prices synced 2026-07-28
U

Solar Pro 3

Upstage · Released Jan 2026

Compare

A Mixture-of-Experts language model from Upstage with 102B parameters total and 12B active per forward pass, operating on a 128K token context window.

Strengths
MoE architecture allows it to process requests with lower compute requirements than comparably-sized dense models while maintaining performance across diverse tasks.
Best for
Tasks requiring broad capability and efficiency trade-offs, or applications where reduced latency and throughput per request matters.
Limitations
Mixture-of-Experts models can exhibit uneven performance across specialized domains and may require careful prompt engineering to fully activate relevant expert pathways.

Input / 1M

$0.15

Output / 1M

$0.6

Cached input / 1M

$0.015

Context window

128K

Price history

Price per 1M tokens over timeOutput $0.6; Input $0.15 as of Jun 2026.$0$0.2$0.4$0.6Output on 11 Jun 2026: $0.6Out $0.6Input on 11 Jun 2026: $0.15In $0.15Jun 2026

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.15 $0.6 $0.015 Imported from OpenRouter openrouter.ai
Report a problem