NOUMENOpen app
NOUMEN

upstage · Efficient

Solar Mini 4 Thinking

Added Sep 23, 2026

Compare models

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

Loading models…

Use in the app

Solar Mini 4 with reasoning enabled for agentic tasks and harder analysis across a 524K-token context window.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
none · low · medium · high
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)
2.8K tokens
Longer than 95% of 465 models

Side by side

Solar Mini 4 Thinking 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 4 ThinkingupstageThis modelSolar Pro 3upstageRemove
Providerupstageupstage
Discovery tierEfficientEfficient
AddedSep 23, 2026Mar 3, 2026
Limits
Context window524.29KBest131.07K
Max output131.07K—
Average output2.8K tokens—
Pricing, USD per 1M tokens
Input$0.05Best$0.15
Output$0.20Best$0.60
Cache read$0.005Best$0.015
Benchmark indexes
Intelligence Index—7.8
Coding Index—16.2
Capabilities
ReasoningYesNo
ToolsYesNo
Structured outputYesNo
Reasoning effortnone, low, medium, high—

Public evaluations

Benchmarks

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

  • Solar Mini 4 Thinking
  • Solar Pro 3

Intelligence Index

  • Solar Mini 4 Thinking—
  • Solar Pro 37.8
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 16.2

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 0.5%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 99 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 264 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 1.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 32.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 0.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 10.3%

  • GPQA Diamond

    Graduate-level science questions

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 72.4%

  • IFBench

    Following precise output instructions

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 71.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 0.0%

  • SciCode

    Scientific computing in Python

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 25.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 7.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 86.3%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Solar Mini 4 Thinking: —
    • Solar Pro 3: 32.3%

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

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:thinking",
    "reasoning_effort": "medium",
    "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:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

upstage

Other upstage models, starting with the same family.