SIDE BY SIDE
Compare selected AI models side by side.
Compare uses, prices, speed evidence, and version details for up to three models. Language, video, decision models and historical evaluations are shown separately.
Language & coding
| What matters | DeepSeek V4.1 Flash (fast) ↗DeepSeek |
|---|---|
| Use cases | Coding · Agents & tools · Reasoning · Visual understanding |
| Model score | 39DeepSeek V4.1 Flash · maxArtificial Analysis · DeepSeek V4.1 Flash · max ↗ |
| Output / 1M tokens · USD | $0.3 |
| Published rates · USD | $0.3 input / $1.2 outputPer 1M native tokens |
| Cached input / 1M | $0.006 |
| Cache write / 1M | Not verified |
| Pricing conditions | DeepSeek API · peak hoursOff-peak rates are 50% lower. Peak: weekdays 01:00–04:00 and 06:00–10:00 UTC.DeepSeek models & pricing ↗ |
| Output speed · tokens/s | 214.1 tokens/sDeepSeek API · V4.1 Flash · Max reasoning. Artificial Analysis reports a rolling 72-hour median of output speed after the first token, not total response time. Checked 2026-10-05; speed varies with workload and serving conditions.Artificial Analysis · DeepSeek V4.1 Flash (Max) ↗Artificial Analysis · performance methodology v2.2.0 ↗ · Checked 2026-10-05 |
| Context window | 1,000,000 |
| Model ID | deepseek-flash |
| Version notes | The old V4 Flash API aliases now serve V4.1 Flash. Preview benchmark scores are not transferred to this version. |
| Official documentation | DeepSeek models & pricing ↗Checked 2026-10-05 |
Language prices are USD per million tokens; input and output are billed separately. Video samples use 5s of 768P output where verified. Extra tools, reasoning, cache writes, input media, storage, and taxes can change the total. (fast) marks a published median output speed above 150 tokens/s in the linked test settings.