost you here

Cheap and sovereign at the same time is the whole point. The low price does not buy down any of this:

EU residencyServed from Stockholm (eu-se-1) and Málaga (eu-es-1), TLS terminated in the EU, region pinned on your key and echoed on every response.
Zero prompt retentionPrompts and completions are processed in memory — not written to disk, not logged, not retained, never used to train. See the privacy policy.
Named hardwareQwen3.8 27B runs on NVIDIA DGX Spark (GB10, 128 GB unified memory) systems AxForge owns and operates — not anonymous capacity resold from somewhere.
Full API surfaceOpenAI-compatible: streaming, tool calls and usage reporting all included at the listed price.

Buyer's guide

How to compare cheap inference honestly

Per-token headline prices hide most of the story. Whoever you compare — including us — check these four things:

CheckWhy it mattersWhere we stand
Input vs output priceOutput tokens usually cost several times more than input. A cheap input rate means little if your workload is generation-heavy — weight both rates by your real traffic mix.€0.29 in / €1.77 out per 1M, both published
Context windowA low price on a small context can cost more overall once you're chunking and re-sending. Compare the context you'll actually use.65,536 tokens
QuantizationThe same model name can be served at very different precisions, and quality follows. A provider should tell you what is actually running.Disclosed on every model page — Qwen3.8 27B is served as NVFP4
Data termsA low price funded by retaining or training on your prompts is not a low price. Read the retention policy, not the pricing page.Zero retention, no training — policy

FAQ

Cheap LLM inference — common questions

Is AxForge the cheapest LLM API?

We make one precise claim: for Qwen3.8 27B, we checked every provider listed for the same model on 2026-08-26, and our €0.29/€1.77 per 1M tokens was below every one of them — and the 80% rule keeps it that way.

Why is AxForge LLM inference so cheap?

We own the hardware the models run on, we serve efficient open-weight models on machines sized for the job, and the price reflects real serving cost plus a thin margin — no cloud markup, no VC-subsidized pricing that has to snap back later. The mechanics are on the pricing page.

Does cheap mean my prompts are used for training?

No. Prompts and completions are processed in memory in Sweden — not written to disk, not logged, not retained, and never used to train anything. Only request metadata (token counts, timestamps, status) is kept for billing and operations. See the privacy policy.

Will the price go up after launch?

Prices follow our pricing rule rather than a promotional calendar: the target is 80% of the lowest current price from a proper inference supplier for the same model, tracked continuously. They can move in both directions with the market — the rule is what keeps them low, not a launch discount.

How do I get access?

API keys are allocated from the waiting list — there is no public free tier today. Once you have a key, the API is OpenAI-compatible: point your existing SDK at https://api.axforge.ai/v1 and pay per token. Setup details are on the Qwen3.8 27B page.

Related

Nearby on AxForge

Cheap, checkable, and served from Europe.

Get an API key Talk to an engineer
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms