Together AI exposes Elorian Glimpse through model ID elorian/glimpse-20261016. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Together AI SDK or REST API to call
elorian/glimpse-20261016— see the documentation for request format.
Code Examples
pip install togetherTOGETHER_API_KEYelorian/glimpse-20261016Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
from together import Together
client = Together() # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
model="elorian/glimpse-20261016",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Capabilities
About Elorian Glimpse
Glimpse is Elorian's first visual thinking model for reasoning over images and video in the physical world. It tracks objects through motion and viewpoint changes, interprets spatial relationships, and predicts physical consequences, and it can use multimodal tools (code, image transforms, video) and subagents. Available via the Elorian API and chat UI. First-party list price is $0.60 per 1M input tokens and $3.00 per 1M output tokens (cache read $0.06 per 1M on gateways that expose it). Released 2026-10-16.