Solar Pro 4

Solar Pro 4 is a reasoning model from Upstage in the Solar family. 16 benchmarks count toward its index, in 5 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2026-08
RankedEnough results for an index.
IndexAll categories, out of 100.52.1±6.0Median 51.0
CoverageIndex weight that has results.80%
SpeedOutput tokens per second.44/sMedian 67/s
First tokenSeconds to the first output token.3.0 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.15Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.60Median $2.55
ContextMaximum tokens in one request.524KMedian 262K
EloLMArena rating and rank.1388±5 #174Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
upstage/solar-pro4
Max outputMaximum output tokens per request.
131K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.03
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$0.15$0.60524K
UpstageMaker$0.30$1.20524K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.6 counted49.9129 / 218
CodingCode writing and repair.3 counted58.079 / 209
ReasoningLogic problems and puzzles.2 counted52.599 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.4 counted50.1134 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted53.9—

Results

16 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Artificial Analysis GPQA DiamondKnowledge89.1%47 / 199
Critical Physics TasksReasoning6.3%77 / 214
AIME 2026Math95.3%13 / 34
GDPval-AA normalizedAgentic30.3%63 / 133
GPQA Diamond · BenchLMKnowledge89.0%41 / 84
Artificial Analysis SciCodeCoding48.0%60 / 114
MCP AtlasAgentic61.4%37 / 52
APEX-AgentsAgentic18.7%12 / 13
BrowseCompAgentic49.2%59 / 63
Agent Arena steerabilityAgentic−20.852 / 54
Agent Arena command recoveryAgentic−25.650 / 50
Agent Arena task outcomeAgentic−29.954 / 54

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseLMArenaCC BY 4.0models.devMIT

History

5 releases
Index52.9 → 52.1
23 Oct 202612 Nov 2026
Output / 1M$0.36 → $0.60
23 Oct 202612 Nov 2026

Questions

How much does Solar Pro 4 cost?
$0.15 per 1M input tokens, $0.60 per 1M output tokens.
How good is Solar Pro 4?
Its index is 52.1 out of 100. That is place 129 of 283 ranked models.
What is Solar Pro 4 best at?
Coding: 58.0 out of 100, place 79 of 209.
How fast is Solar Pro 4?
44 output tokens per second, 3.0 s to the first token.
What is the context window of Solar Pro 4?
524K tokens.
Is Solar Pro 4 open source?
No. Its weights are not published.
When was Solar Pro 4 released?
August 2026.

Badge

Solar Pro 4 on Inference360: place 129 of 283, index 52.1
HTML
<a href="https://inference360.ai/models/solar-pro-4"><img src="https://inference360.ai/badges/solar-pro-4.svg" alt="Solar Pro 4 on Inference360: place 129 of 283, index 52.1" height="20"></a>
Markdown
[![Solar Pro 4 on Inference360: place 129 of 283, index 52.1](https://inference360.ai/badges/solar-pro-4.svg)](https://inference360.ai/models/solar-pro-4)

Compare with

Qwen3.6-27B52.1Ternary Bonsai 2 27B52.2Kimi K2.552.2Gemini 3.5 Flash-Lite52.0Solar Open 253.3

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Upstage

All models
Solar Open 253.3Solar Mini 4UnrankedSolar Pro 339.2Solar Pro 2Unranked