Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for upstage

Upstage: Solar Pro 3

upstage/solar-pro-3

Compare

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.

Modalities
In / Out Price
$0.15 / $0.60per 1M
Context
131K
Released
Jan 27, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Upstage: Solar Pro 3 (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisSolar Pro 3 Intelligence Index7.8
Artificial AnalysisSolar Pro 3 Coding Index16.2
Artificial AnalysisSolar Pro 3 Agentic Index1.4
Artificial AnalysisSolar Pro 3 GPQA Diamond72.4%
Artificial AnalysisSolar Pro 3 HLE10.3%
Artificial AnalysisSolar Pro 3 IFBench71.2%
Artificial AnalysisSolar Pro 3 τ²-Bench Telecom86.3%
Artificial AnalysisSolar Pro 3 AA-LCR32.3%
Artificial AnalysisSolar Pro 3 GDPval-AA0.0%
Artificial AnalysisSolar Pro 3 CritPt0.0%
Artificial AnalysisSolar Pro 3 SciCode25.5%
Artificial AnalysisSolar Pro 3 Terminal-Bench Hard7.6%
Artificial AnalysisSolar Pro 3 AA-Omniscience Accuracy18.5%
Artificial AnalysisSolar Pro 3 AA-Omniscience Non-Hallucination Rate11.8%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
$0.15$0.60$0.0150.64s5 tps
94.16%
Throughput
5tok/s

P50, best across providers

Latency
0.64s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
95.07%

Availability over the last 3 days

Last 72 hours
Availability 95.07%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
90.30%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
57.5Mtokens
2.
Favicon for https://portal.nousresearch.com/api-docs
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
51.9Mtokens
3.
Favicon for https://cline.bot
Cline
Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.
15.8Mtokens
4.
Favicon for https://tietoarc.com/
tietoarc
new
12.4Mtokens
5.
Favicon for https://avvi.cloud/
Avvi Admin Bench
new
2.07Mtokens

Frequently asked questions

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.

Solar Pro 3 costs $0.15/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.015/M tokens.

Solar Pro 3 has a 131,072 token context window. It supports up to 131,072 completion tokens.

Yes. Solar Pro 3 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Solar Decide, Solar Mini 4, and Solar Pro 4 are other text models from Upstage.

Solar Pro 3 was released on January 27, 2026.

More models from upstage

Solar Decide

Solar Decide is Upstage's structured decision model, served as a System One endpoint on Solar Mini 4. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a calibrated probability taken directly from the model rather than written out as text. Because it generates no prose, each decision takes a single forward pass and output tokens are free. With a 512K context window, an entire document can serve as the state. Solar Decide uses the same /v1/systemone schema as Jev, bringing Solar Mini 4's strong Korean understanding to routing, classification, and policy checks.

Decisions$0.05 / $0
Solar Mini 4

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads.

When using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.

Text524K context$0.05 / $0.20
Solar Pro 4

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.

When using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.

Text524K context$0.09 / $0.36