BroadRouter

MiniMax M3 vs Qwen2.5 72B API pricing

Updated

MiniMax M3: USD 0.23 input, USD 0.96 output per 1M tokens (CoreWeave Forge). Qwen2.5 72B: USD 0.36 input, USD 0.40 output per 1M tokens (DeepInfra). At 3 input tokens per output token, MiniMax M3 costs 11% more than Qwen2.5 72B (USD 0.4125 vs USD 0.37 per 1M).

Picked by the same-tier rule: both are in the second quarter of the indexed models by price (USD 0.1556 to USD 0.4512 per 1M tokens at 3:1) and in the same size class, mid-size (no tier word, 40B to 200B parameters or no size in the name). MiniMax M3 is the 4th-closest-priced model from another maker to Qwen2.5 72B in that bucket. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do MiniMax M3 and Qwen2.5 72B differ on price?

MiniMax M3 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.

MiniMax M3 and Qwen2.5 72B API prices compared
PriceMiniMax M3Qwen2.5 72B
Model pageMiniMax M3
MiniMax · 10 providers
Qwen2.5-72B-Instruct
Qwen · 3 providers
Cheapest standard price, blended 3:1USD 0.4125
USD 0.23 in / USD 0.96 out at CoreWeave Forge
CoreWeave Forge page checked 2026-11-15
USD 0.37 lower
USD 0.36 in / USD 0.40 out at DeepInfra
DeepInfra page checked 2026-11-14
Cheapest inputUSD 0.23 lower
CoreWeave Forge source
USD 0.36
DeepInfra source
Cheapest cached inputUSD 0.048 promo
GMI Cloud source
No standard price lists a cache price; cached tokens bill at the input price.
Cheapest outputUSD 0.96
CoreWeave Forge source
USD 0.40 lower
DeepInfra source
Maker's own APIUSD 0.30 / USD 1.20
MiniMax source
Qwen publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.30 / USD 1.20
input / output, 10 prices
USD 0.37 / USD 0.40
input / output, 3 prices
Context window1,048,576 tokens, largest stated; from 262,144 at some providers32,768 tokens, largest stated
Providers with a standard price103

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do MiniMax M3 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).

Monthly cost of three workloads on MiniMax M3 and Qwen2.5 72B
WorkloadMiniMax M3Qwen2.5 72BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 28.26
CoreWeave Forge
USD 39.60
DeepInfra
USD 11.34
MiniMax M3 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 56.64
CoreWeave Forge
USD 92.40
DeepInfra
USD 35.76
MiniMax M3 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 224.64
GMI Cloud
exceeds context—

MiniMax M3 is cheaper on 2 workloads. The widest gap is on RAG over documents: the dearer model costs 63% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 4.3 input tokens per output token, Qwen2.5 72B is cheaper; above 4.3, MiniMax M3 is cheaper. At the site's 3:1 blend, Qwen2.5 72B 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.

Price per 1M tokens of MiniMax M3 and Qwen2.5 72B at different input:output mixes
Input : output tokensMiniMax M3Qwen2.5 72B
1 : 3 (long answers)USD 0.7775
CoreWeave Forge
USD 0.39 lower
DeepInfra
1 : 1USD 0.595
CoreWeave Forge
USD 0.38 lower
DeepInfra
3 : 1 (the site’s blend)USD 0.4125
CoreWeave Forge
USD 0.37 lower
DeepInfra
10 : 1 (retrieval, long prompts)USD 0.2964 lower
CoreWeave Forge
USD 0.3636
DeepInfra
30 : 1 (agents, big contexts)USD 0.2535 lower
CoreWeave Forge
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 M3 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 Qwen2.5 72B is not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: MiniMax M3 vs MiniMax M2.5 · GLM 5.3 vs MiniMax M3 · Kimi K3 vs MiniMax M3 · Qwen3.8 27B vs MiniMax M3 · DeepSeek V4.1 Flash vs MiniMax M3 · MiniMax M3 vs MiniMax M2.7 · Llama 3.3 70B vs Qwen2.5 72B · Qwen2.5 72B vs Qwen 2.5 7B · every MiniMax M3 comparison · every Qwen2.5 72B comparison · all 662 price comparisons

Questions

Is MiniMax M3 cheaper than Qwen2.5 72B?

No. On a blend of 3 input tokens to 1 output token, Qwen2.5 72B costs USD 0.37 per 1M tokens and MiniMax M3 USD 0.4125, at each model's cheapest standard price. For input alone, MiniMax M3 is cheaper (USD 0.23 against USD 0.36 per 1M); for output alone, Qwen2.5 72B is (USD 0.40 against USD 0.96). This compares price only, not quality.

What do MiniMax M3 and Qwen2.5 72B cost per 1M tokens?

MiniMax M3: from USD 0.23 input and USD 0.96 output at CoreWeave Forge; MiniMax's own API charges USD 0.30 / USD 1.20; median of 10 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 M3 and Qwen2.5 72B?

3 providers have a standard price for both: DeepInfra (USD 0.485 and USD 0.37 at 3:1), SiliconFlow (USD 0.525 and USD 0.59 at 3:1), Featherless (USD 0.9625 and USD 0.3775 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.4125 and USD 0.37.

At what input:output ratio does the cheaper of MiniMax M3 and Qwen2.5 72B change?

The cheaper model changes with the mix: below 4.3 input tokens per output token, Qwen2.5 72B is cheaper; above 4.3, MiniMax M3 is cheaper. At the site's 3:1 blend, Qwen2.5 72B 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 M3 and Qwen2.5 72B have cached input pricing?

MiniMax M3 from USD 0.048 per 1M cached input tokens (GMI Cloud; 10 of 10 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 M3 or Qwen2.5 72B?

MiniMax M3: up to 1,048,576 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.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity