BaiduErnie 4.5 Vl 424B A47b
Not yet ranked: too few independent results so far. Released 30 Jun 2025.
- Blended price
- $0.628/M
- $0.420 in · $1.25 out
- Output speed
- 16 tok/s
- First answer
- 1.79 s
- Context
- 123k
No independent quality benchmark results yet — only pricing and metadata.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| NovitaAI | 16 tok/s | 1.79 s | $0.420 | $1.25 | 123k | fp16 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0005 | – | 20.5 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0058 | – | 39.3 s |
| Code edit | 6,000 / 1,500 | $0.0044 | – | 1.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.030 | – | 4.2 min |
| Structured extraction | 2,000 / 200 | $0.0011 | – | 14.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.