ERNIE 4.5 Turbo
- Family
- ERNIE 4.5
- Released
- 2025-04-24
- Context
- 128K
- Max output
- 12K
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Pretrained
Cheapest of 1 route · Baidu Qianfan
About
ERNIE 4.5 Turbo is Baidu's faster, more cost-efficient variant of ERNIE 4.5, launched April 24, 2025. It delivers ERNIE 4.5-level multimodal performance at 20% of the original cost ($0.12/1M input tokens vs $0.59). Strong at multimodal reasoning, with an average benchmark score of 77.68, surpassing GPT-4o (72.76). Text-only API variant; see ERNIE 4.5 Turbo VL for vision capabilities. API model IDs: ernie-4.5-turbo-128k (primary, 128K context); ernie-4.5-turbo-32k (32K context).
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Baidu Qianfan | $0.120 | $0.470 | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Cheapest of 1 route · Baidu Qianfan