RealRelay.ai
MiniMax

API-VLM

MiniMax's vision-language model that reads an image and returns a text answer, priced per call.

Starting at
Per call
$0.01/ call
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

minimax/API-vlm
Per call
$0.01/ call

Endpoints

POST/v1/chat/completionsChat Completions

Call it

Using minimax/API-vlm

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78response = client.chat.completions.create(9    model="minimax/API-vlm",10    messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9  model: "minimax/API-vlm",10  messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);
1curl https://www.realrelay.ai/v1/chat/completions \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "minimax/API-vlm",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

The capability is vision: API-VLM reads an image and responds in text. It does not generate images; it interprets them.

Because each call is billed at a flat rate, the cost of an image-understanding job is the number of calls multiplied by one price, with no token counting.

Vision
Input
Image
Output
Text

Overview

API-VLM is a vision-language model from MiniMax that takes an image as input and returns text. MiniMax lists it among its MCP services and prices it per request. It is built for image understanding, where the answer is a written description or reply rather than a generated picture.

It accepts image input and returns text. Billing is per call, not per token.

Pricing

API-VLM costs $0.01 per call. It is billed per call rather than per token.

API-VLM is available through RealRelay's OpenAI-compatible API.

Use cases

Use API-VLM to describe or interpret an image, such as reading a screenshot, summarising a chart, or explaining what a photo shows. The reply comes back as plain text.

It suits tools that attach an image to a request and need a text answer back, for example support workflows that read a customer's screenshot.

Frequently asked questions

What is API-VLM?
API-VLM is a vision-language model from MiniMax that takes an image as input and returns text. MiniMax lists it among its MCP services and prices it per request. It is built for image understanding, where the answer is a written description or reply rather than a generated picture.
How much does API-VLM cost?
API-VLM costs $0.01 per call.
What inputs and outputs does API-VLM support?
API-VLM accepts image input and returns text.
What is API-VLM used for?
Use API-VLM to describe or interpret an image, such as reading a screenshot, summarising a chart, or explaining what a photo shows. The reply comes back as plain text.
How do I call API-VLM through the API?
Call API-VLM through RealRelay's OpenAI-compatible API by setting the model field to minimax/API-vlm.

More from MiniMax

All 10 MiniMax models