Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for baidu

Baidu: ERNIE 4.5 VL 424B A47B

baidu/ernie-4.5-vl-424b-a47b

Model weights
Compare

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.

Modalities

In / Out Price

$0.42 / $1.25per 1M

Context

123K

Released

Jun 30, 2025

Knowledge Cutoff

Mar 2025

Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQ

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

About Baidu: ERNIE 4.5 VL 424B A47B

OpenRouter makes Baidu: ERNIE 4.5 VL 424B A47B available through a unified, OpenAI-compatible API using the model ID baidu/ernie-4.5-vl-424b-a47b. It is served by NovitaAI.

Baidu: ERNIE 4.5 VL 424B A47B accepts images and text and returns text. It has a 123,000-token context window and a maximum output of 16,000 tokens.

On OpenRouter, Baidu: ERNIE 4.5 VL 424B A47B costs $0.42/M input tokens and $1.25/M output tokens. It was released on June 30, 2025; its knowledge cutoff is March 31, 2025.

Frequently asked questions

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens).

ERNIE 4.5 VL 424B A47B costs $0.42/M input tokens and $1.25/M output tokens.

ERNIE 4.5 VL 424B A47B has a 123,000 token context window. It supports up to 16,000 completion tokens.

The ERNIE 4.5 VL 424B A47B endpoint shown on this page does not accept tools, so function calling is unavailable there. It does not support response_format, so JSON output is not enforced.

ERNIE 4.5 VL 424B A47B accepts images and text as input and returns text.

ERNIE 4.5 VL 424B A47B was released on June 30, 2025. Its knowledge cutoff is March 31, 2025.

$0.42$1.251.62s18 tps
100.00%

Throughput

18tok/s

P50, best across providers

Latency

1.62s

P50, best provider

Uptime (3d)

100.00%

Availability (3d)

99.99%

Availability over the last 3 days

Last 72 hours
Availability 99.99%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
100.00%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://outcited.ai/
CategoryRank
new
20.4Mtokens
2.
Favicon for http://neelnanda.io/
self-preference-pilot
new
10.3Mtokens
3.
Favicon for https://local.brainhub.invalid/
BrainHub blind regional readers
new
8.28Mtokens
4.
Favicon for https://mia-geo.ambr.io/
MIA GEO
new
7.32Mtokens
5.
Favicon for https://sillytavern.app/
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
5.58Mtokens