Upstage's compact, cost-efficient model for agentic useSolar Mini 4 by upstage is offered by 6 providers on this page. Public prices are shown for 5 of them. Its official list price is $0.10 per 1M input tokens and $0.40 per 1M output tokens. The lowest paid channel is OpenRouter at $0.05 / $0.20 per 1M, about 2.0× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 159 tokens per second, with 1.8s to the first token.
The context window is 524,288 tokens, with an output limit of 131,072 tokens. It supports reasoning, tool use, and structured output. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2026-02.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari solar-mini4:free | Gateway | Free | — | — | 524,288 | 131,072 | ||
| OpenRouter | Gateway | $0.05 | $0.20 | $0.005 | — | 524,288 | 131,072 | |
| NanoGPT | Gateway | $0.05 | $0.20 | $0.005 | — | 524,288 | 131,072 | |
| NanoGPT upstage/solar-mini4:thinking | Gateway | $0.05 | $0.20 | $0.005 | — | 524,288 | 131,072 | |
| UpstageOfficial | First-party | $0.10 | $0.40 | $0.01 | — | 524,288 | 131,072 | |
| Kilo Gateway | Gateway | $0.10 | $0.40 | $0.01 | — | 524,288 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.