Magnum v4 72B
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(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
Magnum v4 72B ranks #280 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $3.75 blended per million tokens, it is cheaper than 24% of models with published API pricing. Its 32,768-token context window is 8.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 4096
Pricing
Output / 1M: 5.00
Blend / 1M: 3.75
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $3.75per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $3.75 |
| 10,000,000 | $37.50 |
| 100,000,000 | $375.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
Closest API price
- Qwen3.6 Max Preview$3.59 / 1M · Q 79.9
- Qwen3.8 Max (0902)$4.00 / 1M · Q 93.0
- GPT-3.5 Turbo 16k$3.50 / 1M
- Qwen3.8 2.4T A95B$4.00 / 1M
- Grok 4.6$4.00 / 1M