Together AI serves Elorian Labs Glimpse 1.0 at $0.60 input and $3.00 output per million tokens (November 10, 2026)
Together AI added elorian-labs/glimpse-1.0 on serverless: 262,144 context, function calling, $0.60 in and $3.00 out per 1M tokens.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Together AI API keyTOGETHER_API_KEYGet key
Select Create key on your project's API keys page. The key is shown only once.
What changed
On November 10, 2026, Together AI added elorian-labs/glimpse-1.0 to its serverless models. The changelog lists:
- Context length: 262,144 tokens
- Quantization: FP8
- Function calling: supported
- Structured outputs: supported
- Price per 1M tokens: $0.60 input, $3.00 output, $0.06 cached input
The serverless models page lists Glimpse 1.0 from Elorian Labs in the chat models table with the same model ID, context length and prices.
What to do
Nothing changes for existing integrations. To try the model, set model to elorian-labs/glimpse-1.0 in a request you already send to Together. You need a Together API key in TOGETHER_API_KEY.
The model ID is written in lowercase, so copy it exactly.
On the bill, input costs $0.60 and output $3.00 per 1M tokens. Cached input is billed at $0.06 per 1M tokens, a tenth of the normal input price.
Function calling and structured outputs are both marked as supported, so an integration that uses tools or a JSON schema can switch the model ID without removing those parts. Keep prompts under the 262,144-token context length.
Not confirmed
The changelog entry does not mention image input for this model. The entries for Inkling 2 Small and Kimi K3.1 Pro do say "text and image input", so treat Glimpse 1.0 as text-only on Together until the docs say otherwise. On November 13 the model was on the docs models page, but we did not find it on the together.ai pricing page. The changelog does not say whether the model works through the Messages API and Responses API, and gives no rate limits.
