deepseek-v4-pro-0813 vs minimax-m3
Side-by-side comparison of deepseek-v4-pro-0813 and minimax-m3: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. deepseek-v4-pro-0813 outperforms minimax-m3 on 4 of 5 shared benchmarks.
deepseek-v4-pro-0813
Input / 1M
$1.32
Output / 1M
$3.96
Context
1M
Model ID
deepseek/deepseek-v4-pro-0813
MiniMax50% off
minimax-m3
Input / 1M
$0.60$0.30
Output / 1M
$2.40$1.20
Context
1M
Model ID
minimaxi/minimax-m3
Benchmark comparison
Intelligence Indexreasoning
deepseek-v4-pro-081342.1%
minimax-m335.7%
Coding Indexcoding
deepseek-v4-pro-081368.8%
minimax-m358.6%
GPQA Diamondreasoning
deepseek-v4-pro-081392.8%
minimax-m392.9%
Terminal-Bench Hardagentic
deepseek-v4-pro-0813N/A
minimax-m342.4%
τ²-Benchagentic
deepseek-v4-pro-0813N/A
minimax-m388.9%
SciCodecoding
deepseek-v4-pro-081351.0%
minimax-m347.1%
Humanity's Last Examreasoning
deepseek-v4-pro-081341.0%
minimax-m339.0%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| deepseek-v4-pro-0813 | minimax-m3 | |
|---|---|---|
| Input price / 1M | $1.32 | $0.60$0.30 |
| Output price / 1M | $3.96 | $2.40$1.20 |
| Context window | 1M tokens | 1M tokens |
| Max output | 384K tokens | 128K tokens |
| Vision input | N/A | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | N/A | N/A |
| Provider | DeepSeek | MiniMax |
Questions people ask
Is deepseek-v4-pro-0813 better than minimax-m3?
deepseek-v4-pro-0813 outperforms minimax-m3 on 4 of 5 shared benchmarks. See the benchmark comparison above for specifics: deepseek-v4-pro-0813 and minimax-m3 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, deepseek-v4-pro-0813 or minimax-m3?
minimax-m3 is cheaper. deepseek-v4-pro-0813 costs $1.32/$3.96 per 1M input/output tokens, while minimax-m3 costs $0.30/$1.20. The prices shown are what you pay: minimax-m3 runs at 50% off its list rate of $0.60 per 1M input and $2.40 per 1M output.
Can I use deepseek-v4-pro-0813 and minimax-m3 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "deepseek/deepseek-v4-pro-0813" and "minimaxi/minimax-m3", no other code changes needed.
What are the context windows?
deepseek-v4-pro-0813 supports up to 1M tokens of context. minimax-m3 supports up to 1M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between deepseek-v4-pro-0813 and minimax-m3 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.