Dedicated Capacity
Leading open-weight models, on capacity reserved for you
Run GLM-5.3, MiniMax M3.1 Flash or your own fine-tuned models on inference capacity reserved for you in our data center in Munich. We operate it. You get guaranteed throughput and a predictable monthly cost.
Same platform, more control
The same sovereign platform - reserved for you alone
Dedicated Capacity runs the same OpenAI-compatible API and the same EU sovereignty as our Inference API, with the Inference API models and larger ones - but on single-tenant hardware nobody else touches. You get guaranteed, contention-free throughput for a predictable monthly cost, and you can run your own selection of models, including models beyond the Inference API catalog.
The Fit
When to choose Dedicated Capacity
It pays off once your workload is high, steady, and production-critical. Below that, the Inference API is usually the better deal - and we'll say so.
High, steady volume
Sustained production traffic that consistently pushes past what the Inference API tiers economically cover.
Guaranteed SLAs
Contractual uptime and response-time commitments, with no contention from other tenants.
Custom models
Run large models, fine-tuned checkpoints (BYOC) or several models side by side on your dedicated capacity, switched in milliseconds.
Isolation
Single-tenant hardware for compliance, predictable performance, or peace of mind.
What You Get
A production inference engine, run for you
Your own high-throughput AI inference plant - serving models at production scale, with sovereign, single-tenant infrastructure that is deployed, operated and kept running for you, so your team can focus on building, not ops.
Infrastructure
- Single-tenant capacity reserved for you, sized to your workload
- Fully operated and maintained for you
- Guaranteed throughput - no noisy neighbours
- Custom rate limits, or none at all
- In our data center in Munich, with no persistent storage of your data
Support & SLAs
- Dedicated account team
- Priority support with direct escalation
- Custom SLAs (uptime, response time)
- Right-sizing from your real workload
- ISO 27001 certified operations
- Lead time on request
Models
Models you can run on dedicated capacity
Larger and newer models than the Inference API catalog, plus your own fine-tuned checkpoints. Lead time on request.
- Leading open-weight models such as GLM-5.3 and MiniMax M3.1 Flash
- The Inference API models gpt-oss-120b and Gemma 4
- BYOC - fine-tunes of supported architectures load immediately
- Every listed model runs on one rack
Fine-tunes of supported architectures load immediately; genuinely new architectures are a commercial conversation. We won't promise a specific custom model without checking it can run.
On your dedicated capacity
- GLM-5.3Z.ai · about 750B parameters (mixture of experts) · 1M context
- MiniMax M3.1 FlashMiniMax · 427B parameters (mixture of experts) · 1M context
- gpt-oss-120b and Gemma 4OpenAI and Google · 120B and 31B parameters · 128K context
- Your own checkpoints (BYOC)Fine-tunes of supported architectures
Fine-tuning itself runs on GPUs - you train, then hand us the weights to serve at full speed.
One rack, many models
Switch checkpoints in milliseconds
Each chip has three memory tiers: SRAM on the chip for the live computation, HBM in the same package for the weights of the running model, and a large DDR tier for further models and checkpoints. Because the chip addresses its DDR directly, a rack on your dedicated capacity keeps several models and fine-tuned checkpoints ready and switches between them in milliseconds, versus the seconds to minutes a GPU cluster needs.
That means your dedicated capacity can serve a whole agentic pipeline - a planner model, an executor, and a specialised fine-tune - switching per step without standing up separate infrastructure for each.
How many models fit at once depends on their architecture and precision - we'll size your dedicated capacity to your mix.
Checkpoint switch time
Comparison
Dedicated Capacity vs Inference API
| Inference API | Dedicated Capacity | |
|---|---|---|
| Infrastructure | Shared (multi-tenant) | Reserved (single-tenant) |
| Billing | Pay-per-token | Flat monthly |
| Rate limits | Tier-based | Custom or none |
| Contention | Shared queue under load | None - it's all yours |
| Models | Inference API catalog | GLM-5.3, MiniMax M3.1 Flash and more, plus your checkpoints |
| Custom models (BYOC) | Catalog only | Catalog + your checkpoints |
| Support | Tier-based | Dedicated team |
| SLAs | Best-effort | Custom, guaranteed |
FAQ
Questions, answered straight
Is performance on Dedicated Capacity the same as on the Inference API?
Yes - it's the same hardware and the same speeds. What changes is that the capacity is reserved for you alone: no other tenants, no shared queue, no contention. You get consistent throughput because nobody else uses your dedicated capacity.
When does Dedicated Capacity actually make sense versus pay-per-token?
Two things drive the decision, and only one is about cost. On economics, it makes sense above sustained high utilization - once your steady volume consistently pushes past what the Inference API tiers cover (the exact crossover depends on your model and traffic pattern); below that, pay-as-you-go on the Inference API is usually the better deal. The other driver has nothing to do with load: if you want your own mix of models, or your own fine-tuned checkpoints (BYOC), running on hardware reserved for you alone, Dedicated is how you get that - at any volume. It's also the answer for guaranteed capacity, SLAs, or when you're past the Inference API rate limits. If your workload is variable or exploratory and you don't need that control, we'll tell you to stay on consumption.
Can I run my own fine-tuned model?
Yes, if it's a fine-tune of an architecture we already support - it loads and serves immediately. You fine-tune on GPUs and hand us the weights; we serve them on your dedicated capacity. A genuinely new architecture needs engineering work, which is a commercial conversation. Tell us which model you have in mind and we'll confirm it can run.
Can you fine-tune the model for us?
No - fine-tuning and training run on GPUs, not on this architecture, which is built for inference. You (or your ML partner) fine-tune on GPUs, and we host and serve the resulting checkpoint at full speed. We're transparent about this so there's no mismatch in expectations.
How fast can you switch between models or checkpoints?
Milliseconds, versus seconds to minutes on GPUs. Waiting checkpoints sit in the chip's large DDR tier, which the chip addresses directly, so one rack can hold several fine-tuned checkpoints and switch between them per request, even running different models at different steps of an agentic flow.
Which models can I run, and how large can they be?
Any model in the list, plus supported custom checkpoints. Every model in the list runs on one rack. What fits on a rack depends on the model's architecture and precision, not only on its parameter count. For a model that is not on the list, we check the fit with you.
How much dedicated capacity do I need?
We size your dedicated capacity from your workload - total users, peak concurrency, workload type (interactive, agentic, batch), and throughput targets - worked back from measured concurrency. We'd rather right-size it than oversell you capacity you won't fill.
Can I test before committing?
Yes. We can arrange a time-limited test on dedicated capacity before you sign, so you see the value on your own workload first. Dedicated capacity is a real commitment - it should follow proven value, not precede it.
How long does deployment take?
Lead time on request. It depends on the model and on the hardware it needs - tell us your workload and we'll give you a date.
How is Dedicated Capacity different from On-Premises?
Location and ownership. With Dedicated Capacity, Infercom owns the hardware in our data center in Munich and reserves it exclusively for you - we and our operating partner SambaNova run it, you consume it. With On-Premises, you own the hardware in your own datacenter and operate it yourself. Performance is identical; the difference is who holds the keys.
What throughput will I actually get - not the benchmark number?
Real throughput depends on your context length and input/output ratio. Headline tokens-per-second figures are peak numbers on favourable workloads; long-context and output-heavy traffic run lower. We quote throughput against your actual workload, not a single best-case benchmark - that's the honest way to size dedicated capacity.
How much does it cost?
Dedicated Capacity is a flat monthly cost for the capacity reserved for you, with discounts for longer commitments. Because the right configuration depends on your models, throughput, and contract length, pricing is set per engagement rather than published - talk to us and we'll put real numbers on the table quickly.
Do I have to commit for a long term?
No - longer commitments earn better rates, but we know the model landscape moves fast and you don't want to be locked into last year's setup. We offer shorter terms too. Tell us your risk tolerance and we'll structure something that fits.
Can I resell it or run my own customers' workloads on it?
Yes. It's your reserved capacity - like renting your own server - so you're free to build whatever commercial model you like on top of it, including serving your own clients. System integrators and agencies do exactly this. Talk to us and we'll set it up to fit how you go to market.