Solar Pro 4 benchmarks, pricing and specs
Solar Pro 4 is an Upstage model released on August 6, 2026 that takes text input and produces text. It costs $0.30 per 1M input tokens and $1.20 per 1M output tokens and accepts up to 512,000 tokens of context. It scores 1386 Elo on Arena Text, #45 of 49 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $0.30
- Per 1M output tokens
- $1.20
- Context window
- 512K
- Arena Text
- 1386 Elo · #45/49
Data verified October 13, 2026 · Dataset 2026-10-13
Key facts
- Provider
- Upstage
- Model family
- Solar Pro
- Release date
- August 6, 2026
- Status
- Current
- Access
- API only
- API model id
- solar-pro4-260806
- Context window
- 512,000 tokens
- Max output
- 128,000 tokens
- Input
- text
- Output
- text
- Task families
- text
- Declared capabilities
- reasoning, coding, agentic coding, document understanding
Solar Pro 4 pricing
It is the #9 cheapest of 47 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Upstage's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1386 Elo | #45 of 49 | October 8, 2026 | Arena · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Upstage's agentic flagship for tool calling, terminal tasks and long-document reasoning, with a 512K context and up to 128K output tokens
- Upstage reports 70.6 on SWE-Bench Verified with OpenHands in its own evaluation
- Supports English, Korean and Japanese
Cautions
- A closed model: Upstage does not disclose its parameter count
- Several of its published benchmark figures are in-house evaluations
Best for
- Korean and Japanese enterprise workloads
- Multi-step agent work with tool calls
Alternatives to Solar Pro 4
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
GPT-6 Luna
- 67% cheaper per 1M input tokens, $0.10 vs $0.30
- 57 points higher on Arena Text, 1443 vs 1386
- 1.05M context window vs 512K
- From OpenAI
DeepSeek-V4.1-Flash
- Same price per 1M input tokens, $0.30
- 89 points higher on Arena Text, 1475 vs 1386
- From DeepSeek
Gemini 3.5 Flash-Lite
- Same price per 1M input tokens, $0.30
- 69 points higher on Arena Text, 1455 vs 1386
- 1.05M context window vs 512K
- From Google
GPT-4.1 mini
- 33% more per 1M input tokens, $0.40 vs $0.30
- 3 points lower on Arena Text, 1383 vs 1386
- 1.05M context window vs 512K
- From OpenAI
Compare Solar Pro 4 with
Solar Pro 4 FAQ
How much does Solar Pro 4 cost?
Solar Pro 4 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens at the standard tier. It is the #9 cheapest of 47 current text models priced per 1M input tokens. Source: Upstage, verified October 13, 2026.
What is the context window of Solar Pro 4?
Solar Pro 4 accepts up to 512,000 tokens of context. It can return up to 128,000 tokens in one response. That ranks #45 of 57 current text models by context length.
How does Solar Pro 4 score on independent benchmarks?
Solar Pro 4 scores 1386 Elo on Arena Text, #45 of 49 current models (Arena, measured October 8, 2026). These are independent evaluations, not Upstage's own launch figures.
Is Solar Pro 4 open source or API only?
Solar Pro 4 is available through Upstage's API only; its weights are not published.
What are the best alternatives to Solar Pro 4?
The closest current alternatives by price and measured performance are GPT-6 Luna (67% cheaper per 1M input tokens, $0.10 vs $0.30), DeepSeek-V4.1-Flash (same price per 1M input tokens, $0.30), Gemini 3.5 Flash-Lite (same price per 1M input tokens, $0.30) and GPT-4.1 mini (33% more per 1M input tokens, $0.40 vs $0.30).
Sources
- Solar Pro 4 documentation · Upstage · official · verified October 13, 2026
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Solar Pro 4 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/solar-pro-4
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Solar Pro 4 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls