Stop betting your output on one model.
Fan a single prompt out to top frontier models in parallel, then let a cross-family judge reconcile them into one answer you can trust. OpenAI-compatible. EU-hosted. You pay for the tokens you spend, plus a transparent consensus margin.
One prompt in. Every model's answer + a reasoned verdict out.
A consensus run, shaped exactly like the streamed response from the API and the free public demo.
We're a 12-person SaaS. Should we self-host an LLM or stay on hosted APIs for the next 12 months? Give a one-paragraph recommendation.
Stay on hosted APIs. At 12 people your bottleneck is product velocity, not inference cost; self-hosting adds GPU ops, eval and on-call burden that will not pay back below roughly €8k/mo in spend…
Hosted, with one caveat: route through a gateway so you can switch providers without code changes. Self-hosting only makes sense once a workload is both high-volume and latency-critical…
Remain on hosted APIs for 12 months. Revisit only if data-residency or a >70% cost reduction at scale becomes a hard requirement; otherwise the operational tax outweighs the savings…
All three converge on "stay hosted", so confidence is high. The winner is rewarded for naming the real decision boundary rather than hedging, and for tying the choice to team size — the most actionable framing.
Illustrative example — synthetic data, not a customer run
A confident wrong answer reads exactly like a correct one.
Single-model blind spots
One model means one set of blind spots. You can't see the disagreement you never sampled — and a confident hallucination looks identical to a fact.
Manual comparison doesn't scale
Pasting the same prompt into three chat windows works once. It does not work in a pipeline, a support flow, or an agent loop running thousands of times a day.
Glue code rots
Fan-out, streaming multiplex, a judge prompt, per-model cost accounting, provider failover — that is a system to maintain. Or it is one model slug.
Pick how the answers get reconciled.
Same fan-out, different judge behaviour. Switch with a single field — no re-architecture.
Synthesised agreement
→ default for "give me the best single answer"
Highlight disagreements
→ research, due-diligence, risk review
Judge picks the best response
→ pipelines that need one clean output
No synthesis, parallel only
→ you own the reconciliation
If you can call OpenAI, you can call consensus.
Change the base URL and the model slug. Add an x_council block to pick the pool, the judge, and the mode. That is the integration.
curl https://tokonomix.ai/api/v1/chat/completions \
-H "Authorization: Bearer tok_live_…" \
-d '{
"model": "tokonomix-consensus",
"messages": [{"role":"user","content":"…"}],
"x_council": {
"mode": "best_of",
"models": ["claude-opus-4.8","gpt-5.1","gemini-3-pro"],
"judge_model": "gpt-5.1"
}
}'// tokonomix MCP server
tokonomix_consensus_ask({
prompt: "…",
models: ["claude-opus-4.8","gpt-5.1"],
mode: "full", // answers + reasoning + verdict
judge_model: "gpt-5.1"
})one tool call → multi-model verdict, billed to your Tokonomix balance
IMG=$(base64 -w0 product-shot.png)
curl https://tokonomix.ai/api/v1/chat/completions \
-H "Authorization: Bearer tok_live_…" \
-d '{
"model": "tokonomix-consensus",
"stream": false,
"messages": [{"role":"user","content":[
{"type":"text","text":"Inspect this image for publication-blocking defects. Verdict: DEFECT or CLEAN + findings."},
{"type":"image_url","image_url":{"url":"data:image/png;base64,'$IMG'"}}
]}]
}'Inline base64 only (no URL fetch) · jpeg/png/webp/gif · max 5MB/image · non-streaming · vision models auto-selected
No fee on single calls. You only pay the fee on consensus.
Ask one model and you pay just its tokens plus a small tier margin — no platform fee. The per-call fee applies only to multi-model consensus checks. 100 consensus checks free every month, no card needed; bundles from €10/month for 500 calls. Every token itemised, nothing hidden.
Single-model call
No call-fee — only consensus checks carry the per-call fee. You pay the model provider's token price plus your tier margin (+2–5%). Example: a small model on ~4k tokens ≈ €0.001.
Consensus call
The call-fee varies per package (PAYG founders: 2c/proposer + 3c/judge, a 3+1 council = 9c; bundles: counts against your monthly quota; over quota: 1.5c/call). On top: the model provider's tokens + your tier margin.
Bring your own key (BYOK)
On consensus you pay only the per-package call-fee — your own key bills the provider directly, so no token cost and no margin from us. A single-model BYOK call costs nothing.
Inference and logs in the EU. GDPR-aligned by default.
Standard SDKs. Swap providers without touching your code.
Prepaid balance. No seats, no minimum, stop anytime.
Per-model tokens, cost and latency on every call.
Honest answers
Does multi-model consensus reduce hallucination?
It's a recall amplifier, not a truth oracle. Several models answer in parallel and an independent judge reconciles them, so an error one model makes is more likely to be caught and disagreement is surfaced rather than hidden. It reduces single-model error — it does not guarantee correctness, because frontier models share training data and can be confidently wrong together. Ground high-stakes facts.
How is the judge kept independent?
The judge is disjoint from the proposers and chosen from a different model family; the proposers answer blind and in parallel, so the judge never scores its own answer. This is a design property of how the council is built, not a benchmarked claim.
Can I keep my data in the EU?
Yes. You can pin a council to EU-hosted models by hosting region, so personal-data prompts are routed only to EU-hosted models. Region routing is per call.
Try it free. No sign-up to test.
Run consensus in the browser right now, then grab an API key when you are ready to wire it in.