ERNIE 5.0
- Family
- ERNIE 5
- Released
- 2026-01-22
- Context
- 128k
- Max output
- 65,536
- Parameters
- 2.4T
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Cheapest of 1 route · Baidu Qianfan
About
ERNIE 5.0 is Baidu's fifth-generation flagship foundation model, officially launched January 22, 2026 (preview at Baidu World November 13, 2025). It is a fully native multimodal model supporting text, image, audio, and video understanding and generation under a unified autoregressive framework, trained simultaneously across modalities from scratch. With 2.4 trillion total parameters and ultra-sparse MoE activation engaging <3% of parameters per inference, it delivers frontier performance at high efficiency. Available on Baidu AI Cloud's Qianfan MaaS platform. API model IDs: ernie-5.0; ernie-5.0-thinking-preview (thinking mode).
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Baidu Qianfan | $0.890 | $3.54 | Serverless |
Capabilities
Benchmark peer barsfor Classification
Benchmark scores(4)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| AIME 2025 | 87.0 | From official ERNIE 5 (accuracy%)Observed 2026-06-07 | — | Source |
| Google-Proof Q&A | 85.0 | GPQA Diamond (accuracy%)Observed 2026-06-07 | — | Source |
| Humanity's Last Exam | 39.0 | Humanity's Last Exam (accuracy%)Observed 2026-06-07 | — | Source |
| MMLU PRO | 87.0 | From official ERNIE 5 (accuracy%)Observed 2026-06-07 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Cheapest of 1 route · Baidu Qianfan