modelgrep
M

Mancer: Weaver (alpha)

mancer/weaver

JSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
32
231st fastest
Latency
1.0s
first token
Input price
$0.750
189th cheapest
Context
8K
2K max out

How it compares

Faster than22%
of all ranked models
Cheaper than37%
of all ranked models

Overview

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.

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mancer 2fp8$0.750$1.00

Specifications

Context window8K
Max output2K
Knowledge cutoffJun 2023
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Weaver (alpha) FAQ

How much does Weaver (alpha) cost?

Weaver (alpha) costs $0.750 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 189th cheapest of 298 paid models.

How fast is Weaver (alpha)?

Weaver (alpha) generates around 32 tokens per second with 1.0s time-to-first-token (p50), the 231st fastest tracked model.

What is Weaver (alpha)'s context window?

Weaver (alpha) supports a 8K-token context window and can output up to 2K tokens. It accepts text input.