AI model comparison
MiniMax M3 vs DeepSeek V3.1 Terminus
Side by side comparison of MiniMax M3 and DeepSeek V3.1 Terminus on pricing, benchmark scores, context window, and more.
MiniMax-M3 is a multimodal foundation model from MiniMax.
- Input / 1M
- $0.30
- Output / 1M
- $1.20
- Context
- 1.05M
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's
- Input / 1M
- $0.27
- Output / 1M
- $1
- Context
- 164K
Comparing image generators? Compare image models
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
DeepSeek V3.1 Terminus
1.2x cheaper for a typical chat
Higher intelligence score
MiniMax M3
18.9 vs 14.8 on Artificial Analysis
Larger context window
MiniMax M3
1.05M vs 164K tokens
Newer release
MiniMax M3
Released May 31, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
MiniMax M3 vs DeepSeek V3.1 Terminus API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $0.30 | $0.27 |
| Output tokensPer 1M tokens | $1.20 | $1 |
| Cached input (read)Per 1M tokens | $0.06 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Coding task
30K in, 4K out
Long document summary
150K in, 2K out
Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | ||
|---|---|---|
| Context window | 1.05M tokens | 164K tokens |
| Max output | 512K tokens | 147K tokens |
| Input types | Image, Text, Video | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | May 31, 2026 | September 22, 2025 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Not supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Not supported | Not supported |
Our take
DeepSeek V3.1 Terminus is 1.2x cheaper for a typical chat. MiniMax M3 scores higher on the Artificial Analysis Intelligence Index (18.9 vs 14.8). MiniMax M3 has the larger context window (1.05M vs 164K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is MiniMax M3 or DeepSeek V3.1 Terminus cheaper?
DeepSeek V3.1 Terminus is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1 per 1M output tokens, while MiniMax M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.
Which has a bigger context window, MiniMax M3 or DeepSeek V3.1 Terminus?
MiniMax M3 supports up to 1.05M tokens of context, compared with 164K for DeepSeek V3.1 Terminus.
Is MiniMax M3 smarter than DeepSeek V3.1 Terminus?
On the Artificial Analysis Intelligence Index, MiniMax M3 scores 18.9 and DeepSeek V3.1 Terminus scores 14.8, putting MiniMax M3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use MiniMax M3 and DeepSeek V3.1 Terminus at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see MiniMax M3 and DeepSeek V3.1 Terminus answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to MiniMax M3 and DeepSeek V3.1 Terminus at the same time. Compare the answers side by side and keep the best one.