Felo API PlatformFelo API Platform
Back to models
Elorianmessages

Glimpse API

Elorian's first model, Glimpse, is a visual reasoning AI that re-examines images and videos during reasoning and answers in text.

Elorian: Glimpse is Elorian's first model, released on October 16, 2026 as a research preview with API access and a waitlist-only chat interface. It accepts text, image, and video input and produces text output, backed by a 262K-token context. Its defining trait is a visual scratch space: rather than relying on a single lossy first impression, it revisits the actual images and videos mid-reasoning, zooming into image corners to inspect details, slowing video to a higher frame rate for review, and tracking a specific object across multiple frames.

The model is built for visual workloads that demand close attention to detail. It suits synthetic data labeling and high-level planning in robotics, video review on construction and manufacturing sites, dense video captioning for media archives, accurate object counting on construction sites, timestamped video review, and comparing multiple images. It supports tool calling and structured outputs, and Elorian positions it for applications that perform frequent, large-volume visual analysis across both physical-world and media use cases. Elorian says it fills a gap where frontier general models are either insufficiently accurate or too expensive for visual workloads, and notes that Glimpse reports when it cannot identify an item.

Independent hands-on testing tempers the picture. Glimpse does not outperform GPT-6 Astra and Claude Opus 5.5 on every task; GPT-6 Astra remains stronger on fine visual puzzle tasks and dense video captioning, while Claude Opus 5.5 is slightly better at reading scientific charts. Glimpse can also contradict its own earlier statements within long multi-part answers, so it is not fully self-consistent. Elorian's own comparisons claim Glimpse surpasses GPT-6 Astra on scientific chart reasoning, open-vocabulary object counting, short video captioning, and manipulation event understanding, and matches it on embodied reasoning, though no scores are given.

Updated:

MODEL ID

glimpse
Context
262.144K
Max output
256K
Recommended API
messages
Input
text / image / video
Output
text

Highlights

  • Visual scratch space for re-examining inputs
  • Zooms into image corners for detail
  • Slows video to a higher frame rate
  • Tracks objects across frames
  • 262K-token context window
  • Tool calling and structured outputs

Providers

1 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details
$0.6$3$0.06

What $10 buys

Input
16.7M tokens
Output
3.3M tokens

Estimated from current input and output prices, before discounts.

Reasoning

Always enabled
No

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

1

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"
2

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

glimpse

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "glimpse",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

3

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "glimpse",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription
modelstringglimpsePublic model ID to call.
max_tokensinteger—Maximum generated tokens.
messagesarray—Conversation messages for Chat Completions.
stop———
min_p———
toolsarray—Tool calling definitions following compatible schema.
top_k———
top_p———
logprobs———
reasoning———
logit_bias———
temperaturenumber—Controls response variety when supported.
tool_choicestring or object—Controls whether a tool should be called.
top_logprobs———
response_formatobject—Request structured output when supported.
presence_penalty———
frequency_penalty———
include_reasoning———
repetition_penalty———
structured_outputs———

Frequently asked questions

What is Glimpse?

Elorian: Glimpse is Elorian's first model, released on October 16, 2026 as a research preview with API access and a waitlist-only chat interface. It accepts text, image, and video input and produces text output, backed by a 262K-token context. Its defining trait is a visual scratch space: rather than relying on a single lossy first impression, it revisits the actual images and videos mid-reasoning, zooming into image corners to inspect details, slowing video to a higher frame rate for review, and tracking a specific object across multiple frames. The model is built for visual workloads that demand close attention to detail. It suits synthetic data labeling and high-level planning in robotics, video review on construction and manufacturing sites, dense video captioning for media archives, accurate object counting on construction sites, timestamped video review, and comparing multiple images. It supports tool calling and structured outputs, and Elorian positions it for applications that perform frequent, large-volume visual analysis across both physical-world and media use cases. Elorian says it fills a gap where frontier general models are either insufficiently accurate or too expensive for visual workloads, and notes that Glimpse reports when it cannot identify an item. Independent hands-on testing tempers the picture. Glimpse does not outperform GPT-6 Astra and Claude Opus 5.5 on every task; GPT-6 Astra remains stronger on fine visual puzzle tasks and dense video captioning, while Claude Opus 5.5 is slightly better at reading scientific charts. Glimpse can also contradict its own earlier statements within long multi-part answers, so it is not fully self-consistent. Elorian's own comparisons claim Glimpse surpasses GPT-6 Astra on scientific chart reasoning, open-vocabulary object counting, short video captioning, and manipulation event understanding, and matches it on embodied reasoning, though no scores are given.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

What input modalities does Glimpse support?

Glimpse accepts text, image, and video input. It processes images and videos directly and answers in text.

How large is its context window?

Glimpse supports a 262K-token context.

What visual reasoning abilities does it have?

It uses a visual scratch space to revisit actual images and videos during reasoning. It can zoom into image corners, slow down video to a higher frame rate, and track a specific object across multiple frames.

What tasks is it best suited for?

It targets synthetic data labeling and high-level planning in robotics, video review on construction and manufacturing sites, dense video captioning for media archives, accurate object counting, timestamped video review, and comparing multiple images.

Does it support tool calling and structured outputs?

Yes, Glimpse supports both tool calling and structured outputs.

How does it compare with GPT-6 Astra and Claude Opus 5.5?

Elorian reports that Glimpse surpasses GPT-6 Astra on scientific chart reasoning, open-vocabulary object counting, short video captioning, and manipulation event understanding, and matches it on embodied reasoning. In independent hands-on testing, however, GPT-6 Astra remains stronger on fine visual puzzles and dense video captioning, and Claude Opus 5.5 is slightly better at reading scientific charts.