Index / providers / infermatic-ai

Infermatic.ai

Flat-rate hosting of creative and roleplay fine-tunes "without guardrails". Popular with SillyTavern users, but doesn't claim abliterated or uncensored weights.

Models9
Per-token price—
Plans from$9/mo
Free tierYes
infermatic.ai ↗Pending review
[ 01 ] Models & prices

BILLINGFlat rate. Free $0 (web UI only, no API, 300 UI requests/day, 60-token UI responses). Essential $9/mo: "curated models up to 72B", API 1 parallel / 12 RPM. Standard $16/mo: "all listed models up to 72B", API 1 parallel / 15 RPM. Plus $20/mo: all incl. MoE/BETA/72B+, API 2 parallel / 18 RPM, early access, plus monthly credits for premium models (credits reset monthly, no rollover). Tiers are cumulative (Plus ⊃ Standard ⊃ Essential ⊃ Free). No logging of prompts/responses. API is OpenAI-compatible: base https://api.totalgpt.ai/v1 (/models, /chat/completions, /completions, /embeddings, /audio/speech); premium Credits API at https://api-dev.totalgpt.ai/v1 with a separate key. Payment: credit card or crypto (ui.infermatic.ai/docs).

ModelMethodContext
Fine-tuned33K
Doctor-Shotgun-L3.3-70B-Magnum-v4-SELlama-3.3-70B · 70B · Llama 3.3 Community
Fine-tuned33K
Fine-tuned66K
Fine-tuned33K
Sao10K-L3.3-70B-Euryale-v2.3-FP8-DynamicLlama-3.3-70B · 70B · Llama 3.3 Community
Fine-tuned33K
Sao10K-L3.1-70B-Hanami-x1Llama-3.1-70B · 70B · Llama 3.1 Community
Fine-tuned33K
TheDrummer-Anubis-70B-v1.1-FP8-DynamicLlama-3.3-70B · 70B · Llama 3.3 Community
Fine-tuned33K
Fine-tuned33K
Fine-tuned33K

Per 1K chats = cost of 1,000 messages of ~1,000 tokens in and ~500 out. Click a model to compare it across providers.All models →

[ 02 ] At a glance
Method
Fine-tuned
Access
Web chat + OpenAI-compatible API
Logging
No logs
Trains on prompts
Unverified
Guarantee
Policy only
Jurisdiction
Delaware, US
Signup
Account required
Payments
Card, Crypto
Data checked
Oct 11, 2026

PRIVACYStates it does not store any input prompts or model outputs. Training use isn't addressed explicitly. Policy ↗

[ 03 ] Scores
Compliance
Benchmark pending
measured
Capability
Benchmark pending
measured
Privacy
40.0
from published policy & pricing
Truthfulness
Benchmark pending
measured
Cost
Insufficient data
from published policy & pricing
Speed
Benchmark pending
measured

Composite: pending capability and compliance runs · method

[ 04 ] Notes & sources

Infermatic Inc. Runs a vLLM backend with an OpenAI-compatible API. Nothing larger than 72B is currently listed, although the Plus plan advertises "72B+". Plus also includes monthly credits for premium (mainstream) models.

  1. https://infermatic.ai/models/
  2. https://infermatic.ai/pricing/
  3. https://infermatic.ai/privacy-policy/
  4. https://ui.infermatic.ai/docs
  5. https://infermatic.ai/docs/overview/