Mancer
1 model built · 6 served
Mancer is an API-only host built around a single model: Weaver (alpha). It's served through Mancer's own service and picked up by aggregators like OpenKey, rather than sold through a broad platform presence. There's no public record here of founding details or funding — Mancer reads as a narrow, focused operation rather than a general-purpose lab chasing a wide model lineup. If you've used Weaver before through another host, this is the same model, same pricing structure, just routed through one API key alongside everything else you use.
Lineup
There's one model to choose from: Weaver (alpha), at $0.75/M input tokens and $1.00/M output tokens, with an 8,000-token context window. Through OpenKey that's $0.7725/M input and $1.03/M output ($0.75 x 1.03 and $1.00 x 1.03) after the flat 3% fee. No free tier, no cheaper or pricier sibling to weigh it against — if Weaver fits your use case, use it; if you need longer context or lower cost, look at another lab's lineup.
- Weaver (alpha)Aug 2, 2023 8K $0.772 $1.03 ctx 8K · in $0.772 · out $1.03
Prices per 1M tokens, flat 3% fee included.
Models Mancer serves
Beyond its own models, Mancer hosts 6 models in the OpenKey catalog. Prices are Mancer’s own list price per 1M input tokens, before our fee.
| Model | Built by | Context | Input /M |
|---|---|---|---|
| Magnum v4 72B | Anthracite | 33K | $3.00 |
| DeepSeek V4 Flash | DeepSeek | 1.0M | $0.250 |
| MythoMax 13B | Gryphe | 4K | $0.450 |
| Weaver (alpha) | Mancer | 8K | $0.500 |
| gpt-oss-120b | OpenAI | 131K | $0.055 |
| ReMM SLERP 13B | Undi95 | 6K | $0.450 |
From the OpenRouter catalog, Jul 28, 2026. All providers
Privacy policy ↗Terms of service ↗
Questions
- What does Mancer's Weaver model cost?
- Weaver (alpha) is priced at $0.75 per 1M input tokens and $1.00 per 1M output tokens direct from Mancer. Through OpenKey, that becomes $0.7725/M input and $1.03/M output after the flat 3% fee ($0.75 x 1.03 and $1.00 x 1.03). There's no free version and no alternate tier — this is the only price point Mancer offers.
- Is Weaver the best or cheapest model to use from Mancer?
- It's both, by default — Weaver (alpha) is the only model Mancer offers, so there's no lineup to compare within. Context length is 8,000 tokens, released August 2023. Judge it against models from other labs on OpenKey if you need a price or context comparison point.
- Can I access Mancer's Weaver model through OpenKey's API?
- Yes. OpenKey gives you one API key across 329 models from 52 labs, including Mancer's Weaver (alpha), so you don't need a separate Mancer account or key to call it alongside other providers' models.