Atlas / Models / Baidu / Baidu: ERNIE 4.5 VL 424B A47B

Baidu: ERNIE 4.5 VL 424B A47B✓ Catalog verified

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

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.

Input price
$0.42 /1M
Output price
$1.25 /1M
Context
123K
Modalities
imagetext
Released
Jun 30, 2025
Tool calling
Atlas signal
80/100
01

Overview

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.

Access: available through the official Baidu API. Context window: 123K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifierbaidu/ernie-4.5-vl-424b-a47b
ProviderBaidu
Model typeMultimodal LLM
Context window123K catalog
Input modalitiesimage · text
Output modalitiestext
ReleasedJun 30, 2025
ModeratedNo
Architecture modalitytext+image->text
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetop_ktop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for baidu/ernie-4.5-vl-424b-a47b as published in the catalog.

$0.42
Input /1M
$1.25
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$4.2e-7$0.42 / 1MPer input token
Completion tokens$0.00000125$1.25 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.46Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Baidu: ERNIE 4.5 VL 424B A47B
MMLU Signal (Reasoning)
92signal
Coding Signal (HumanEval proxy)
74signal
Math Signal (GSM8K proxy)
78signal
Science Signal (GPQA proxy)
74signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Baidu: ERNIE 4.5 VL 424B A47B through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="baidu/ernie-4.5-vl-424b-a47b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Baidu: ERNIE 4.5 VL 424B A47B cost?

$0.42 per 1M input tokens and $1.25 per 1M output tokens on the official Baidu API.

What is the context window of Baidu: ERNIE 4.5 VL 424B A47B?

Baidu: ERNIE 4.5 VL 424B A47B supports up to 123K tokens of context.

Does Baidu: ERNIE 4.5 VL 424B A47B support tool / function calling?

Baidu: ERNIE 4.5 VL 424B A47B does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Baidu: ERNIE 4.5 VL 424B A47B?

Use the official Baidu API with the model id `baidu/ernie-4.5-vl-424b-a47b`. See the Quick start section above for code examples.