K-EXAONE-236B-A23B: API Pricing, Context Window & Benchmarks
K-EXAONE-236B-A23B is a language model from LG AI Research, released in December 2025.
K-EXAONE is a state-of-the-art large language model developed by LG AI Research with 236 billion parameters. It features advanced reasoning capabilities, strong performance in both Korean and English, and excels at complex tasks including
K-EXAONE-236B-A23B benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
How K-EXAONE-236B-A23B performs across real-world prompt categories.
Performance by conversation depth
How K-EXAONE-236B-A23B holds up as conversations get longer.
Quality Tracker
K-EXAONE-236B-A23B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Aug 24 2026K-EXAONE-236B-A23B pricing
Providers
K-EXAONE-236B-A23B starts at $0.600 per million input tokens and $1.00 per million output tokens via FriendliAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 FriendliAI | $0.600 | — | $1.00 | 32.8K/32.8K | 0.40 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
K-EXAONE-236B-A23B context window
Input and output token limits for K-EXAONE-236B-A23B, plus how it ranks on long-context understanding.
K-EXAONE-236B-A23B API
Available from the model provider
K-EXAONE-236B-A23B has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationK-EXAONE-236B-A23B latency
K-EXAONE-236B-A23B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
K-EXAONE-236B-A23B examples
Recent arena outputs from K-EXAONE-236B-A23B, picked from the highest-ranked matchups.
K-EXAONE-236B-A23B license
K-EXAONE-236B-A23B is a proprietary model available under its provider's product and API terms, has 236.0B parameters, has a knowledge cutoff of October 2025.
- License
- Proprietary
- Hosted access
- Parameters
- 236.0B
- Knowledge cutoff
- October 2025
Proprietary license - usage restrictions apply
K-EXAONE-236B-A23B resources
Official sources for K-EXAONE-236B-A23B: api documentation, official playground, official launch post, source repository.
K-EXAONE-236B-A23B vs other models
The most-compared alternatives to K-EXAONE-236B-A23B are Seed 2.0 Lite, GPT OSS 120B High, Claude 3.7 Sonnet. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like K-EXAONE-236B-A23B
Models ranked just above and below K-EXAONE-236B-A23B by LLM Stats score.
FAQ
Common questions about K-EXAONE-236B-A23B.