Solar Mini 4 (Reasoning)
by Upstage
Solar Mini 4 (Reasoning) is a reasoning model from Upstage, released on September 22, 2026. It has a 524K-token context window and can generate up to 131K output tokens. API pricing is $0.1 per 1M input tokens and $0.4 per 1M output tokens. It ranks #74 of 220 models by Intelligence Score with a score of 31.9.
Solar Mini 4 is Upstage's cost-efficient proprietary MoE language model (35B total / 3B active) for agentic use where speed and cost matter. API id solar-mini4 (version solar-mini4-260922). Text→text with English, Korean, and Japanese; reasoning mode, tool calling, and structured outputs. Upstage Console docs: 512K context, up to 128K max output, February 2026 training cutoff. List pricing $0.10 input / $0.40 output / $0.01 cached per 1M tokens. Independent Artificial Analysis benches (not vendor self-report): AA-LCR 83.3, SciCode 47.6, HLE text-only 25.8, Terminal-Bench 4.0 1.0, GDPval-AA v2.1 1072 Elo, AA-Briefcase v1.1 872 Elo. No separate Upstage-published bench table found beyond console/product claims; AA rows stored as third-party.
Key specs
| Provider | Upstage |
|---|---|
| Release date | 2026-09-22 |
| License | proprietary |
| Context window | 524K tokens |
| Max output | 131K tokens |
| Input price | $0.1 / 1M tokens |
| Output price | $0.4 / 1M tokens |
| Intelligence Score | 31.9 |
| Coding index | 17.1 |
Quick answers
What is the context window of Solar Mini 4 (Reasoning)?
Solar Mini 4 (Reasoning) has a context window of 524K tokens, with a maximum output of 131K tokens per response.
How much does Solar Mini 4 (Reasoning) cost?
Solar Mini 4 (Reasoning) costs $0.1 per 1M input tokens and $0.4 per 1M output tokens through the API.
Is Solar Mini 4 (Reasoning) open source?
No. Solar Mini 4 (Reasoning) is a proprietary model from Upstage (proprietary license).
When was Solar Mini 4 (Reasoning) released?
Upstage released Solar Mini 4 (Reasoning) on September 22, 2026.
How does Solar Mini 4 (Reasoning) compare to Claude Opus 5.5 (Reasoning)?
Solar Mini 4 (Reasoning) scores 31.9 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.1 vs $4 per 1M tokens.
Compare on the AI leaderboard · All AI models
More models from Upstage
- Solar Pro 4 (Reasoning) — Upstage