Weaver (alpha)

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

ChatMancer8k tokens$0.545 / $0.8175 · 1M

mancer/weaver

Context
8k tokens
Completion cap
6,000
Tools
No
JSON
Yes
Released
2023-08-02

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mancer/weaver",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Weaver (alpha)?
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations. Weaver (alpha) runs on the Geek Hub API (OpenAI-compatible). Model id: mancer/weaver.
Is Weaver (alpha) free?
No. Input is $0.545 per 1M tokens and output is $0.8175 per 1M tokens on Geek Hub (markup included).
What is the context length of Weaver (alpha)?
Weaver (alpha) has a 8k tokens context window. It supports up to 6,000 completion tokens.
Does Weaver (alpha) support tool calling and structured outputs?
Weaver (alpha) does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Weaver (alpha) released?
Weaver (alpha) was released on 2023-08-02.