This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tu…
Model details →Magnum v4 72B vs Mancer: Weaver (alpha)
Mancer: Weaver (alpha) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
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.
Model details →Side-by-side comparison
| Capability | Magnum v4 72B | Mancer: Weaver (alpha) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 16K | 8K | 🏆 Magnum v4 72B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.00 | $0.75 | 🏆 Mancer: Weaver (alpha) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $5.00 | $1.00 | 🏆 Mancer: Weaver (alpha) |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Magnum v4 72B better than Mancer: Weaver (alpha)?
Mancer: Weaver (alpha) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Magnum v4 72B and Mancer: Weaver (alpha)?
Input: $3.00 vs $0.75 per 1M tokens. Output: $5.00 vs $1.00 per 1M tokens.
What context windows do Magnum v4 72B and Mancer: Weaver (alpha) support?
Magnum v4 72B supports up to 16K tokens. Mancer: Weaver (alpha) supports up to 8K tokens.
Do both Magnum v4 72B and Mancer: Weaver (alpha) support tool calling?
Magnum v4 72B: not advertised. Mancer: Weaver (alpha): not advertised.