Magnum v4 72B
by anthracite-org · anthracite-org/magnum-v4-72b
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. The model is fine-tuned on top of Qwen2.5 72B.
- Input / 1M tokens
- $2.50
- Output / 1M tokens
- $5.00
- Context
- 32.8K
Specs
| Input price | $2.50 / 1M tokens |
|---|---|
| Output price | $5.00 / 1M tokens |
| Context window | 32.8K tokens |
| Max output | 4.1K tokens |
| Reads | text |
| Writes | text |
| Tool calling | No |
| Reasoning | No |
| Listed | Oct 22, 2024 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
1 provider serves this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|
| Mancer 2 | fp8 | 32.8K | 4.1K | $2.50 | $5.00 | 100% | 1.03 s | 16 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- unbiased
Pareto 26.9
- Input
- $2.50
- Output
- $7.50
- Context
- 262K
- Anthropic
Claude Opus 5 (batch)
- Input
- $2.50
- Output
- $12.50
- Context
- 1M
- Anthropic
Claude Opus 4.8 (batch)
- Input
- $2.50
- Output
- $12.50
- Context
- 1M
- OpenAI
GPT-5.5 (batch)
- Input
- $2.50
- Output
- $15.00
- Context
- 1.05M
- Anthropic
Claude Opus 4.7 (batch)
- Input
- $2.50
- Output
- $12.50
- Context
- 1M
- OpenAI
GPT-5.4
- Input
- $2.50
- Output
- $15.00
- Context
- 1.05M