Glimpse is a multimodal visual reasoning model developed by Elorian. It is built to facilitate deep visual understanding and reasoning within the physical world.
The model functions as a chat interface that processes various input types. It is engineered to handle complex visual data through its specialized architecture.
The model accepts text, image, and video inputs to generate text outputs.
Glimpse is built for direct visual understanding and reasoning in the physical world.
The model supports a context window of 256K tokens.
Features include streaming, structured output, tools, and vision support.
Analyzing complex video content for visual insights.
Interpreting images to provide detailed text descriptions.
Performing visual reasoning tasks in physical world contexts.
Generating structured text output from multimodal inputs.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "elorian/glimpse", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "elorian/glimpse", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"elorian/glimpse","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Billed per token: $0.82524 / 1M input tokens, $0.082524 / 1M cached input tokens and $4.1262 / 1M output tokens. Reasoning tokens are billed as output.
Analyzing complex video content for visual insights.
Interpreting images to provide detailed text descriptions.
Performing visual reasoning tasks in physical world contexts.
Generating structured text output from multimodal inputs.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Glimpse This page | Complex visual reasoning and multimodal analysis. | |||
| Agentic frontend & coding workflows | ||||
| Multimodal + agents | ||||
| Long-horizon coding agents | ||||
| Reasoning + agents |
Glimpse costs $0.82524 / 1M tokens for input and $4.1262 / 1M tokens for output on AI/ML API. Cached input is billed at $0.082524 / 1M tokens.
Glimpse accepts text, image, and video inputs.
The model supports a context window of 256K tokens.
Glimpse was developed by Elorian.
The model returns text output based on the provided inputs.
