ERNIE 4.5 VL 424B A47B API: toman pricing and code
baidu/ernie-4.5-vl-424b-a47b
visionreasoningYou are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups
ERNIE 4.5 VL 424B A47B example: reading an image into JSON
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "baidu/ernie-4.5-vl-424b-a47b",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "Return only the invoice number and the total, as JSON."},
{"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
]
}]
}'import base64, json
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
img = base64.b64encode(open("factor.jpg", "rb").read()).decode()
resp = client.chat.completions.create(
model="baidu/ernie-4.5-vl-424b-a47b",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
],
}],
response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))import OpenAI from "openai";
import { readFileSync } from "node:fs";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");
const resp = await client.chat.completions.create({
model: "baidu/ernie-4.5-vl-424b-a47b",
messages: [{
role: "user",
content: [
{ type: "text", text: "Return the invoice number, the date and the total as JSON." },
{ type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
],
}],
response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));What is ERNIE 4.5 VL 424B A47B good for?
ERNIE 4.5 VL 424B A47B is one of Baidu's models. Put "baidu/ernie-4.5-vl-424b-a47b" in the model field and the rest of your code stays as it is. ERNIE 4.5 VL 424B A47B keeps 123,000 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 16,000 tokens. On price it sits in the "cheap" band — cheaper than 164 and dearer than 242 of the other paid models in the catalogue.
Capabilities available on this id: it reads images directly, which makes it a real option for invoices, forms and screenshots; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.
For a back-of-envelope figure: about 630 toman per 1,000-word exchange (121,853 in, 362,656 out, per 1M tokens). You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is MiniMax-01: ERNIE 4.5 VL 424B A47B works out roughly 1.3× more expensive, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 159 thousand-word requests on ERNIE 4.5 VL 424B A47B , and every 1,000 toman is about 1,587 words of round trip. A job with one million input tokens and one million output tokens comes to 484,509 toman in total. Filling this model's 123,000-token window costs 14,988 toman on the input side alone, which is the real reason to keep conversation history short.
Among the less common parameters it accepts repetition_penalty, top_k — all through the standard request body. It does not support response_format, tool_choice, tools, structured_outputs, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Sonar at 127,072 tokens.
What to use it for: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, pulling text and fields out of images.
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...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 328 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 705 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 21,875 toman |
Frequently asked
- How do I call ERNIE 4.5 VL 424B A47B from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "baidu/ernie-4.5-vl-424b-a47b". Nothing else in your code changes.
- What does ERNIE 4.5 VL 424B A47B cost in toman?
- 121,853 toman per 1M input tokens and 362,656 toman per 1M output tokens; a 1,000-word request is around 630 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does ERNIE 4.5 VL 424B A47B take?
- Up to 123,000 tokens per request, roughly 92k words. A single answer can reach 16,000 tokens.
- Does ERNIE 4.5 VL 424B A47B support streaming and image input?
- Streaming (stream=true) works on every model here. Image input is accepted through image_url, as a data URI or a public URL.