Magnum v4 72B pricing
$2.50 per 1M input tokens and $5.00 per 1M output tokens. In real work that is 0.52¢ per chat answer and 3.6¢ to summarize a 20-page PDF.
What Magnum v4 72B costs per task
Token counts estimated from a measured model of the same lab (MiniMax M3), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.52¢$5.18 / 1,000 | 206 in · 451 out · 482 reasoning | 225 of 336 | estimated |
| Reply to a customer email | 0.33¢$3.30 / 1,000 | 420 in · 262 out · 187 reasoning | 260 of 336 | estimated |
| Write a 1,500-word blog post | 1.2¢$11.71 / 1,000 | 220 in · 1,790 out · 442 reasoning | 196 of 336 | estimated |
| Write 10 product descriptions | 0.92¢$9.16 / 1,000 | 444 in · 1,080 out · 531 reasoning | 200 of 336 | estimated |
| Translate 1,000 words | 3.2¢$32.47 / 1,000 | 1,486 in · 1,217 out · 4,535 reasoning | 279 of 336 | estimated |
| Proofread one page (500 words) | 0.76¢$7.56 / 1,000 | 881 in · 656 out · 416 reasoning | 247 of 336 | estimated |
| Summarize a 20-page PDF | 3.6¢$36.10 / 1,000 | 13,017 in · 466 out · 246 reasoning | 276 of 336 | estimated |
| Extract data from an invoice | 0.56¢$5.64 / 1,000 | 540 in · 568 out · 289 reasoning | 243 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥9.2¢$92.47 / 1,000 | 4,984 in · 154 out · 15,847 reasoning | 282 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 1.6¢$15.85 / 1,000 | 3,807 in · 829 out · 437 reasoning | 270 of 336 | estimated |
| Classify 100 support tickets | 1.3¢$13.23 / 1,000 | 1,436 in · 444 out · 1,485 reasoning | 226 of 336 | estimated |
| Review 500 lines of code | 2.5¢$25.07 / 1,000 | 4,805 in · 2,611 out | 218 of 336 | estimated |
| Write a SQL query | 0.42¢$4.22 / 1,000 | 274 in · 708 out | 208 of 336 | estimated |
| Run a 50-step coding agent | $5.73$5,727 / 1,000 | 2,241,975 in · 15,030 out · 9,350 reasoning | 318 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Magnum v4 72B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| M Mancer 2fp8 | $2.50 / $5.00 | - | 32K | 100% |
Price history
First seen in our price history on Nov 4, 2024 at $1.88 input / $2.25 output. Since then the output price moved from $2.25 to $5.00 per 1M tokens (7 changes).
FAQ
How much does Magnum v4 72B cost?
Magnum v4 72B costs $2.50 per 1 million input tokens and $5.00 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.52¢ and summarizing a 20-page PDF about 3.6¢.
Where is Magnum v4 72B cheapest?
Among 1 providers we track, the lowest list price today is at Mancer 2: $2.50 input and $5.00 output per 1M tokens.
Is the Magnum v4 72B cost per task measured or estimated?
Estimated: Magnum v4 72B was not run directly. Tokens come from MiniMax M3 and are rescaled by the tokenizer of Anthracite Org. Real usage can differ.