LLM Comparison
DeepSeek V4 Flash 0731 vs MiniCPM
Side-by-side specs, pricing & capabilities · Updated August 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 46 219 | |
| Family | DeepSeek V4 Flash | MiniCPM |
| Status | Current | Current |
| Release Date | Jul 2026 | — |
| Context Window | 1.0M tokens | 128K tokens |
| Input Price | $0.14/M tokens | Free |
| Output Price | $0.28/M tokens | Free |
| Pricing Notes | DeepSeek API pricing lists $0.0028 cache-hit input, $0.14 cache-miss input, and $0.28 output per 1M tokens for deepseek-v4-flash; peak pricing may change after a future official announcement. | Open-weight GitHub and Hugging Face model family. There is no fixed vendor API price; runtime cost depends on the host, hardware, or inference provider. |
| Capabilities | reasoningcodingtool-usestructured-outputlong-contextresponses-api | textcodereasoninglocal-inference |
| Training Cutoff | — | Not publicly specified in queued source |
| Max Output | 393K tokens | 33K tokens |
| API Identifier | deepseek-v4-flash | OpenBMB/MiniCPM |
| Benchmarks | ||
| Artificial Analysis Intelligence Index v4.1 | 50artificial-analysis | — |
| Artificial Analysis Intelligence Index v4.1.1 | 52artificial-analysis | — |
| MiniCPM-SALA standard benchmark average | — | 76.53official-github-readme |
| MiniCPM-SALA long-context average | — | 38.97official-github-readme |
| MiniCPM-SALA 2048K extrapolation score | — | 81.6official-github-readme |
| MiniCPM4.1 reasoning decoding speedup | — | 3official-github-readme |
| MiniCPM4 Jetson AGX Orin decoding speedup vs Qwen3-8B | — | 7official-github-readme |
| View DeepSeek V4 Flash 0731 | View MiniCPM | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| MiniCPMCheapest | $0.00 | $0.00 | $0.00 | — |
| DeepSeek V4 Flash 0731 | $0.14 | $0.14 | $0.28 | +0% |
DeepSeek
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is an open-weight, cost-efficient reasoning model for long-context coding, agent tasks, and API workflows through DeepSeek.
OpenBMB
MiniCPM
MiniCPM is OpenBMB’s ultra-efficient open language-model family for edge and end-device deployment. The MiniCPM4 and MiniCPM4.1 lines focus on fast local reasoning, while MiniCPM-SALA extends the family toward sparse/linear attention and million-token context research.
More Comparisons
Looking for more AI models?
Browse All LLMs