upstage/solar-mini4

Model release OpenRouter 模型 Source language: Chinese

OpenRouter 于 2026-09-23 收录该模型(收录时间不等于模型正式发布日期);上下文:524,288 tokens;输入价:$0.0500/百万 tokens;输出价:$0.2000/百万 tokens;定位(来源描述):Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts…

Full text

Upstage: Solar Mini 4

upstage/solar-mini4

Compare

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 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.

Modalities

In / out price

50% off

$0.05 / $0.20per 1M

Context

524K

Released

Sep 23, 2026

Compare

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

50% off

$0.10$0.05$0.40$0.20$0.01$0.0050.52s64 tok/s

100.00%

50% off

$0.10$0.05$0.40$0.20$0.01$0.0050.56s94 tok/s

100.00%

Provider50% offInput / Output /M

Input $0.05 / Output $0.2050% off

64 tok/s100.00% uptime

Input $0.05 / Output $0.2050% off

94 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.03093/M tokens

Output

$0.3941/M tokens

Solar Mini 4 — Price history

Price history

No effective price data for this selection

$0.0244$0.33182.5%14.1%

$0.0320$0.39975.5%85.9%

ProviderInput / Output /M

Token share

Effective in $0.0244 / Effective out $0.331

Token share

14.1%

Effective in $0.0320 / Effective out $0.399

Token share

85.9%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

94tok/s

P50, best across providers

Latency

0.52s

P50, best provider

Reasoning effortLatency / throughput

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.84%

Availability over the last 3 days

Last 72 hours

Availability 99.84%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.91%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Upstage: Solar Mini 4 (Artificial Analysis and Design Arena)

SourceBenchmarkScore

Artificial AnalysisSolar Mini 4 HLE25.8%

Artificial AnalysisSolar Mini 4 AA-LCR83.3%

Artificial AnalysisSolar Mini 4 GDPval-AA29.6%

Artificial AnalysisSolar Mini 4 CritPt1.4%

Artificial AnalysisSolar Mini 4 SciCode47.6%

Artificial AnalysisSolar Mini 4 Terminal-Bench 4.01.0%

Artificial AnalysisSolar Mini 4 AA-Omniscience Accuracy18.2%

Artificial AnalysisSolar Mini 4 AA-Omniscience Non-Hallucination Rate63.5%

Design ArenaSolar Mini 4 Models Arena 3D Elo1083

Design ArenaSolar Mini 4 Models Arena Code Categories Elo1126

Design ArenaSolar Mini 4 Models Arena Data Visualization Elo1131

Design ArenaSolar Mini 4 Models Arena Game Development Elo1097

Design ArenaSolar Mini 4 Models Arena UI Component Elo1082

Design ArenaSolar Mini 4 Models Arena Website Elo1143

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

3.66Ttokens

2.

Cline

Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.

909Btokens

3.

Freebuff

Powerful coding models, funded by ads

880Btokens

4.

Nous Research API

Nous Research is an AI research team focused on advancing open-source AI.

116Btokens

5.

CodeGPT

new

9.03Btokens

Top 5 Apps

15.4B

Rest of OpenRouter

74.4M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

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 speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads.

Solar Mini 4 costs $0.05/M input tokens and $0.20/M output tokens, with separate rates for Cache Read at $0.005/M tokens.

Solar Mini 4 has a 524,288 token context window. It supports up to 131,072 completion tokens.

Yes. Solar Mini 4 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Solar Mini 4 is served by 1 provider on OpenRouter: Upstage.

Solar Decide Flash, Solar Decide, and Solar Pro 4 are other text models from Upstage.

Solar Mini 4 was released on September 23, 2026.

Sources

← Back to the daily brief