upstage
Upstage: Solar Mini 4
upstage/solar-mini4
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter lists upstage/solar-mini4 as an Upstage text-to-text language model positioned as compact and cost-efficient. The catalog describes a 35B-parameter mixture-of-experts design with 3B active parameters and a 524,288-token context window, though this is a source-reported description rather than independently verified performance. It exposes optional reasoning controls plus tool-calling and structured-output parameters. Design Arena measurements cover several design and coding categories, but the pack includes no independent model card, so suitability should be validated on target workloads.[1]
Strengths
- The OpenRouter catalog reports a compact, cost-efficient positioning and a 35B-parameter MoE design that activates 3B parameters.[1]
- Its listed 524,288-token context window is suited, in principle, to long prompts, extended conversations or large documents.[1]
- Request controls include tools, parallel tool calls, tool choice, structured outputs and optional reasoning effort.[1]
Limitations
- Only OpenRouter evidence was supplied, and the catalog description is truncated; no independent model card was available, so positioning claims remain unverified.[1]
- Measured evidence is limited to Design Arena category entries, while Artificial Analysis data is null; results may not transfer to other workloads without validation.[1]
- The catalog lists only text input and output and omits knowledge cutoff, license, hardware and safety details; those omissions are unknowns, not demonstrated absences.[1]
Where to use it
- Candidate for agentic text workflows that need long context, tool calling, structured output and configurable reasoning, pending task-level tests.[1]
- Potential fit for cost-conscious assistants, summarization and document question answering over long inputs, if its claimed efficiency is confirmed.[1]
- Worth prototyping for data-visualization, website, UI-component or game-development assistants because Design Arena measured those categories; use results only as screening evidence.[1]
Sources
- [1] OpenRouter catalog · Upstage: Solar Mini 4Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Solar 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...
Specifications
- Model ID
- upstage/solar-mini4
- Canonical ID
- upstage/solar-mini4-20260922
- Creator
- upstage
- Added to OpenRouter
- 23.09.2026
- Context length
- 524,288
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.050 / out $0.200
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default medium · efforts: max, xhigh, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default medium · efforts: max, xhigh, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · 3dwin rate 24.9% · rank 95 | 1,091Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 30.1% · rank 101 | 1,127Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 37.1% · rank 73 | 1,167Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 28% · rank 97 | 1,098Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 27.3% · rank 102 | 1,093Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 32% · rank 98 | 1,141Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Upstage | 524,288 | $0.050 | $0.200 | — | — | 100% |
| Upstage | 524,288 | $0.050 | $0.200 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.