Elorian Glimpse
by NanoGPT · listed Oct 2026RTV
Glimpse is Elorian's visual reasoning model for understanding images and video and answering in text. It can analyze charts, count objects, follow events over time, and reason about spatial relationships and physical cause and effect. It supports tool calling and structured output across a shared 262,144-token context window, with up to 256,000 output tokens within the remaining context.
Current rates USD per 1M tokens
Input$0.63
Output$3.15
Cache read$0.063
Cache write—
Against the market
On the record
- Model id
elorian/glimpse- Context window
- 262K tokens
- Max output
- 256K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-10-17
- Last updated
- 2026-10-17
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Vercel AI Gateway$0.60 in · $3.00 out
- Kilo Gateway$0.60 in · $3.00 out
- OpenRouter$0.60 in · $3.00 out