by Baidu

Baidu: ERNIE 4.5 300B A47B .

text open weights datacenter 300B params 131K ctx
Cheapest input
$0.28/M
on OpenRouter
Cheapest output
$1.1/M
on OpenRouter
Fastest
16 tok/s
on OpenRouter
Smallest GPU
1× AMD MI300

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in...

Smallest GPU to run it See all quantisations →

1× AMD MI300.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.28 $1.1 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 16.3 1756 ms 8729 ms
FAQ

Frequently asked.

How do I run Baidu: ERNIE 4.5 300B A47B ?
Baidu: ERNIE 4.5 300B A47B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Baidu: ERNIE 4.5 300B A47B ?
Baidu: ERNIE 4.5 300B A47B is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Baidu: ERNIE 4.5 300B A47B ?
API pricing starts at $0.28/M input tokens and $1.1/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Baidu: ERNIE 4.5 300B A47B open-source or proprietary?
Baidu: ERNIE 4.5 300B A47B is open-weight under the license. You can download and self-host it.