Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Solar Pro 3

Upstage· released 27 Jan 2026

upstage/solar-pro-3
Input / 1M tokens
$0.15
Output / 1M tokens
$0.6
Context window131K tokens

Longest answer: 118K tokens

reads texttool callingreasoning
See it on openrouter.ai

About

Solar Pro 3 is Upstage's mixture-of-experts language model, with 102B total parameters and 12B active parameters per forward pass. It accepts text and produces text. The listed context window is 131,072 tokens, and maximum output is 117,964 tokens. Solar Pro 3 supports reasoning and tools. It was released on 2026-01-27 and has model ID upstage/solar-pro-3. Input costs $0.15 per 1M tokens; output costs $0.6 per 1M tokens. The listed facts describe a text-only model, with no image, audio, or other input modalities specified. Its mixture-of-experts design and active-parameter figure provide details for teams assessing model architecture alongside the supported reasoning and tool capabilities.

Who it is for

Solar Pro 3 suits teams seeking a text-in, text-out language model with reasoning and tool support. Its parameter and token-window figures may help teams assess whether it fits their model requirements.

What is good

  • Supports reasoning and tools.
  • Context window is 131,072 tokens.
  • Maximum output is 117,964 tokens.
  • Input costs $0.15 per 1M tokens.

What to know first

  • Accepts text input only.
  • Outputs text only.
  • Context window is 131,072 tokens.

Verdict

Solar Pro 3 offers reasoning and tool support for text workflows, with explicit parameter and token limits. Its listed text-only input and output make modality fit straightforward to assess.

Details

Lab
Upstageopenrouter.ai · 3 Oct 2026
Context
131Kopenrouter.ai · 3 Oct 2026
Input price
$0.15 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.6 / 1Mopenrouter.ai · 3 Oct 2026
Max output
117,964 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources