U

Upstage API Pricing (Updated 2026)

Compare pricing for all 4 Upstage models. Prices shown per 1M tokens with historical trends.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

4
Total Models
$0.05
Cheapest Input (per 1M)
524K
Max Context Length

Model Release Timeline

3 releases
Jan 2026
$0.15 / $0.60
Aug 2026
$0.15 / $0.60
Sep 2026
$0.05 / $0.20
Spacing represents time between releases
Jan 2026→Sep 2026

All Upstage Models

Compare pricing for all 4 Upstage models.

View Provider Pricing
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Model
Context
Input
Output
Cached Input
Cache Write
MMLU
GPQA
Actions
524K
$0.050
$0.200
$0.005
-
—
—
Try
128K
$0.150
$0.600
-
-
—
—
Try
524K
$0.150
$0.600
$0.03
-
—
89.1
Try
4K
$0.300
$0.300
-
-
—
—
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts under 200k tokens.

Showing lowest price across all providers. Benchmarks from Artificial Analysis and HuggingFace Open LLM Leaderboard.

Cost vs. Quality

Compare Upstage models by benchmark performance and cost.

X-axis:
Y-axis:

No benchmark data available for comparison

Benchmark scores are sourced from Artificial Analysis

Upstage Models

Community Ratings

Rate how well Upstage models perform across popular AI coding tools.

Historical Pricing Trends

Price Changes Over Time

No historical pricing data available for this provider.

Try Upstage Models

Cost Calculator

Estimate your costs for any Upstage model based on expected token usage.

Open Cost Calculator

Try in Playground

Test Upstage models directly in your browser.

Open Playground

Frequently Asked Questions

Currently, Solar Mini4 is the most affordable at $0.05 per 1M input tokens.
Count your input tokens (prompt) and expected output tokens (response). Use the formula: (input_tokens/1M × input_price) + (output_tokens/1M × output_price). Our pricing calculator can help automate this.
Upstage pricing varies by model. Input costs range from $0.05 to $0.30 per 1M tokens. See the table above for specific model pricing.