LLM Comparison
DeepSeek V4 Pro vs MiniMax M2.5
Side-by-side specs, pricing & capabilities · Updated September 2026
Price vs Intelligence
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 55 20.9 | 48 86.3 |
| Family | DeepSeek V4 | MiniMax |
| Status | Current | Current |
| Release Date | Aug 2026 | Feb 2026 |
| Context Window | 1.0M tokens | 197K tokens |
| Input Price | $1.32/M tokens | $0.12/M tokens |
| Output Price | $3.96/M tokens | $0.99/M tokens |
| Pricing Notes | DeepSeek direct API, DeepSeek-V4-Pro-0813: headline prices are peak uncached input $1.32 and output $3.96 per million tokens. Off-peak input is $0.66 and output $1.98; cache-hit input is $0.044 peak/$0.022 off-peak. Peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday-Friday; all other hours are off-peak. DeepSeek has withdrawn the planned September 14, 2026 retirement and continues this API. Rates are conditional, not an unconditional off-peak offer. | Cache read: $0.0590/M tokens |
| Capabilities | reasoningcodingtool-usestructured-outputlong-contextagenticresponses-api | textcode |
| Max Output | 393K tokens | 66K tokens |
| API Identifier | deepseek-v4-pro | minimax/minimax-m2.5 |
| Benchmarks | ||
| Artificial Analysis Intelligence Index v4.1 | 44artificial-analysis | — |
| Artificial Analysis Intelligence Index v4.1.1 | 53artificial-analysis | — |
| Artificial Analysis Intelligence Index v4.3 | 36.2829artificial-analysis | — |
| GPQA Diamond | 92.8283artificial-analysis | 84.8485artificial-analysis |
| SciCode | 51.0417artificial-analysis | — |
| Terminal-Bench 2.1 | 78.6517artificial-analysis | — |
| View DeepSeek V4 Pro | View MiniMax M2.5 | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| MiniMax M2.5Cheapest | $0.12 | $0.50 | $0.61 | — |
| DeepSeek V4 Pro | $1.32 | $1.98 | $3.30 | +438% |
DeepSeek
DeepSeek V4 Pro
DeepSeek V4 Pro 0813 is an open-weight Mixture-of-Experts reasoning model for long-context coding, tool use, and agentic workloads, with native Responses API support through the DeepSeek API.
MiniMax
MiniMax M2.5
MiniMax M2.5 is a large language model from MiniMax. Supports up to 196,608 token context window. Available from $0.12/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs