Weaver (alpha)
Mancer · released Aug 2, 2023
- Type
- Proprietary
- Input
- $0.50
- Output
- $0.75
- Cached
- Not published
List price · per 1M tokens · Mancer 2 at 8K context · source ↗
Our take
Written Aug 3, 2026Weaver is a proprietary text-only model from Mancer with an eight-thousand-token request limit and identical pricing across its two hosts. It is a slow, unmeasured option for text generation where speed and verified quality are not priorities.
Pick this for simple text generation tasks where you want the same rate on either host and do not mind waiting. Use it when throughput below six tokens per second is acceptable and you do not need benchmark-backed quality claims. Skip it if you need fast output, a longer request limit, or any measured performance data.
The case for it
- Identical pricing across both tracked hosts, so cost does not lock you to one provider.
- Proprietary hosted weights mean no local hardware requirements.
The case against it
- Very low generation speed on the native host, at 5.5 tokens per second with no faster alternative in our data.
- No benchmark scores on file, so chat, reasoning and coding quality are all unverified.
- Eight-thousand-token request limit is narrow by current standards, with no larger variant listed.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Weaver (alpha) — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Mancer 2's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.50 in / $0.75 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.50 / $0.75 | 8K | not measured | Unknown | Unknown | Unknown |
| Mancer 2fp8 | $0.50 / $0.75 | 8K | 5 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| Mancer 2fp8 | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- mancer-weaver-alpha