NOUMENOpen app
NOUMEN

upstage · Efficient

Solar Mini 4

Added Sep 23, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Upstage's compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window. Built for fast, cost-efficient agentic tasks, with strong Korean and English support.

  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.20
Cache read
$0.005

Reference prices as published by the model provider. API example

Specifications

Context window
524.3K
Max output
131.1K
Average output (7 days)
561 tokens
Longer than 53% of 468 models

Side by side

Solar Mini 4 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Solar Mini 4upstageThis modelGPT 5.1 Codex MaxOpenAIRemove
ProviderupstageOpenAI
Discovery tierEfficientFrontier
AddedSep 23, 2026Dec 4, 2025
Limits
Context window524.29KBest400K
Max output131.07KBest128K
Average output561 tokens—
Pricing, USD per 1M tokens
Input$0.05Best$2.50
Output$0.20Best$20.00
Cache read$0.005Best$0.25
Performance
Throughput90.6 tok/s—
Time to first token2.2 s—
Request success (24h)89.1%—
Benchmark indexes
Intelligence Index24.1Best23.7
Math Index—95.7
Capabilities
ReasoningNoYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
PDF inputNoYes
Reasoning effort—none, minimal, low, medium, high, xhigh

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Solar Mini 4
  • GPT 5.1 Codex Max

Intelligence Index

  • Solar Mini 424.1
  • GPT 5.1 Codex Max23.7

Solar Mini 4: Better than 59% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 95.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Solar Mini 4: 22.3%
    • GPT 5.1 Codex Max: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Solar Mini 4: 2.4%
    • GPT 5.1 Codex Max: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Solar Mini 4: 867 Elo
    • GPT 5.1 Codex Max: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Solar Mini 4: 1,085 Elo
    • GPT 5.1 Codex Max: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Solar Mini 4: 5.0%
    • GPT 5.1 Codex Max: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Solar Mini 4: 83.3%Top
    • GPT 5.1 Codex Max: 69.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Solar Mini 4: 6.7%
    • GPT 5.1 Codex Max: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Solar Mini 4: 25.8%Top
    • GPT 5.1 Codex Max: 25.7%

  • GPQA Diamond

    Graduate-level science questions

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 86.0%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 86.0%

  • IFBench

    Following precise output instructions

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 70.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Solar Mini 4: 1.0%
    • GPT 5.1 Codex Max: —

  • SciCode

    Scientific computing in Python

    • Solar Mini 4: 47.6%
    • GPT 5.1 Codex Max: —

  • LiveCodeBench

    Recent competitive programming problems

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 84.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 95.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 34.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Solar Mini 4: —
    • GPT 5.1 Codex Max: 83.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Solar Mini 4: 83.3%Top
    • GPT 5.1 Codex Max: 69.3%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
90.6 tok/s
Faster than 59% of 253 models
Time to first token
2.2 s
Quicker than 72% of 253 models
Prompt cache hits
22.9%
About $0.0397 per 1M input tokens with caching
Request success (24h)
0.0%
Failing

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 0.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "upstage/solar-mini4",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="upstage/solar-mini4",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

upstage

Other upstage models, starting with the same family.