MiniMax M2.7 vs Qwen2.5 72B API pricing
Updated
MiniMax M2.7: USD 0.21 input, USD 0.84 output per 1M tokens (GMI Cloud, promotional). Qwen2.5 72B: USD 0.36 input, USD 0.40 output per 1M tokens (DeepInfra). At 3 input tokens per output token, Qwen2.5 72B costs 0.7% more than MiniMax M2.7 (USD 0.37 vs USD 0.3675 per 1M).
How do MiniMax M2.7 and Qwen2.5 72B differ on price?
- Cheapest input price: MiniMax M2.7 USD 0.21 against USD 0.36 per 1M tokens, so Qwen2.5 72B costs 1.71× as much (71% more).
- Cheapest output price: Qwen2.5 72B USD 0.40 against USD 0.84 per 1M tokens, so MiniMax M2.7 costs 2.1× as much.
- Among the 201 indexed models, MiniMax M2.7 ranks 77th cheapest and Qwen2.5 72B 78th on the 3:1 blend.
- The cheaper model changes at 2.9 input tokens per output token.
- Only MiniMax M2.7 lists a cached-input discount: MiniMax M2.7 at 3 standard prices of 3, from USD 0.042 (GMI Cloud, 80% below that provider's input price). Qwen2.5 72B's cached tokens bill at the input price.
- MiniMax M2.7 states up to 204,800 tokens of context, 6.3× the 32,768 of Qwen2.5 72B.
- Both have 3 providers with a standard price; 1 provider sells both (Featherless).
- On one account, Featherless charges USD 0.525 for MiniMax M2.7 (1.43× its cheapest price) and USD 0.3775 for Qwen2.5 72B (1.02× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for MiniMax M2.7: its dearest standard price is 1.79× its cheapest, against 1.59× for Qwen2.5 72B.
MiniMax M2.7 and Qwen2.5 72B prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | MiniMax M2.7 | Qwen2.5 72B |
|---|---|---|
| Model page | MiniMax M2.7 MiniMax · 3 providers | Qwen2.5-72B-Instruct Qwen · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.3675 lower promo USD 0.21 in / USD 0.84 out at GMI Cloud GMI Cloud page checked 2026-11-15 | USD 0.37 USD 0.36 in / USD 0.40 out at DeepInfra DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.21 lower promo GMI Cloud source | USD 0.36 DeepInfra source |
| Cheapest cached input | USD 0.042 promo GMI Cloud source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.84 promo GMI Cloud source | USD 0.40 lower DeepInfra source |
| Cheapest non-promotional price | USD 0.30 / USD 1.20 Featherless, USD 0.525 blended source | The cheapest price is not promotional. |
| Maker's own API | MiniMax publishes no paid standard price on its own API that we found. | Qwen publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.30 / USD 1.20 input / output, 3 prices | USD 0.37 / USD 0.40 input / output, 3 prices |
| Context window | 204,800 tokens, largest stated; from 196,608 at some providers | 32,768 tokens, largest stated |
| Providers with a standard price | 3 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do MiniMax M2.7 and Qwen2.5 72B cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | MiniMax M2.7 | Qwen2.5 72B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 24.95 GMI Cloud | USD 39.60 DeepInfra | USD 14.65 MiniMax M2.7 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 50.90 GMI Cloud | USD 92.40 DeepInfra | USD 41.50 MiniMax M2.7 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 196.56 GMI Cloud | exceeds context | — |
MiniMax M2.7 is cheaper on 2 workloads. The widest gap is on RAG over documents: the dearer model costs 82% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 2.9 input tokens per output token, Qwen2.5 72B is cheaper; above 2.9, MiniMax M2.7 is cheaper. At the site's 3:1 blend, MiniMax M2.7 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | MiniMax M2.7 | Qwen2.5 72B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.6825 GMI Cloud | USD 0.39 lower DeepInfra |
| 1 : 1 | USD 0.525 GMI Cloud | USD 0.38 lower DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.3675 lower GMI Cloud | USD 0.37 DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.2673 lower GMI Cloud | USD 0.3636 DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.2303 lower GMI Cloud | USD 0.3613 DeepInfra |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do MiniMax M2.7 and Qwen2.5 72B cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and MiniMax M2.7 and Qwen2.5 72B are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- MiniMax M2.7 API pricing: all 3 providers and other tiers.
- Qwen2.5-72B-Instruct API pricing: all 3 providers and other tiers.
- Cost calculator with MiniMax M2.7 and Qwen2.5 72B preloaded
- Token counter
- Qwen token counter
- Prompt caching calculator
More comparisons: MiniMax M3 vs MiniMax M2.7 · MiniMax M2.7 vs MiniMax M2.5 · Llama 3.3 70B vs Qwen2.5 72B · Qwen2.5 72B vs Qwen 2.5 7B · every MiniMax M2.7 comparison · every Qwen2.5 72B comparison · all 662 price comparisons
Questions
Is MiniMax M2.7 cheaper than Qwen2.5 72B?
Yes. On a blend of 3 input tokens to 1 output token, MiniMax M2.7 costs USD 0.3675 per 1M tokens and Qwen2.5 72B USD 0.37, at each model's cheapest standard price. For input alone, MiniMax M2.7 is cheaper (USD 0.21 against USD 0.36 per 1M); for output alone, Qwen2.5 72B is (USD 0.40 against USD 0.84). This compares price only, not quality.
What do MiniMax M2.7 and Qwen2.5 72B cost per 1M tokens?
MiniMax M2.7: from USD 0.21 input and USD 0.84 output at GMI Cloud (promotional); median of 3 standard prices USD 0.30 / USD 1.20. Qwen2.5 72B: from USD 0.36 input and USD 0.40 output at DeepInfra; median of 3 standard prices USD 0.37 / USD 0.40. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both MiniMax M2.7 and Qwen2.5 72B?
1 provider has a standard price for both: Featherless (USD 0.525 and USD 0.3775 at 3:1). Buying each model from its own cheapest provider costs USD 0.3675 and USD 0.37.
At what input:output ratio does the cheaper of MiniMax M2.7 and Qwen2.5 72B change?
The cheaper model changes with the mix: below 2.9 input tokens per output token, Qwen2.5 72B is cheaper; above 2.9, MiniMax M2.7 is cheaper. At the site's 3:1 blend, MiniMax M2.7 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do MiniMax M2.7 and Qwen2.5 72B have cached input pricing?
MiniMax M2.7 from USD 0.042 per 1M cached input tokens (GMI Cloud; 3 of 3 standard prices list a discount). Qwen2.5 72B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, MiniMax M2.7 or Qwen2.5 72B?
MiniMax M2.7: up to 204,800 tokens, against 32,768 for Qwen2.5 72B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.