Upstage: Solar Mini 4

Text input Text output
Author's Description

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...

Key Specifications
Cost
$$
Context
524K
Parameters
35B (Rumoured)
Released
Sep 23, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Max Tokens Frequency Penalty Temperature Tool Choice Response Format Include Reasoning Tools Presence Penalty Structured Outputs Reasoning
Features

This model supports the following features:

Tools Response Format Structured Outputs Reasoning
Performance Summary

Upstage's Solar Mini 4, a compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window, demonstrates strong performance in several key areas. It consistently ranks among the fastest models, achieving the 96th percentile across eight benchmarks, and offers highly competitive pricing, placing in the 88th percentile. The model also exhibits exceptional reliability with a 99% success rate, indicating minimal technical failures. While excelling in speed, cost-efficiency, and reliability, Solar Mini 4 shows varied accuracy across benchmarks. It performs well in Ethics (99% accuracy, 57th percentile) and Email Classification (96% accuracy, 31st percentile). Its General Knowledge is also strong at 93% accuracy, though this places it in the 29th percentile. However, the model struggles with Hallucinations, achieving only 64% accuracy (13th percentile) by failing to consistently acknowledge uncertainty. Instruction Following (53% accuracy, 41st percentile), Coding (77% accuracy, 29th percentile), Reasoning (68% accuracy, 39th percentile), and Mathematics (79% accuracy, 28th percentile) also present areas for improvement. Its primary strength lies in its operational efficiency and cost-effectiveness, making it a compelling option for agentic use cases where these factors are critical, despite some accuracy limitations in complex cognitive tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.05
Completion $0.2
Input Cache Read $0.005

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Upstage
Upstage | upstage/solar-mini4-20260922 524K $0.05 / 1M tokens $0.2 / 1M tokens
Upstage
Upstage | upstage/solar-mini4-20260922 524K $0.05 / 1M tokens $0.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by upstage