Providers /Mancer 2
Inference provider

Mancer 2

Models
7
Regions
00

Our take

Editorial by LLMap · updated Jul 28, 2026

A niche host with a tiny 7-offer catalogue skewed toward roleplay and downloadable models. It has the cheapest tracked input price for openai-gpt-oss-120b but highly variable throughput and no verified compliance disclosures.

Use this for budget access to openai-gpt-oss-120b at $0.055 per million input tokens. Pick it for roleplay or creative writing on undi95-remm-slerp-13b or gryphe-mythomax-13b if you can tolerate slow response times. Skip it if you need a broad model choice, consistent speed, or any verified compliance, geographic, or data-handling assurances.

Strengths
  • Cheapest tracked input price for openai-gpt-oss-120b in the sample — $0.055 per million tokens.
  • Carries some roleplay-specialized models competitors may not: undi95-remm-slerp-13b, gryphe-mythomax-13b, mancer-weaver-alpha, and anthracite-org-magnum-v4-72b in a 7-offer catalogue.
Trade-offs
  • Extremely small catalogue limits model choice — 7 tracked offers, with one model duplicated; throughput is highly variable and often poor.
  • No verified compliance, geographic, or data-handling disclosures — HQ country, EU endpoint, prompt-training policy, SOC 2, and zero-retention option are all unverified in our data.
  • Expensive flagship relative to throughput: anthracite-org-magnum-v4-72b at $3.00/$5.00 per million tokens with only 22 tps.
01

Privacy & data handling

Yes
No
No answer on record

The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.

Trains on your prompts
No
Logs prompts
No
Offered
No answer on record

Prompt retention: none.

02

Models & pricing

Something wrong on this page? Tell us