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.
Kataleptic — from the Stoic kataleptikē phantasia, the impression that grasps the world with certainty — is an OpenAI-compatible inference endpoint serving fifty-four frontier open-source and proprietary models through one billing surface.
Fifty-four models, three backends, one OpenAI-compatible surface. No proxy hops, no SDK rewrites, no surprise rate limits.
GPT-6 Astra/Sol/Luna, GPT-5.6 Sol/Terra/Luna, DeepSeek V4 Pro/Flash and V3.2, Llama 3.3/4-Maverick, Mistral Large 3 / Medium 3.5 / 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/K2.7-Code, Grok 4.3 and 4.1 Fast, Gemma 3 27B, GLM-4 9B, Qwen 3 8B, Qwen 2.5 Coder, plus realtime voice, transcription, image, video and embeddings.
For models we self-host, inference runs on our own fleet of GPU servers in our own colocation, orchestrated by xinity-ai. Open-weight only, transparent stack, no upstream provider in the loop.
$ curl https://api.kataleptic.com/v1/chat/completions \
-H "Authorization: Bearer dg_…" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b",
"messages": [
{ "role": "user",
"content": "Compose a haiku about inference." }
],
"stream": true
}'
> data: {"id":"chatcmpl-…","provider":"duguet-ai",
> data: "choices":[{"delta":{"content":"Quiet servers hum,"}}]}
> data: {"choices":[{"delta":{"content":" one token at a time—"}}]}
> data: {"choices":[{"delta":{"content":" the answer arrives."}}]}
> data: [DONE]
Transparent per-million-token pricing. No top-up fee, no hidden request surcharge. Billed by the token, paid from prepaid credit. First $2 on us.
Where a model supports prompt caching, re-sent context bills at the cached rate shown beneath the input price — one tenth of fresh input, and we charge nothing extra to write the cache. Agents that resend a conversation every turn pay a fraction of the headline number.
| Model | Context | Input / MTok | Output / MTok | Backend |
|---|---|---|---|---|
| — Open-source chat — | ||||
GLM-4 9B retiring 2026-10-23 glm4-9b | 128k | $0.05 | $0.08 | Sovereign fleet · xinity |
Qwen 3 8B retiring 2026-10-23 qwen3-8b | 32k | $0.05 | $0.08 | Sovereign fleet · xinity |
Qwen 2.5 Coder 7B code retiring 2026-10-23 qwen2.5-coder-7b | 32k | $0.05 | $0.08 | Sovereign fleet · xinity |
Mistral Nemo 12B retiring 2026-10-23 mistral-nemo-12b | 128k | $0.10 | $0.15 | Sovereign fleet · xinity |
Gemma 3 27B retiring 2026-10-23 gemma3-27b | 128k | $0.15 | $0.20 | Sovereign fleet · xinity |
Llama 3.3 70B llama-3.3-70b | 131k | $0.30 | $0.40 | Azure MaaS |
DeepSeek V3.2 deepseek-v3-2 | 131k | $0.40 | $0.60 | Azure MaaS |
Mistral Large 3 mistral-large-3 | 262k | $0.40 | $1.20 | Azure MaaS |
Cohere Command-A new cohere-command-a | 288k | $2.50 | $10.00 | Azure MaaS |
DeepSeek V4 Pro tools new deepseek-v4-pro | 1M | $1.74 | $3.48 | Azure MaaS |
DeepSeek V4 Flash tools new deepseek-v4-flash | 1M | $0.19 | $0.51 | Azure MaaS |
DeepSeek V4.1 Flash preview · retires 2026-12-15 deepseek-v4.1-flash | 1M | $0.46875$0.010 cached | $1.875 | Azure MaaS |
Mistral Medium 3.5 vision new mistral-medium-3.5 | 262k | $1.50 | $7.50 | Azure MaaS |
Cohere Command-A Plus new cohere-command-a-plus | 131k | $0.80 | $3.20 | Azure MaaS |
Llama 4 Maverick 17B vision new llama-4-maverick | 128k | $0.50 | $1.50 | Azure MaaS |
| — Reasoning — | ||||
GPT-OSS 120B reasoning gpt-oss-120b | 131k | $0.15 | $0.60 | Azure MaaS |
DeepSeek V3.2 Speciale reasoning new deepseek-v3-2-speciale | 131k | $0.58 | $1.68 | Azure MaaS |
Kimi K2.7 Code reasoning new kimi-k2.7-code | 262k | $0.95 | $4.00 | Azure MaaS |
xAI Grok 4.3 reasoning new grok-4.3 | 200k | $1.25 | $2.50 | Azure MaaS |
Kimi K2.5 reasoning kimi-k2.5 | 262k | $0.60 | $2.40 | Azure MaaS |
Kimi K2.6 reasoning kimi-k2.6 | 262k | $0.60 | $2.40 | Azure MaaS |
xAI Grok 4.1 Fast reasoning new grok-4-1-fast | 128k | $0.20 | $0.50 | Azure MaaS |
xAI Grok 4.7 provisional 4.6 pricing grok-4.7 | 500k | $2.50$0.625 cached | $7.50 | Azure MaaS |
Phi-4 Mini Reasoning reasoning new phi-4-mini-reasoning | 4k | $0.10 | $0.30 | Azure MaaS |
| — Proprietary — | ||||
GPT-5 gpt-5 | 400k | $2.50$0.25 cached | $10.00 | Azure OpenAI |
GPT-5.2 gpt-5.2 | 400k | $2.50$0.25 cached | $14.00 | Azure OpenAI |
GPT-5.4 Mini vision new gpt-5.4-mini | 400k | $0.75$0.075 cached | $4.50 | Azure OpenAI |
GPT-5.4 vision new gpt-5.4 | 1M | $2.50$0.25 cached | $15.00 | Azure OpenAI |
GPT-5.5 vision flagship new gpt-5.5 | 1M | $5.00$0.50 cached | $30.00 | Azure OpenAI |
GPT-5.6 Luna vision new gpt-5.6-luna | 400k | $1.00$0.10 cached | $6.00 | Azure OpenAI |
GPT-5.6 Terra vision new gpt-5.6-terra | 1M | $2.50$0.25 cached | $15.00 | Azure OpenAI |
GPT-5.6 Sol vision flagship new gpt-5.6-sol | 1M | $5.00$0.50 cached | $30.00 | Azure OpenAI |
GPT-6 Luna vision new gpt-6-luna | 1.05M | $0.10$0.01 cached | $0.50 | Azure OpenAI |
GPT-6 Sol vision new gpt-6-sol | 1.05M | $2.00$0.20 cached | $10.00 | Azure OpenAI |
GPT-6 Astra vision flagship new gpt-6-astra | 1M | $10.00$1.00 cached | $50.00 | Azure OpenAI |
| — Embeddings — | ||||
Nomic Embed retiring 2026-10-23 nomic-embed | 8k | $0.02 | — | Sovereign fleet · xinity |
| — Image generation · flat rates at 1024×1024; 2.5 variants per MTok — | ||||
GPT-Image-1 Mini new gpt-image-1-mini | — | $0.011 / image | Azure OpenAI | |
FLUX.2 Pro new flux-2-pro | — | $0.040 / image | Azure MaaS | |
GPT-Image-2 flagship new gpt-image-2 | — | $0.080 / image · high ×2 | Azure OpenAI | |
GPT-Image-2.5 Flare new gpt-image-2.5-flare | — | $6.25 / MTok text | $37.50 / MTok image | Azure OpenAI |
GPT-Image-2.5 Sunburst new gpt-image-2.5-sunburst | — | $6.25 / MTok text | $37.50 / MTok image | Azure OpenAI |
| — Full-duplex voice · per minute of session clock — | ||||
GPT-Live 1 new gpt-live-1 | — | $0.09375 / min + delegate tokens | Azure OpenAI · provisional pricing | |
| — Speech recognition · per minute of audio — | ||||
Whisper Large V3 Turbo new fastest retiring 2026-10-23 whisper-large-v3-turbo | — | $0.003 / min | Sovereign fleet · xinity | |
GPT-4o Transcribe new gpt-4o-transcribe | — | $0.006 / min | Azure OpenAI | |
GPT-4o Transcribe (diarized) new gpt-4o-transcribe-diarize | — | $0.024 / min | Azure OpenAI | |
GPT-4o Mini Transcribe new cheapest gpt-4o-mini-transcribe | — | $0.0045 / min | Azure OpenAI | |
GPT Transcribe new gpt-transcribe | — | $0.006 / min | Azure OpenAI | |
Whisper large-v2 timestamps retires 2026-12-15 whisper-large-v2 | — | $0.0097 / min | Azure OpenAI | |
GPT Live Transcribe streaming new gpt-live-transcribe | — | $0.02125 / min | Azure OpenAI | |
GPT Realtime Whisper streaming new gpt-realtime-whisper | — | $0.02125 / min | Azure OpenAI | |
| — Video generation · per second of output, async job — | ||||
Sora 2 new sora-2 | — | $0.20 / sec | Azure OpenAI | |
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.
We build the smallest piece that solves the actual problem. Fewer abstractions, more measurements, and a clear paper trail from input to output.
We prefer open weights and open formats; we contribute the generalisable parts back. Proprietary work earns its keep on results, not on lock-in.
Every release ships with throughput numbers, latency p50/p99, failure modes, and a runbook. If it cannot be operated, it is not finished.
$2 in free trial credit for eligible new inboxes, no card. Drop-in replacement for
OpenAI or OpenRouter clients — point base URL at
https://api.kataleptic.com/v1 and go.
One free trial per inbox, including email aliases. Disposable addresses are not eligible. Daily trial availability is limited.
Welcome. A key has been minted for you.
We also sent it to your inbox — check your mail.
Copy it now. This is the only time it appears on screen.
Already have an account but lost the key? Recover by email →