AC Flash 4.5
webparam/ac-flash-4-5-standardFast tier — the cheapest way to run high volume. Measured at 2.2s to first token and 24.1 tokens/sec.
— ctx · R10 in · R40 out
Category
Language
General text generation and understanding. The workhorse category: drafting, summarising, extraction and conversation across every domain. Start here for anything text-shaped and trade up only when a task genuinely needs it. The deciding numbers are usually price per million and how much of the you actually fill.
51 models in Language from 19 providers
Top models
Leading language models
Browse all language models →
51 models in the directory
How to choose
Choosing a model in Language
- 01
Match cost to volume
High-volume pipelines rarely need flagship pricing. Mid-tier models handle most drafting and summarisation at a fraction of the cost.
- 02
Check context honestly
A huge context window matters only if you actually fill it. Paying for 1M tokens of context you never use is the most common overspend.
- 03
Test your own prompts
Leaderboards measure averages. Your production prompts are not average. Try two or three candidates side by side before committing.