Kimi K2.8 Preview vs MiniCPM5-2B
Kimi K2.8 Preview comes out ahead, 66 to 31 on our weighted score.
- Our pick
Moonshot AIKimi K2.8 Preview
66/100- ECI—
- Price—
- Context1.05M
OpenBMB
MiniCPM5-2B
31/100- ECI—
- Price$0.124 / $0.743
- Context131K
Add a model
Make it a three-way comparison.
Kimi K2.8 Preview is our pick
Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against MiniCPM5-2B (31). It leads on inputs & features and 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 priceMiniCPM5-2BMiniCPM5-2B $0.279 per 1M tokens (3:1 blend) · Kimi K2.8 Preview unpriced
- Longest contextKimi K2.8 PreviewKimi K2.8 Preview 1,048,576 · MiniCPM5-2B 131,072 tokens
- Widest inputsKimi K2.8 PreviewKimi K2.8 Preview: Text, Images, Video · MiniCPM5-2B: Text
- Self-hostingMiniCPM5-2BPublishes downloadable weights (apache-2.0)
| Measure | Weight | Kimi K2.8 Preview | MiniCPM5-2B |
|---|---|---|---|
| Inputs & features | 60% | 70 | 35 |
| Context window | 40% | 61 | 24 |
| Overall | 100% | 66/100 | 31/100 |
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 | Kimi K2.8 PreviewMoonshot AI | MiniCPM5-2BOpenBMB |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | — | $0.124 |
| Output | — | $0.743 |
| Cached input | — | — |
| Blended (3:1) | — | $0.279 |
| Long-context rate | — | Same rate |
| Price source | — | Median of 1 providers |
| Limits | ||
| Context window | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | — | 131,072 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | No |
| PDFs | No | No |
| Audio | No | No |
| Video | Yes | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Proprietary | Openapache-2.0 |
| API model ID | — | — |
| API providers | — | 1 |
| Released | Sep 11, 2026 | Sep 6, 2026 |
| Knowledge cutoff | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Kimi K2.8 Preview—
- MiniCPM5-2B$2.73
Which should you choose?
Which is better: Kimi K2.8 Preview or MiniCPM5-2B?
Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against MiniCPM5-2B (31). It leads on inputs & features and 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, Kimi K2.8 Preview or MiniCPM5-2B?
MiniCPM5-2B is cheaper at $0.124 input / $0.743 output per million tokens (median across 1 API provider). . At a typical mix of three input tokens to one output token, that is $0.279 per million tokens for MiniCPM5-2B versus . Kimi K2.8 Preview has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Kimi K2.8 Preview has not been scored yet and MiniCPM5-2B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2.8 Preview and MiniCPM5-2B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.
Which has the bigger context window?
Kimi K2.8 Preview has the largest context window at 1,048,576 tokens, against 131,072 for MiniCPM5-2B. Maximum output per response: MiniCPM5-2B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Kimi K2.8 Preview accepts text, images and video; MiniCPM5-2B accepts text. Kimi K2.8 Preview handles the widest range of inputs.
Are any of these open source?
MiniCPM5-2B publishes its weights (apache-2.0) and can be self-hosted; Kimi K2.8 Preview is proprietary.
Which is newer?
Kimi K2.8 Preview is the newest, released Sep 11, 2026. MiniCPM5-2B came out Sep 6, 2026.
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.
