MagmaRouter vs Infermatic
Infermatic is a subscription service hosting a large set of 70B class roleplay and creative writing finetunes, with flat monthly plans from $9. MagmaRouter is pay as you go and sells a short line of uncensored models built to do tool calling and drive coding agents.
Facts checked October 2026 against Infermatic’s own site, docs and policies.
| MagmaRouter | Infermatic | |
|---|---|---|
| What it is | Hosted gateway for one uncensored, tool capable model line (Xploded). | A subscription LLM host with a chat UI and an OpenAI-compatible API, serving open models and roleplay finetunes on a vLLM backend. |
| Pricing | Pay as you go, $5 minimum top-up, no subscription required. | Flat monthly subscriptions: Free $0 (chat UI only, no API access), Essential $9/month (curated models up to 72B), Standard $16/month (all listed models up to 72B), Plus $20/month (all listed models including MOE, BETA and 72B+, plus premium models with monthly credits), and Custom Enterprise on request. No per-token billing is shown. |
| OpenAI-compatible | Yes | Yes. Base URL https://api.totalgpt.ai/v1 with /chat/completions, /completions, /models and /embeddings. Some models (for example Rocinante) have no chat template and must use /v1/completions. |
| Anthropic-compatible | Yes, /v1/messages (verified with Claude Code) | Not documented. Only OpenAI-style endpoints are listed. |
| Uncensored / abliterated | Five uncensored models, the Xploded line: GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiMo V2.6 Flash and Qwen3.8 27B. Every one calls tools. | Roleplay and creative finetunes including Magnum-72b-v4, L3.3-70B-Euryale-v2.3 and Rocinante-12B-v1.1 (also Anubis 70B and Cydonia-24B). |
| Prompt retention | No prompt or completion stored; model, tokens and cost kept 90 days; signed prompt-hash receipt | Pricing page says all plans include no logging of prompts or responses. Privacy policy: prompts and outputs are processed in real time and not saved, recorded, or used beyond the immediate interaction. Training use is not explicitly addressed. |
| Per-key spend caps | Lifetime and monthly per-key caps, enforced by reserving the worst case and clamping max_tokens | Per plan rate limits: API parallel requests 1 (Essential), 1 (Standard), 2 (Plus); API requests per minute 12, 15, 18. Free tier has no API. Per-key spend limits are not documented (flat subscription). |
Where Infermatic is the better choice
- Flat monthly pricing from $9 to $20 with no per-token charges, which works out much cheaper than any pay per token service for heavy, long roleplay sessions.
- A much wider catalogue of dedicated roleplay finetunes (Magnum, Euryale, Anubis, Rocinante, Cydonia) plus a free chat UI tier, where MagmaRouter sells five models.
Where MagmaRouter is different
- MagmaRouter is pay as you go with a $5 minimum top-up and no subscription, so light or bursty use costs only what you send.
- MagmaRouter offers an Anthropic-compatible /v1/messages endpoint alongside OpenAI, every Xploded model does tool calling for agents like Claude Code, Cline and OpenCode, and keys can have hard lifetime and monthly spend caps.
The uncensored models MagmaRouter sells
If you are comparing Infermatic because you want an uncensored or abliterated model API, these are the models on MagmaRouter: GLM 5.3 uncensored, GLM 5.3 Flash uncensored, DeepSeek V4.1 Flash uncensored, MiMo V2.6 Flash abliterated, Qwen3.8 27B uncensored and Qwen3.8 27B Fast uncensored. Every one calls tools, works in Claude Code through the Anthropic endpoint, and is priced per million tokens as listed on its model page.
| Model | What it is | Context | Price in / out | Supports |
|---|---|---|---|---|
| GLM 5.3 Xploded glm-5.3-xploded | GLM 5.3 uncensored API | 1M | $2.00 / $5.00 | tools, reasoning |
| GLM 5.3 Flash Xploded glm-5.3-flash-xploded | GLM 5.3 Flash uncensored API | 1M | $0.30 / $1.00 | tools, vision, reasoning |
| DeepSeek V4.1 Flash Xploded deepseek-v4.1-flash-xploded | DeepSeek V4.1 Flash uncensored API | 1M | $0.30 / $1.50 | tools, reasoning |
| MiMo V2.6 Flash Xploded mimo-v2.6-flash-xploded | MiMo V2.6 Flash abliterated API | 1M | $1.00 / $2.00 | tools, vision, reasoning |
| Qwen3.8 27B Xploded qwen3.8-27b-xploded | Qwen3.8 27B uncensored API | 1M | $1.50 / $5.00 | tools, vision, reasoning |
| Qwen3.8 27B Fast Xploded qwen3.8-27b-fast-xploded | Qwen3.8 27B Fast uncensored API | 524K | $1.50 / $5.00 | tools, vision, reasoning |
FAQ
Is Infermatic cheaper than MagmaRouter for roleplay?
For heavy use, almost certainly yes. Infermatic charges a flat $9 to $20 a month regardless of tokens, while MagmaRouter bills per token. If you roleplay for hours every day, the subscription will usually win.
Can I use Infermatic with Claude Code?
Infermatic documents only OpenAI-style endpoints and no Anthropic /v1/messages endpoint, and its docs do not mention tool calling. MagmaRouter has an Anthropic-compatible endpoint and tool calling models aimed at coding agents.
Does Infermatic log my prompts?
Infermatic says all plans include no logging of prompts or responses, and its privacy policy says inputs and outputs are processed in real time and not saved. The policy does not explicitly address training.
Which uncensored models does MagmaRouter sell?
MagmaRouter sells GLM 5.3 Xploded, GLM 5.3 Flash Xploded, DeepSeek V4.1 Flash Xploded, MiMo V2.6 Flash Xploded, Qwen3.8 27B Xploded, Qwen3.8 27B Fast Xploded. The table above has the price and context for each.
Are these models abliterated or uncensored?
MiMo V2.6 Flash Xploded is abliterated: the refusal direction was removed from the weights. GLM 5.3 Xploded, GLM 5.3 Flash Xploded, DeepSeek V4.1 Flash Xploded, Qwen3.8 27B Xploded, Qwen3.8 27B Fast Xploded are uncensored: the refusal was trained back out. The abliterated vs uncensored page explains the difference.
Which one answers fastest?
MiMo V2.6 Flash Xploded usually starts answering in one to two seconds. The GLM 5.3 Flash model thinks before it answers, so its first word can take much longer.