Can I run Solar Pro 3 locally?

Upstage | 131,072 token context | $0.15/M input, $0.60/M output. Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.

Guides for this model

Open weights vs open source vs API-only: what you are actually allowed to do

How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Solar Pro 3 is Upstage's Mixture-of-Experts model with 102B total parameters but only 12B active per forward pass, keeping inference costs well below what the parameter count implies. It is built first for Korean, with English and Japanese also supported. If Korean-language quality is a priority and you are working via API, it is worth a close look.

Known for

MoE architecture: 102B total parameters, 12B active per forward pass
Strong Korean-language optimization, with English and Japanese support
131K token context window for longer documents
Competitive API pricing at $0.15/M input and $0.60/M output

Watch out for

Closed weights only — no local deployment option.
Optimized for Korean first; English and Japanese users may find better-tuned alternatives at similar prices.
No model card details published, so fine-tuning, safety and licence specifics are unclear.

Best for

Prompts to try

Korean document summary

아래 계약서 조항을 읽고, 핵심 의무 사항과 위험 요소를 불릿 포인트 5개로 요약해 주세요. 법률 전문가가 아닌 일반인도 이해할 수 있는 언어로 작성해 주세요. [계약서 텍스트를 여기에 붙여넣으세요]

Cross-language reasoning task

A company's Korean annual report states revenue grew 23% year-on-year, but operating profit fell 8%. List the three most likely explanations for this divergence, then suggest two financial metrics an analyst should check next to confirm which explanation is correct.

Long document extraction

I'm pasting a lengthy policy document below. Extract every deadline, every named responsible party, and every financial figure mentioned. Present the results as a structured table with columns: Item, Value, Context. Do not summarise — list every instance you find.

Compare with

Solar Mini 4
API-only model
524,288 token context · $0.05/M input, $0.20/M output
Nemotron 3 Ultra
Open-weights model
262,144 token context · $0.60/M input, $2.40/M output
Nemotron 3.5 Lightning
Open-weights model
262,144 token context · $0.07/M input, $0.20/M output
Qwen3.5-9B
Open-weights model
262,144 token context · $0.10/M input, $0.15/M output

More text models from upstage

Questions people ask

Can I run Solar Pro 3 locally?: No. Upstage has not released open weights for Solar Pro 3, so it is API access only.
What does Solar Pro 3 cost and how long is its context?: Pricing is $0.15 per million input tokens and $0.60 per million output tokens, with a 131,072-token context window.
Which languages does Solar Pro 3 actually support?: It is optimized for Korean, with English and Japanese also supported — Korean is the primary focus of Upstage's tuning work.

Captain's verdict
A sensible pick if Korean-language quality is non-negotiable and you want MoE efficiency without paying frontier-model prices.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Solar Pro 3 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm upstage reasoning multilingual chat long context

Browse by Model Family