ERNIE 4.5 Turbo 32K
ERNIE 4.5 Turbo 32K is a Qianfan text-generation endpoint. It is a hosted service, separate from the downloadable ERNIE 4.5 checkpoints.
Architecture and access
The text generation interface uses conversation messages and can stream the response. The service’s endpoint identifier selects its context tier. The listed output ceiling and overall context limit are separate constraints; the entire conversation must fit the selected tier.Qianfan text generation guide
Practical use
Practical guidance. Keep prompts compact and leave room for the response. Summaries of prior turns can reduce context pressure, but check that they retain dates, names and constraints needed by the next task.Qianfan text generation guide
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | ernie-4.5-turbo-32k |
| Endpoint limits | 32K context; 27K maximum input; 12,288 maximum output tokensQianfan current model and endpoint list |
Related models
- ERNIE 4.5 Turbo 128K
Baidu · ERNIE 4.5 Turbo
Hosted ERNIE 4.5 Turbo text model with a 128K context for long documents.
Launch date not confirmedAPI