← All open-weight models

Chinese AI labs · Reasoning

ERNIE-4.5-21B-A3B-Thinking

Small Apache-2.0 reasoning model that runs on a single modern GPU; not a line item in Qianfan's price table, so treat it as self-host-only.

Open weights · Permissive (Apache, MIT, OpenMDW) · Data checked September 6, 2026 · Not a hands-on evaluation

Model ID

Parameters
21B total · 3B active21B total / 3B active MoE (64 text experts, 6 active + 2 shared, 28 layers)
Architecture
Mixture of experts
Context window
131,072 tokensMaximum input
Max output
Not recordedPer response
Input price
Not published
Output price
Not published
Cached input
Not published
Blended price
Not available3:1 input to output
Knowledge cutoff
Not recorded
Released
Not recorded
Status
ga
Size band
15B to 40B

License and openness

ERNIE-4.5-21B-A3B-Thinking is released under the Apache-2.0. This is a permissive license. It generally allows use, modification and redistribution, including commercial use, subject to attribution and notice requirements. License terms can change between versions; confirm the text published with the weights you download.

Capabilities

Input modalitiestext
Output modalitiestext

Cost at list price

InputNot published
OutputNot published
Cached inputNot published
Blended, 3:1Not available

The provider publishes no per-token price for this model. Any price you see elsewhere belongs to a third-party host, and running the weights yourself has hardware costs instead.

Estimate a workload across all models ↗

Sources

Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.

Other open-weight models from Chinese AI labs

See all 17 from Chinese AI labs ↗

Browse all open-weight models ↗