MiniCPM5-1B vs Nex-N2-Pro vs Command A Plus
Nex-N2-Pro comes out ahead, 57 to 52 and 31 on our weighted score, and it is the cheaper option too.
OpenBMB
MiniCPM5-1B
31/100- ECI—
- Price—
- Context131K
- Our pick
Nex AGI
Nex-N2-Pro
57/100- ECI—
- Price$0.50 / $2.50
- Context262K
CohereCommand A Plus
52/100- ECI—
- Price$2.50 / $10.00
- Context128K
Nex-N2-Pro is our pick
Nex-N2-Pro is the better all-round choice, scoring 57/100 against Command A Plus (52) and MiniCPM5-1B (31). It leads on context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNex-N2-ProNex-N2-Pro $1.00 · Command A Plus $4.38 per 1M tokens (3:1 blend) · MiniCPM5-1B unpriced
- Longest contextNex-N2-ProNex-N2-Pro 262,144 · MiniCPM5-1B 131,072 · Command A Plus 128,000 tokens
- Widest inputsNex-N2-Pro and Command A PlusMiniCPM5-1B: Text · Nex-N2-Pro: Text, Images · Command A Plus: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MiniCPM5-1B | Nex-N2-Pro | Command A Plus |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 70 | 70 |
| Context window | 40% | 24 | 37 | 24 |
| Overall | 100% | 31/100 | 57/100 | 52/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiniCPM5-1BOpenBMB | Nex-N2-ProNex AGI | Command A PlusCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | $0.50 (best) | $2.50 |
| Output | — | $2.50 (best) | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | — | $1.00 (best) | $4.38 |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 1 providers | Official Cohere API |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 128,000 tokens |
| Max output | 131,072 tokens | 262,144 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Openapache-2.0 | Open | Open |
| API model ID | — | — | command-a-plus-05-2026 |
| API providers | — | 1 | 1 |
| Released | May 19, 2026 | Jun 2, 2026 | May 20, 2026 |
| Knowledge cutoff | — | — | Apr 1, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiniCPM5-1B—
- Nex-N2-Pro$10.00
- Command A Plus$45.00
Which should you choose?
Which is better: MiniCPM5-1B, Nex-N2-Pro or Command A Plus?
Nex-N2-Pro is the better all-round choice, scoring 57/100 against Command A Plus (52) and MiniCPM5-1B (31). It leads on context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MiniCPM5-1B, Nex-N2-Pro or Command A Plus?
Nex-N2-Pro is cheaper at $0.50 input / $2.50 output per million tokens (median across 1 API provider). Command A Plus costs $2.50 input / $10.00 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Nex-N2-Pro versus $4.38 for Command A Plus (4.4× as much). MiniCPM5-1B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniCPM5-1B has not been scored yet, Nex-N2-Pro has not been scored yet and Command A Plus has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniCPM5-1B, Nex-N2-Pro and Command A Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Nex-N2-Pro has the largest context window at 262,144 tokens, against 131,072 for MiniCPM5-1B and 128,000 for Command A Plus. Maximum output per response: MiniCPM5-1B up to 131,072, Nex-N2-Pro up to 262,144, Command A Plus up to 64,000 tokens.
Which can read images, PDFs, audio or video?
MiniCPM5-1B accepts text; Nex-N2-Pro accepts text and images; Command A Plus accepts text and images. Nex-N2-Pro handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (apache-2.0), so you can self-host them.
Which is newer?
Nex-N2-Pro is the newest, released Jun 2, 2026. Command A Plus came out May 20, 2026; MiniCPM5-1B came out May 19, 2026. Knowledge cutoff: Command A Plus Apr 1, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
