Reliova Token Supply
Spec · Verify · Supply

Most teams can't say what their AI costs — or whether they got what they paid for.

Reliova specs what your workload actually needs, verifies that the capacity behind it is what it claims to be, and supplies it — on one OpenAI-compatible key, one endpoint, one invoice.

GLM-5.3 GLM-5.2 DEEPSEEK V4 FLASH DEEPSEEK V4 PRO KIMI K3 VERIFIED ONE KEY
Screened suppliers · one endpoint · one invoice
2,000–3,000
Requests per minute, per account
10M–50M
Tokens per minute of throughput
OpenAI-compatible
Change one base URL — your SDK keeps working
USD
Per-token metered, invoiced in USD
How we work

Three steps. Where you start depends on where you are.

Building something new? Start at Spec. Already running on a provider? Start at Verify. Both are free, and neither commits you to buying anything.

Step 01FREE

Spec

For teams about to ship AI

Tell us what the feature does and how many people will use it. We model what it will actually cost per month at each model tier, and name the cheapest model that is genuinely good enough for the job.

Run it yourself now →

Free · cost model in 5 business days
Step 02FREE

Verify

For teams already running on a provider

We fingerprint your provider's output against a reference implementation and tell you whether the model you pay for is the model you get — at the precision you were promised.

Free · audit report in 5 business days
Step 03

Supply

For everyone who liked the numbers

If our capacity is the right answer, we supply it — screened, continuously monitored suppliers behind one key. If it isn't, we say so and tell you where to buy instead.

Prepaid, metered per token
Method · Spec

What the cost model answers

Nobody can forecast an inference bill from a pricing page. Token counts per call, input-to-output ratios and model choice move the number by an order of magnitude. We work it out from the shape of your feature.

  • Tokens per callestimated from your actual prompt and output shape
  • Monthly bill by model tierthe same workload priced across the roster and the closed models you'd otherwise use
  • Good-enough analysiswhether this job actually needs a frontier model, which most don't
  • What breaks at scaleconcurrency, rate limits, and what the bill does when usage grows 10×
Method · Verify

Inference is nearly deterministic

With a fixed sampling seed, over 98% of an LLM's output tokens reproduce exactly. Compare a provider's output against a reference implementation and the divergence tells you whether the weights, the quantization or the sampling configuration changed underneath you. Legitimate differences produce far smaller divergence than a real change — that gap is the signal.

  • ~100Changed sampling configuration
  • ~1,0004-bit weight quantization
  • ~10,000KV cache quantization
  • variesServing bugs & silent model swaps

We publish the method and hand you the harness, so your own engineers can reproduce every number in the report.

The roster

Frontier open models, screened suppliers

Every model here runs on capacity we have tested and keep testing. A supplier that fails an audit comes off the roster.

GLM-5.3
Zhipu · Z.ai
Repository-scale coding and long-horizon agent runs. The strongest value on the roster for teams with real volume.
744Btotal
1Mcontext
GLM-5.2
Zhipu · Z.ai
The proven prior generation — the workhorse for steady, high-volume production traffic.
753Btotal
1Mcontext
DeepSeek V4 · Flash
DeepSeek
Sparse and fast, for latency-sensitive paths where every millisecond is user-visible.
284Btotal
1Mcontext
DeepSeek V4 · Pro
DeepSeek
Deep reasoning and agentic work where the answer has to be right the first time.
1.6Ttotal
1Mcontext
Kimi K3
Moonshot AI
Long-document comprehension and tool use at the frontier, for the workloads that justify it.
2.8Ttotal
1Mcontext

The roster tracks the frontier as it moves. Need a model, a region or an SLA that isn't here? Ask — we will source it or tell you straight that we can't.

Supply

Three ways to buy, one endpoint

Most workloads are a mix. Run user-facing paths on demand, reserve throughput for traffic you can forecast, and send everything that can wait to the batch tier.

Mode 01

On-demand

Pay per token as you go. Fund a balance, draw it down, top it up when you like. The right place to start when your volume is still growing.

LatencyReal-time
Mode 02

Reserved throughput

Lock a dedicated throughput block at a fixed monthly rate. Your cost stops moving with your traffic, and the headroom is held for you.

LatencyReal-time · priority routed
Mode 03

Batch tier

For work with no deadline: embeddings, backfills, evaluation runs, document pipelines. Submit the job, collect the output, pay less.

LatencyCan wait
For platforms & builders

Sit behind your brand, not ours

If you ship a product with AI inside it, inference is a supply problem you did not sign up to solve. Reliova runs underneath: your customers see your product, your pricing, your brand — you see one contract and one invoice.

Talk about white-label →

What you get underneath

Resale is welcome. Reselling capacity to your own customers is part of the agreement, not a clause to work around.
Per-tenant keys. A separate key per end customer, each with its own quota, rate limit and usage record.
Usage data you can bill on. Per-key token accounting that drops straight into your own invoicing.
We stay invisible. Reliova never appears to your end users, and never approaches them.
For supply partners

Bring capacity. We bring the demand book.

Idle accelerators earn nothing. Reliova aggregates enterprise demand into steady, forecastable offtake on one clean contract — so your clusters run loaded, including through the hours they would otherwise sit quiet.

Talk about supply →

What we ask, and what we give

We verify before we buy. Every supplier is fingerprint-tested at onboarding and monitored continuously after.
Committed offtake. We forecast and commit ahead, so your utilization is planned rather than opportunistic.
One counterparty. A single contract and settlement cycle instead of a long tail of small accounts.
A channel that compounds. Every account we land deepens the book you supply into.
Questions

Straight answers

How do I forecast what an AI feature will cost before we launch it?

Estimate tokens per call from your real prompt and output shape, multiply by expected call volume, and price that across model tiers. A pricing page alone tells you almost nothing, because token count per call and the input-to-output ratio move the bill by an order of magnitude. Reliova builds this model free of charge before you commit to anything.

How do I know if my inference provider is silently degrading quality?

You test it. LLM inference is nearly deterministic: with a fixed sampling seed, over 98% of output tokens reproduce exactly. Comparing a provider's output to a reference implementation reveals changed weights, quantization or sampling config. Roughly 1,000 tokens detects 4-bit quantization; about 100 detects a changed sampling configuration. Reliova runs this audit free of charge.

Does my AI feature really need a frontier model?

Usually not. Classification, extraction, summarisation, routing and most agent loops run on open-weight models at a fraction of the cost with no measurable quality loss. The tasks at the edge of model capability are the ones worth paying frontier prices for — and the point of the analysis is to tell the two apart on your own workload rather than in general.

Which models does Reliova supply?

GLM-5.3 and GLM-5.2 from Zhipu, DeepSeek V4 Pro and V4 Flash, and Kimi K3 from Moonshot AI. All are open-weight models with a 1M-token context window. The roster changes as the frontier moves.

Do we have to change our code?

No. The endpoint is OpenAI-compatible: point your existing SDK at the Reliova base URL and use a Reliova key. Switching between models on the roster needs no code change either.

How does procurement review this?

The models on the roster are published as open weights, so running them is a matter of deploying weights rather than transacting with the labs that released them. Where each workload is served, and how data moves through it, is set out in writing before anything is signed.

What throughput does an account get?

2,000 to 3,000 requests per minute and 10 million to 50 million tokens per minute, sized to the workload. Reserved throughput plans hold that headroom for you exclusively.

Can we resell capacity to our own customers?

Yes — resale is explicitly permitted. Platforms and agencies get per-tenant keys with separate quotas and usage records, and Reliova never appears to your end users.

What if Reliova isn't the cheapest option for us?

Then we say so and tell you where to buy instead. The analysis is worth having either way, and a recommendation you can't trust is worth nothing to either of us.

Start here

Start with the free analysis

Building something new, or already running on a provider — either way, tell us the shape of it. We come back within two business days with a scope, and the analysis five business days after that. No charge, no commitment.

Email
Entity
Reliova Inc.
Add detail — optional, and it makes the first reply sharper