SERVICE 01 · SERVERLESS INFERENCE

One API. Compatible with OpenAI and with Anthropic. Served from Europe.

Change the base URL and you are already running open models on our infrastructure. Nothing to deploy, no GPUs to manage, no commitment. You pay per million tokens.

Get your API key See models and prices

The service

One API, two endpoints, and we run the rest.

api.nextbit256.com

from openai import OpenAI

client = OpenAI(
    api_key="nb-...",
    base_url="https://api.nextbit256.com/v1",  # the only change
)

Dual compatibility

Change the base URL. Your code stays put.

We expose the API in the two formats your stack already uses: OpenAI’s and Anthropic’s. If you build with Claude Code, Cursor, Cline or any agent that speaks either protocol, you change the base URL and the key and it keeps working.

Endpoints

Two endpoints, the same API.

EU only8 MODELS

Only models served from European infrastructure. Your data does not leave the EU.

Global13 MODELS

The whole catalogue, from the EU by default. Whatever runs outside is flagged in the table.

Load balancingAutoscalingQueuesFault toleranceObservabilityCompliance

What we run for you

Hardware, balancing and queues. You send an HTTP request.

The inference stack, the autoscaling and the fault tolerance are on us. You deploy nothing and manage not a single GPU.

01Create your account
02Change the base_url
03Runs in Spain
04Answers in ms

Who it is not for: if your load is high and sustained (an agent in production, a contact centre, a document pipeline), paying per token ends up costing more than Dedicated Inference. We tell you on the first call, even when it suits us less.

Catalogue

Available models, with their price per token.

They all speak the same API. Each model’s provenance is in its row, not in the small print.

13 MODELS · EU = PRESENT IN eu.api.nextbit256.com/v1/models

Model	Family	Context	Input $/M	Output $/M	Cache $/M	Region
Gemma 4 26B A4B	Gemma	262.144	0,090	0,300	0,050	EU
deepseek:v4.1-flash	DeepSeek	1.048.576	0,210	0,840	0,004	Multi
DeepSeek V4 Flash (0731)	DeepSeek	1.048.576	0,352	1,056	0,012	Multi
DeepSeek V4 Pro (0813)	DeepSeek	1.048.576	1,056	3,168	0,035	Multi
DeepSeek V4 Pro	DeepSeek	1.048.576	1,740	3,480	0,145	Multi
Qwen3 14B	Qwen	40.960	0,100	0,220	—	EU
gemma3:12b-it	Gemma3	131.072	0,050	0,150	—	EU
gemma3:27b	Gemma3	131.072	0,070	0,275	0,040	EU
GLM 5.3 Flash	GLM	1.048.576	0,150	0,500	0,050	Multi
ALIA-40B	ALIA	65.536	0,300	0,600	—	EU
Gemma 2 27B	Gemma	8192	0,650	0,650	—	EU
ReMM SLERP L2 13B	ReMM SLERP	6144	0,450	0,650	—	EU
Euryale 3.3 70B	Euryale	131.072	0,650	0,750	—	EU

FAQ

The objections, answered.

Is it really compatible with the OpenAI API?

Yes: the same request and response format. You change base_url and api_key, and the rest of your code stays as it is.

Is my data used for training?

No, never. Neither prompts nor responses train any model, ours or anyone else’s.

How long do you keep requests?

On the EU endpoint, nothing: requests are processed in memory and never stored. On the global endpoint (models marked "Multi"), they are not kept once the request is completed, save where the law requires it, and then for 30 days at most.

Can I move to dedicated without rewriting code?

Yes. Same API and same layer: going from serverless to dedicated is a deployment decision, not a migration.

What rate limits are there?

Standard per-key limits meant for production. If your case exceeds them, they are raised during sizing.

Start now

Generate your API key and change one line of configuration.

No contracts, no minimums, not a single GPU to manage. Try it in minutes with your current stack.

No GPU managementPay per tokenServed from Spain

Get your API key Talk to us