anthracite-org · live price
Magnum v4 72B API pricing
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.
Mid-range ($1–5 per 1M)
- Input
- $2.50
- per 1M tokens
- Output
- $5
- per 1M tokens
- Cached input
- $2.50
- per 1M tokens
- Context
- 33K
- 4K max output
List price from OpenRouter, which passes anthracite-org's price through without markup. Refreshed hourly. Released October 22, 2024. Model id anthracite-org/magnum-v4-72b.
What Magnum v4 72B costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$5.00
1,000 input + 500 output tokens each
1,000 RAG questions
$22.50
8,000 input + 500 output tokens each
100 coding-agent steps
$8.50
30,000 input + 2,000 output tokens each, no caching
Magnum v4 72B price history
No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.
Magnum v4 72B price by host
One host serves this model through OpenRouter.
- Mancer 2$2.50 in · $5 out · 33K ctx · 100.0% uptime 24h
Where to buy anthracite-org credits for less
Magnum v4 72B costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Magnum v4 72B cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$175.00/ month
Cheaper alternatives to Magnum v4 72B
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Mistral: Pixtral Large 2502 | $2 | $6 |
| Qwen: Qwen4 Max | $1.42 | $4.27 |
| Google: Gemini 4 Hydrogen | $1.50 | $7.50 |
| Z.ai: GLM 5.3 FlashX Legal | $0.37 | $1.25 |
| OpenAI: GPT-6.1 Terra Pro | $1 | $5 |
| OpenAI: GPT-6.1 Terra | $1 | $5 |