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 →Mancer: Weaver (alpha) vs Microsoft: Phi 4
Microsoft: Phi 4 wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Model details →Side-by-side comparison
| Capability | Mancer: Weaver (alpha) | Microsoft: Phi 4 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 8K | 16K | 🏆 Microsoft: Phi 4 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.40 | $0.07 | 🏆 Microsoft: Phi 4 |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.75 | $0.14 | 🏆 Microsoft: Phi 4 |
| 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 Mancer: Weaver (alpha) better than Microsoft: Phi 4?
Microsoft: Phi 4 wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mancer: Weaver (alpha) and Microsoft: Phi 4?
Input: $0.40 vs $0.07 per 1M tokens. Output: $0.75 vs $0.14 per 1M tokens.
What context windows do Mancer: Weaver (alpha) and Microsoft: Phi 4 support?
Mancer: Weaver (alpha) supports up to 8K tokens. Microsoft: Phi 4 supports up to 16K tokens.
Do both Mancer: Weaver (alpha) and Microsoft: Phi 4 support tool calling?
Mancer: Weaver (alpha): not advertised. Microsoft: Phi 4: not advertised.