MiniMax M2.5 vs MiniMax M3
MiniMax M2.5 (MiniMax) and MiniMax M3 (MiniMax) are listed at different prices. MiniMax M2.5 costs less: $0.27 per 1M input tokens and $0.95 per 1M output tokens, against $0.30 and $1.20 for MiniMax M3. MiniMax M3 has the larger context window, 1,048,576 tokens against 198,000 for MiniMax M2.5. MiniMax M3 can write up to 512,000 tokens in one response, against 32,768 for MiniMax M2.5. MiniMax M2.5 accepts text and produces text; MiniMax M3 accepts text, images and video and produces text.
MiniMax M2.5 accepts and produces text, with a 198,000-token context window; MiniMax M3 accepts text, images, and video and produces text, with a 1,048,576-token context window. Both support tools, structured outputs, response formats, and reasoning.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | MiniMax M2.5 | MiniMax M3 |
|---|---|---|
| Maker | MiniMax | MiniMax |
| Added to catalog | 12 Feb 2026 | 31 May 2026 |
| Input, per 1M tokens | $0.27 | $0.30 |
| Output, per 1M tokens | $0.95 | $1.20 |
| Cached input read, per 1M | $0.03 | $0.06 |
| Context windowTokens | 198,000 | 1,048,576 |
| Max outputTokens | 32,768 | 512,000 |
| Accepts | text | image, text, video |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | MiniMax M2.5 | MiniMax M3 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0004 | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0075 | $0.0085 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.010 | $0.011 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.042 | $0.047 |
Which to choose
Choose MiniMax M2.5 if
- Input tokens cost less: $0.27 against $0.30 per 1M
- Output tokens cost less: $0.95 against $1.20 per 1M
- Cached input costs less: $0.03 against $0.06 per 1M
Choose MiniMax M3 if
- You need the larger context window: 1,048,576 tokens against 198,000
- You need longer answers in one response: 512,000 tokens against 32,768
- It has to read images and video, which the other model does not
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.