New serverless model elorian-labs/glimpse-1.0 on Together AI
Together AI added the serverless model elorian-labs/glimpse-1.0, with a 262,144 context length and listed input, output and cached input prices.
Models:elorian-labs/glimpse-1.0
What changed
Together AI added the serverless model elorian-labs/glimpse-1.0. It supports a 262,144 context length, FP8 quantization, function calling, and structured outputs. Pricing is $0.60 input, $3.00 output and $0.06 cached input per 1M tokens.
Source
elorian-labs/glimpse-1.0: 262,144 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.60 input / $3.00 output / $0.06 cached input (per 1M tokens).
Original announcement: Together AI changelog
Source: Together AI changelog (2026-11-10)