Upstage: Models Intelligence, Performance & Price

Upstage

This analysis is intended to support you in choosing the best model provided by Upstage for your use-case.

Most Intelligent

Updated

Intelligence Index

Total 4 models

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 4 models

Lowest Price

Solar Mini 4

$0.07

Solar Pro 3

$0.10

Solar Mini

$0.15

Solar Pro 4

$0.22

Blended price (per 1M tokens)

Total 4 models

Upstage offers 4 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

For latency, Solar Mini (0.83s), Solar Pro 3 (18.94s), and Solar Pro 4 (61.04s) offer the lowest time to first answer token.
For pricing, Solar Mini 4 ($0.07), Solar Pro 3 ($0.10), and Solar Mini ($0.15) offer the lowest blended prices per 1M tokens. Prices vary up to 3.3x across models.
For context window size, Solar Mini 4 (524k), Solar Pro 4 (512k), and Solar Pro 3 (131k) support the largest context windows on Upstage.

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

No data available

Time per Task

Inference time (minutes) per Intelligence Index task · Lower is better

No data available

Price

USD per 1M tokens (blended) · Lower is better

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

No data available

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100

AA-Briefcase v1.1

Agentic knowledge work, Elo

AA-Omniscience v1.1 AccuracyUpdated

Knowledge

AA-Omniscience v1.1 Non-Hallucination RateUpdated

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 2.0New

Agentic software engineering in open-source repositories

No data available

HLE-DiamondNew

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

CritPt v2 (Hard Subset)

Physics reasoning

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

No data available

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

No data available

EnterpriseOps-Gym-AA

Agentic business operations

No data available

GDPval-AA v2.1

Agentic real-world work tasks, Elo

AA-3DNew

Agentic interactive 3D experiences, Elo

No data available

Code2Video-AANew

Product and brand videos designed in code, Elo

No data available

ITBench-AA

Kubernetes incident root-cause analysis

No data available

MLCR-AAUpdated

Medical long context reasoning

MMMU-Pro

Visual reasoning

No data available

AA-PersonalityBench: Expressiveness ScoreNew

Rich, varied, well-crafted language

No data available

AA-PersonalityBench: Organization ScoreNew

Well-structured, scannable, answer-first

No data available

AA-PersonalityBench: Transparency ScoreNew

Truthful, acknowledges uncertainty, non-sycophantic

No data available

AA-PersonalityBench: Slop ScoreNew

Use of filler and generic language

No data available

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

No data available

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Pricing

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

No data available

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Speed

Average of the single-request and multi-turn agentic workloads measured

Output Speed

Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Quality

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Share of requests over the past 5 days that the endpoint failed with an error, a rate limit or a timeout. Failures on our side are left out of both counts. Across several workloads, the failures and requests are pooled before dividing.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Caching

Cache Hit Rate

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026

Most attractive quadrant

No data available


								Further Analysis
Solar Pro 4	--	--	--	61.04	3.9%	512k	Proprietary	Model Provider
Solar Mini 4	--	--	--	62.85	2.9%	524k	Proprietary	Model Provider
Solar Pro 3	--	--	--	18.94	0.0%	131k	Proprietary	Model Provider
Solar Mini	--	--	--	0.83	0.0%	4k	Open	Model Provider

Key definitions

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Frequently Asked Questions

Common questions about Upstage

Upstage offers 4 models that we track: Solar Pro 4, Solar Mini 4, Solar Pro 3, and Solar Mini.

The model with the lowest time to first answer token on Upstage is Solar Mini at 0.83s. Lower latency means faster initial response time.

The most affordable model on Upstage by blended price is Solar Mini 4 at $0.07 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on Upstage vary up to 3x across models, from $0.07 per 1M tokens for Solar Mini 4 to $0.22 per 1M tokens for Solar Pro 4.

Yes, Upstage offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.

Yes, all 4 models on Upstage support JSON mode for structured output.

Yes, all 4 models on Upstage support function calling (tool use).

Yes, Upstage offers 3 reasoning models: Solar Pro 4, Solar Mini 4, and Solar Pro 3. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, 1 of 4 models on Upstage are open weight models: Solar Mini.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

When choosing a model on Upstage, consider: intelligence (for quality-sensitive tasks), time per task (how quickly the model completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.

Upstage: Models Intelligence, Performance & Price

Most Intelligent

Lowest Time per Task

Lowest Price

Intelligence

Time per Task

Price

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence Index vs. Price

Price-Quality Variance

Pricing

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Intelligence Index vs. Price

Price-Quality Variance

Speed

Output Speed

End-to-End Output Speed

Time Period

Quality

Context Window

Context Window for RAG

Context Window

Latency

Time to First Answer Token

Time to First Answer Token

Time Period

Reliability

Endpoint Error Rate

Endpoint Error Rate

Time Period

Caching

Cache Hit Rate

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate

Cost per Intelligence Index Task

What Cache Hit Rate Shows

Key definitions

Index Cost per Task

Frequently Asked Questions

What models does Upstage offer?

Which model has the lowest latency on Upstage?

What is the cheapest model on Upstage?

How much do prices vary across models on Upstage?

Is Upstage OpenAI compatible?

Does Upstage support JSON mode?

Does Upstage support function calling?

Does Upstage offer reasoning models?

Does Upstage offer open weight models?

Does Upstage's performance change over time?

How do I choose a model on Upstage?