EXAONE 4.5 33B API Pricing

LG AI Research · released 2026-04-09 · merges 2 reasoning-effort tiers

Benchmarks shown for the highest-scoring reasoning tier. Merged tiers: EXAONE 4.5 33B, EXAONE 4.5 33B (Non-reasoning).

Pricing

Pricing not published by Artificial Analysis yet.

Benchmarks

13.2
Intelligence
#198 of 533
23.6
Coding
#131 of 197
Math
Tokens/sec
Time to first token

Leaderboard neighbours

ModelIntelligenceBlended $/1M
Apriel-v1.6-15B-Thinker13.4
Nova 2.0 Lite (high)13.4$0.85
Qwen3 VL 235B A22B (Reasoning)13.4$1.30
EXAONE 4.5 33B13.2
Command A+13.1
DeepSeek R1 0528 (May '25)13.1$1.763
Gemini 2.5 Flash (Reasoning)13.1$0.85

More from LG AI Research

ModelIntelligenceBlended $/1M
K-EXAONE 2.0 080319.7
K-EXAONE (Reasoning)14.4
EXAONE 4.0 32B (Reasoning)8.2
EXAONE 4.0 32B (Non-reasoning)6.3
Exaone 4.0 1.2B (Reasoning)5.3
Exaone 4.0 1.2B (Non-reasoning)5.2

See EXAONE 4.5 33B on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops EXAONE 4.5 33B?

EXAONE 4.5 33B is developed by LG AI Research, released 2026-04-09.

Is EXAONE 4.5 33B's API pricing published?

No — as of the last data sync (2026-09-22), Artificial Analysis has not published official API pricing for EXAONE 4.5 33B. This page updates automatically once pricing is available.

How does EXAONE 4.5 33B rank on benchmarks?

EXAONE 4.5 33B scores 13.2 on the Artificial Analysis Intelligence Index, ranking #198 of 533 models we track.

Where does this data come from?

Pricing and benchmark data for EXAONE 4.5 33B comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.