BLIP

Popular
Salesforce
Multimodal

Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.

Try BLIP now
Send a single prompt and stream a response inline. Hit Cmd+Enter to submit.
Sign in to try this model with €5 free credits.
Sign in
Press Cmd+Enter to send
Response appears here.
TL;DRΒ·Last updated June 24, 2026

BLIP is multimodal AI model from Salesforce, priced at €0.000 per 1M input tokens with a unknown context window.

About this model

BLIP (Bootstrapping Language-Image Pre-training) from Salesforce Research unifies captioning and VQA in one model. In caption mode it returns a concise description of the scene; in question-answering mode it answers a free-form question grounded in the image. It is one of the most-run captioning models on Replicate and a common building block for image search and accessibility alt-text.
Try BLIP

0.7

Sign in to generate β€” 50 free credits on sign-up

Pricing

Price per Generation
Per generation€1.00

API Integration

Use our OpenAI-compatible API to integrate BLIP into your application.

Install
npm install railwail
JavaScript / TypeScript
import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

// Simple β€” just pass a string
const reply = await rw.run("blip-captioning", "Hello! What can you do?");
console.log(reply);

// With message history
const reply2 = await rw.run("blip-captioning", [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);

// Full response with usage info
const res = await rw.chat("blip-captioning", [
  { role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);
Specifications
Price
€1.00
Developer
Salesforce
Category
Multimodal
Supported Formats
image
text
Tags
replicate
blip
captioning
vqa
salesforce
vision-understanding
image

Frequently asked questions

Start using BLIP today

Get started with free credits. No credit card required. Access BLIP and 100+ other models through a single API.