MiniCPM5-2B
Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks.
- Capability
- —No ECI score yet
- Input
- $0.124per 1M tokens
- Output
- $0.743per 1M tokens
- Context
- 131K131K max output
What it costs
- Input
- $0.124per million tokens
- Output
- $0.743per million tokens
- Blended (3:1)
- $0.279cheaper than 72% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.619 |
| Team assistant25M input + 5M output tokens | $6.81 |
| Production app250M input + 50M output tokens | $68.13 |
Median of 1 paid API provider on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for MiniCPM5-2B yet.
The details
- Lab
- OpenBMB
- Released
- Sep 6, 2026
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights · apache-2.0
- Availability
- 1 API providerlisted on models.dev
More from OpenBMB
About MiniCPM5-2B
How much does MiniCPM5-2B cost?
MiniCPM5-2B costs $0.124 input / $0.743 output per million tokens (median across 1 API provider). At a 3:1 input-to-output mix that is $0.279 per million tokens, cheaper than 72% of the 360 priced models we track.
What is the context window of MiniCPM5-2B?
MiniCPM5-2B accepts up to 131,072 tokens per request and can write up to 131,072 tokens in one response.
How good is MiniCPM5-2B?
Epoch AI has not published a Capabilities Index score for MiniCPM5-2B yet.
Is MiniCPM5-2B open source?
Yes. OpenBMB publishes the weights under the apache-2.0 licence, so it can be downloaded and self-hosted.
What inputs does MiniCPM5-2B support?
MiniCPM5-2B accepts text and replies in text. It is a reasoning model, supports tool calling.
When was MiniCPM5-2B released?
OpenBMB released MiniCPM5-2B on Sep 6, 2026.
What are the best alternatives to MiniCPM5-2B?
The closest current models from other labs on capability, price and release date are Qwen3.8 Flash Next (Alibaba (Qwen), $0.20 / $0.50), DeepSeek V4 Flash Vision Exp (DeepSeek, $0.216 / $0.647), Hy3 (Tencent, $0.132 / $0.53) and Viv Fast (Vivgrid, $0.13 / $0.40).