Intelligence index
Outperforms 20% of compared models
Solar Pro 3
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.
- Input / output price
- $0.15/$0.6per 1M tokens
- Context
- 131K
- Released
- 2026-01-27
Pricing
Artificial Analysis
Explore rankingsCoding index
Outperforms 15% of compared models
Agentic index
Outperforms 23% of compared models
Related Models
Solar Pro 4
upstageSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding. When using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.
- Context
- 524K
- Max output
- 131.1K
- Released
- 2026-08-10
- Input
- $0.15/M
- Output
- $0.6/M
- Cache read
- $0.03/M
Solar Mini 4
upstageSolar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads. When using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.
- Context
- 524K
- Max output
- 131.1K
- Released
- 2026-09-23
- Input
- $0.05/M
- Output
- $0.2/M
- Cache read
- $0.005/M
Solar Decide Flash
upstageSolar Decide Flash is Upstage's low-latency structured decision model, a faster variant of Solar Decide built on Solar Mini 4 and served through the System One (/v1/systemone) API. Instead of generating text, it reads a state and answers typed questions, returning a choice, a score, or a yes/no answer, each with a probability taken directly from the model. Each decision is a single forward pass, and output tokens are free. It is tuned for consistently fast response times in routing, classification, and policy checks. It keeps the 512K context window, so a full document can serve as the state, and carries Solar Mini 4's Korean-language strength.
- Context
- 524K
- Max output
- 471.9K
- Released
- 2026-10-08
- Input
- $0.05/M
- Output
- $0/M
- Cache read
- $0.05/M