# Glimpse (slim)

> Glimpse is Elorian's visual reasoning model, released as a research preview on 16 October 2026. It takes text, images and video and returns text, through Elorian's own API and chat app and through OpenRouter.

- Full: https://www.anchorterminal.com/tools/elorian-glimpse.md (~10,200 tokens) · this version ~2,230 tokens · JSON https://www.anchorterminal.com/tools/elorian-glimpse.json · canonical https://www.anchorterminal.com/tools/elorian-glimpse
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-18 · pricing https://www.anchorterminal.com/tools/elorian-glimpse#pricing · reviews https://www.anchorterminal.com/tools/elorian-glimpse#reviews
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**D · 48.6/100 · rank #915 of 1133 · #23 in Model APIs & inference · not agent-ready · confidence medium**


Assessment: Glimpse reads images and video at $0.60 input and $3.00 output per million tokens, and OpenRouter serves it with tools, structured output and a 262,144-token context. It is a research preview with no public Elorian docs, model card or status page, and Elorian's terms allow training on submitted content unless a paid user opts out.

## Facts

- Kind: Model API · vendor: Elorian · category: Model APIs & inference · legal entity: Elorian AI, Inc. · provenance 40/100
- Endpoint: `https://openrouter.ai/api/v1` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed model and service under the Elorian AI, Inc. terms of service (California law). Weights not released.
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: OpenRouter's endpoint for `elorian/glimpse`, served by Together, read from OpenRouter's model API, model page and docs on 17 October 2026, because Elorian's own API documentation sits inside its signed-in console at platform.elorian.ai and is not public. No key was created and no request was sent to either API. Elorian's own API at api.elorian.ai is described below and not graded
- Model: Visual reasoning model, text, image and video in, text out. Post-trained on an unnamed open-weight base model. The launch post says it is trained to use tools that write code, transform images and watch videos, and to spawn subagents. Labelled a research preview
- OpenRouter endpoint: Model `elorian/glimpse`, provider Together (`elorian/glimpse-20261016`), context 262,144 tokens, up to 256,000 output tokens, quantisation not stated. Parameters include tools, tool_choice (none, auto or required, not a named function), response_format, structured_outputs, reasoning, include_reasoning, logprobs and the usual sampling controls. Implicit prompt caching. Reported uptime 98.7 per cent over the last day on 17 October 2026
- Elorian API: api.elorian.ai/v1, OpenAI-style, with keys beginning `elor_sk_` created in the console. Its unauthenticated 404 names chat completions, models, limits, usage, files and conversations, and says embeddings, audio, image generation and the Responses API are not offered. Sign-in at platform.elorian.ai uses Google or email with a Cloudflare Turnstile check
- Price: $0.60 per million input tokens, $0.06 per million cached input tokens and $3.00 per million output tokens on OpenRouter, the same input and output rates Elorian publishes. Elorian's post says Glimpse can be tried free on its platform. Volume access, custom evaluation and procurement review through sales@elorian.ai
- Data handling: OpenRouter shows Together's policy for this endpoint as no training and no prompt retention. Elorian's privacy policy (12 October 2026) trains on Inputs and Outputs from free access by default, says different terms may apply to paid, API and enterprise offerings, and takes opt-outs at privacy@elorian.ai. Services hosted in the United States
- Terms: Elorian AI, Inc. terms of service, last updated 12 October 2026. California law, binding individual arbitration with a 30-day opt-out, liability capped at the greater of 12 months' fees and $100 ($100 for preview offerings). Elorian may modify or discontinue the Service without notice and has no obligation to provide support
- Elorian's figures: Vendor-reported at maximum thinking effort. WGO Bench 42.70, ERQA 83.75, BabyVision 95.36, HSS 46.36, CharXiv-R 92.90, UGC-VideoCap 82.66, DREAM-1K 76.04, TOMATO 93.60, Video-MME v2 with subtitles 56.68, E.T. Bench 63.55, FSC-147 83.36, CountQA 82.66
- Age: Announced on 16 October 2026 and listed on OpenRouter on 17 October 2026, the day of this check. Elorian's blog has one earlier post, the HSS benchmark of 8 October 2026
- Support: contact@elorian.ai, support@elorian.ai and a Discord server. Elorian's support page says it has no support queue or ticket system
- Prices: Glimpse input on OpenRouter $0.60 per 1M tokens; Glimpse cached input on OpenRouter $0.06 per 1M tokens; Glimpse output on OpenRouter $3 per 1M tokens

- Scores: Reliability 38, Performance pending, Schema & documentation 60, Agent ergonomics 66, Security & auth 56, Payments & pricing 25, Task success pending, Maintenance & community 51, Transparency & trust 36 · total over the 7 assessed categories
- Why: Reliability, Hosted lines, read on the OpenRouter route. · Schema & documentation, Model reading. · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). · Security & auth, Model reading. · Payments & pricing, No machine payment protocol on OpenRouter or from Elorian (0). · Maintenance & community, Model reading. · Transparency & trust, Closed model under clear terms (California law, arbitration with an opt-out, liability caps), with weights not released and the open-weight…
- Sources: 17, open questions: 8, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/elorian-glimpse.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/elorian-glimpse.svg` or a link to https://www.anchorterminal.com/tools/elorian-glimpse from a page on elorian.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Call it through OpenRouter as `elorian/glimpse` at https://openrouter.ai/api/v1/chat/completions. Elorian's own API docs sit behind a console sign-in
2. Send video as a `video_url` content part, as a public URL or a base64 data URL. Batch requests are not available for this model
3. Set `max_tokens` yourself. The endpoint allows up to 256,000 output tokens, and visual reasoning spends many of them
4. Honour Retry-After on 429 and 503. With a single provider, a 503 means the Together deployment is unavailable, not that another host can take over
5. Treat counts and timestamps as unverified. Elorian's terms say outputs need independent human review before anyone relies on them

## Connect

```bash
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"elorian/glimpse","messages":[{"role":"user","content":[{"type":"text","text":"How many open pliers are in this photo?"},{"type":"image_url","image_url":{"url":"https://example.com/photo.jpg"}}]}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI API | A | 82.9 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| Claude API | BB | 77.3 | inference.llm | https://www.anchorterminal.com/tools/anthropic-api.min.md |
| GroqCloud | BB | 74.5 | inference.llm | https://www.anchorterminal.com/tools/groq.min.md |
| BlockRun.AI | BB | 72.4 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |
| Mistral AI API | BB | 71.2 | inference.llm | https://www.anchorterminal.com/tools/mistral-api.min.md |


## Panel reviews (4, average 2.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ About $6.00 per 1,000 image calls, if reasoning stays short (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ A generic OpenRouter contract with no model-specific reference (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ One provider, no model limit, a day of uptime data (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Unscoped keys and terms that train on content (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-17; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with ratings of 3, 3, 2 and 2. They credit a low per-token price with a cached rate a tenth of input and OpenRouter's documented video input and Retry-After, and mark down the lack of Elorian-specific docs, limits and status page, terms that licence content for training, and a single provider with a day of uptime data. Read it as a research preview graded on OpenRouter's route, where the contract and the failure handling are OpenRouter's and Elorian's own terms remain unsettled for API traffic.