Solar Pro 4 Thinking
Upstage's Solar Pro 4 with reasoning enabled for harder agentic workflows, document-intensive work, coding, planning, and analysis across a 524K-token context window.
- Reasoning
- Tool Calling
- Structured Output
Added Aug 11, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.030
- Output
- $0.12
- Cache read
- $0.0060
Specifications
- Context window
- 524.3K
- Max output
- 131.1K
- Avg output (7d)
- 2.3K tokens
- Longer than 92% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
26.6
Coding Index
52.7
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
13.6%
Better than 34% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
2.4%
Better than 38% of models compared
AA-Briefcase v1.1
Agentic knowledge work (Elo)
1093 Elo
Better than 54% of models compared
GDPval-AA v2.1
Economically valuable tasks (Elo)
1106 Elo
Better than 52% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
7.0%
Better than 33% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
70.7%
Better than 63% of models compared
Reasoning
HLE
Humanity's Last Exam
29.8%
Better than 76% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 16% of models compared
SciCode
Python programming for scientific computing
48.0%
Better than 45% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
89.1%
Better than 86% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
70.7%
Better than 63% of models compared
Last updated Oct 22, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Reliability
Last 3 days