Baidu
Ernie 5.0 Thinking Preview
Compact GPT model for low-latency assistance and high-volume workloads
Model facts
- Context window
- 128K tokens
- Maximum output
- 16K tokens
- Cheapest paid input
- $1 per 1M tokens
- Cheapest paid output
- $3.5 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, attachments, text, image.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 22.3 | not measured | 85.0 | not measured |
Observed price history
- 2026-08-24: $1 input / $3.5 output per 1M tokens
API providers
- NanoGPT — model id ernie-5.0-thinking-preview; $1 input / $3.5 output per 1M tokens; provider documentation