Kataleptic
Vol. 01 № 2026 · 04
Status — Operating

Inference, served clean. Frontier models, answered with conviction.

Kataleptic — from the Stoic kataleptikē phantasia, the impression that grasps the world with certainty — is an OpenAI-compatible inference endpoint serving twenty-five frontier open-source and proprietary models through one billing surface, with EU or US residency on demand. Operated by DLabs SpA.

Claim $5 free credit See the price list
§ 01

One endpoint.

Twenty-five models, three backends, two regions, one OpenAI-compatible surface. No proxy hops, no SDK rewrites, no surprise rate limits.

  1. Catalogue Live

    Twenty-five curated models

    DeepSeek V3.1/V3.2/R1, Llama 3.1/3.3/4-Maverick, Mistral Large 3 / Medium / Nemo, GPT-5/5.2/5.4/5.4-mini/5.5, GPT-OSS 120B, Cohere Command-A, Phi-4 Mini Reasoning, Kimi K2.5/K2.6, Grok 4.1 Fast, Gemma 3 27B, GLM-4 9B, Qwen 3 8B, Qwen 2.5 Coder, plus embeddings.

    See the price list
  2. Residency Live

    EU or US, on demand

    Every Azure-backed model is mirrored in Sweden Central. Flip a single per-account toggle and the next request terminates inside the EU — same models, same prices, no separate billing.

    Open the account dashboard
  3. Sovereign Live

    A100 on dedicated metal

    For models we self-host, inference runs on a dedicated A100 80GB in our own colocation, orchestrated by xinity-ai. Open-weight only, transparent stack, no upstream provider in the loop.

    Live status & latency
§ 02

A line of code,
then you're inferring.

~/kataleptic · cURL 
$ curl https://api.kataleptic.com/v1/chat/completions \
  -H "Authorization: Bearer dg_…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "duguet-ai/llama-3.3-70b",
    "messages": [
      { "role": "user",
        "content": "Compose a haiku about sovereignty." }
    ],
    "stream": true
  }'

> data: {"id":"chatcmpl-…","provider":"duguet-ai",
> data:   "choices":[{"delta":{"content":"Quiet servers hum,"}}]}
> data: {"choices":[{"delta":{"content":" data stays where it was born—"}}]}
> data: {"choices":[{"delta":{"content":" sovereignty in code."}}]}
> data: [DONE]
§ 03

The price list

Transparent per-million-token pricing. No top-up fee, no hidden request surcharge. Billed by the token, paid from prepaid credit. First $5 on us.

Model Context Input / MTok Output / MTok Backend
— Open-source chat —
Llama 3.1 8B duguet-ai/llama-3.1-8b131k$0.05$0.08Azure MaaS
GLM-4 9B duguet-ai/glm4-9b128k$0.05$0.08Sovereign A100 · xinity
Qwen 3 8B duguet-ai/qwen3-8b32k$0.05$0.08Sovereign A100 · xinity
Qwen 2.5 Coder 7B code duguet-ai/qwen2.5-coder-7b32k$0.05$0.08Sovereign A100 · xinity
Mistral Nemo 12B duguet-ai/mistral-nemo-12b128k$0.10$0.15Sovereign A100 · xinity
Gemma 3 27B duguet-ai/gemma3-27b128k$0.15$0.20Sovereign A100 · xinity
Llama 3.3 70B duguet-ai/llama-3.3-70b131k$0.30$0.40Azure MaaS
DeepSeek V3.2 duguet-ai/deepseek-v3-2164k$0.40$0.60Azure MaaS
Mistral Medium 2505 new duguet-ai/mistral-medium131k$0.40$2.00Azure MaaS
Mistral Large 3 duguet-ai/mistral-large-3131k$0.40$1.20Azure MaaS
Cohere Command-A new duguet-ai/cohere-command-a131k$2.50$10.00Azure MaaS
DeepSeek V3.1 tools new duguet-ai/deepseek-v3-1131k$0.27$1.10Azure MaaS
Llama 4 Maverick 17B vision new duguet-ai/llama-4-maverick1M$0.50$1.50Azure MaaS
— Reasoning —
GPT-OSS 120B reasoning duguet-ai/gpt-oss-120b128k$0.15$0.60Azure MaaS
DeepSeek R1 reasoning duguet-ai/deepseek-r1164k$0.50$2.00Azure MaaS
Kimi K2.5 reasoning duguet-ai/kimi-k2.5131k$0.60$2.40Azure MaaS
Kimi K2.6 reasoning duguet-ai/kimi-k2.6131k$0.60$2.40Azure MaaS
xAI Grok 4.1 Fast reasoning new duguet-ai/grok-4-1-fast131k$0.20$0.50Azure MaaS
Phi-4 Mini Reasoning reasoning new duguet-ai/phi-4-mini-reasoning128k$0.10$0.30Azure MaaS
— Proprietary —
GPT-5 duguet-ai/gpt-5400k$2.50$10.00Azure OpenAI
GPT-5.2 duguet-ai/gpt-5.2400k$2.50$10.00Azure OpenAI
GPT-5.4 Mini vision new duguet-ai/gpt-5.4-mini400k$0.25$2.00Azure OpenAI
GPT-5.4 vision new duguet-ai/gpt-5.41M$2.50$15.00Azure OpenAI
GPT-5.5 vision flagship new duguet-ai/gpt-5.51M$2.50$15.00Azure OpenAI
— Embeddings —
Nomic Embed duguet-ai/nomic-embed8k$0.02—Sovereign A100 · xinity

A note on price: we aren't chasing the absolute floor. We undercut the major aggregators by 20–40 % on most SKUs and don't charge a top-up fee.

§ Volume discounts Auto-applied · rolling 30-day window · no contracts
  • $0–$500 / moPay-as-you-golisted price
  • $500+ / moScale5 % off
  • $2,000+ / moVolume10 % off
  • $10,000+ / moEnterprise15 % off · talk to us
§ 04

The workshop

i.

From first principles.

We build the smallest piece that solves the actual problem. Fewer abstractions, more measurements, and a clear paper trail from input to output.

ii.

Sovereign by architecture.

Compute, weights, and data stay where you can audit them. Self-host the entire stack, or use ours under a contract that forbids egress.

iii.

Open where it matters.

We prefer open weights and open formats; we contribute the generalisable parts back. Proprietary work earns its keep on results, not on lock-in.

iv.

Production-shaped.

Every release ships with throughput numbers, latency p50/p99, failure modes, and a runbook. If it cannot be operated, it is not finished.

Claim your API key.

$5 in free credit, no card. Drop-in replacement for OpenAI or OpenRouter clients — point base URL at api.kataleptic.com/v1 and go.

One inbox, read by a human · hello@kataleptic.com