How much does Solar Pro 4 cost?

Solar Pro 4 costs $0.15/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.03/M tokens.

What is the context length of Solar Pro 4?

Solar Pro 4 has a 524,288 token context window. It supports up to 131,072 completion tokens.

Does Solar Pro 4 support tool calling and structured outputs?

Yes. Solar Pro 4 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve Solar Pro 4?

Solar Pro 4 is served by 2 providers on OpenRouter: Upstage and KT. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Solar Pro 4 released?

Solar Pro 4 was released on August 10, 2026.

Upstage: Solar Pro 4

upstage/solar-pro4

Compare

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.

Modalities

In / out price

50% off

$0.15 / $0.60per 1M

Context

524K

Released

Aug 10, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


50% off	$0.30$0.15	$1.20$0.60	$0.06$0.03	0.98s	84 tok/s	100.00%
	$0.30	$1.20	$0.06	0.92s	128 tok/s	99.94%
50% off	$0.30$0.15	$1.20$0.60	$0.06$0.03	2.57s	57 tok/s	100.00%

Input $0.15Output $0.60
50% off
84 tok/s100.00% uptime
Input $0.30Output $1.20
128 tok/s99.94% uptime
Input $0.15Output $0.60
50% off
57 tok/s100.00% uptime

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.

Weighted average

Input

$0.06948/M tokens

Output

$1.014/M tokens

Solar Pro 4 — Price history

Price history

No effective price data for this selection

$0.0482	$0.646	86.9%	1.4%
$0.0695	$1.031	95.5%	97.4%
$0.0943	$1.199	85.7%	1.2%

Effective in $0.0482Effective out $0.646
Token share
1.4%
Effective in $0.0695Effective out $1.031
Token share
97.4%
Effective in $0.0943Effective out $1.199
Token share
1.2%

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.

Uptime (3d)

100.00%

Availability (3d)

99.78%

Availability over the last 3 days

Last 72 hours

Availability 99.78%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

Without Routing

98.90%

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 provider routing options.

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 4 (Artificial Analysis and Design Arena)
Source	Benchmark	Score
Artificial Analysis	Solar Pro 4 Intelligence Index	28.2
Artificial Analysis	Solar Pro 4 Coding Index	52.7
Artificial Analysis	Solar Pro 4 GPQA Diamond	89.1%
Artificial Analysis	Solar Pro 4 HLE	29.2%
Artificial Analysis	Solar Pro 4 AA-LCR	74.0%
Artificial Analysis	Solar Pro 4 τ-Bench Banking	23.3%
Artificial Analysis	Solar Pro 4 GDPval-AA	30.4%
Artificial Analysis	Solar Pro 4 CritPt	5.4%
Artificial Analysis	Solar Pro 4 SciCode	44.6%
Artificial Analysis	Solar Pro 4 Terminal-Bench 4.0	0.5%
Artificial Analysis	Solar Pro 4 Terminal-Bench 2.1	57.3%
Artificial Analysis	Solar Pro 4 AA-Omniscience Accuracy	18.9%
Artificial Analysis	Solar Pro 4 AA-Omniscience Non-Hallucination Rate	75.6%
Artificial Analysis	Solar Pro 4 Intelligence Index	14.2
Artificial Analysis	Solar Pro 4 Agentic Index	28.8
Artificial Analysis	Solar Pro 4 GPQA Diamond	89.1%
Artificial Analysis	Solar Pro 4 HLE	29.8%
Artificial Analysis	Solar Pro 4 AA-LCR	70.7%
Artificial Analysis	Solar Pro 4 τ-Bench Banking	23.3%
Artificial Analysis	Solar Pro 4 GDPval-AA	30.3%
Artificial Analysis	Solar Pro 4 CritPt	6.3%
Artificial Analysis	Solar Pro 4 SciCode	48.0%
Artificial Analysis	Solar Pro 4 Terminal-Bench 4.0	0.0%
Artificial Analysis	Solar Pro 4 Terminal-Bench 2.1	57.3%
Artificial Analysis	Solar Pro 4 AA-Omniscience Accuracy	18.4%
Artificial Analysis	Solar Pro 4 AA-Omniscience Non-Hallucination Rate	79.1%
Design Arena	Solar Pro 4 Agents Arena Webapps Elo	1081
Design Arena	Solar Pro 4 Models Arena 3D Elo	1159
Design Arena	Solar Pro 4 Models Arena Code Categories Elo	1170
Design Arena	Solar Pro 4 Models Arena Data Visualization Elo	1174
Design Arena	Solar Pro 4 Models Arena Game Development Elo	1168
Design Arena	Solar Pro 4 Models Arena UI Component Elo	1140
Design Arena	Solar Pro 4 Models Arena Website Elo	1163

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.

Freebuff

Powerful coding models, funded by ads

1.71Ttokens

Daum

new

197Btokens

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.

19.7Btokens

TimelyAI

new

14.7Btokens

CodeSolar

new

2.14Btokens

Top 5 Apps

34.4B

Rest of OpenRouter

1.2B

Not currently available through EU in-region routing. In-region routing docs

More models from upstage

Solar Decide Flash

Solar Decide Flash is Upstage's low-latency structured decision model, a faster variant of Solar Decide built on Solar Mini 4 and served through the System One (/v1/systemone) API. Instead of generating text, it reads a state and answers typed questions, returning a choice, a score, or a yes/no answer, each with a probability taken directly from the model. Each decision is a single forward pass, and output tokens are free.

It is tuned for consistently fast response times in routing, classification, and policy checks. It keeps the 512K context window, so a full document can serve as the state, and carries Solar Mini 4's Korean-language strength.

Decisions$0.05 / $0

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 3

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.

Text128K context

Upstage: Solar Pro 4

Providers