DeepSeek V4.1 Flash — API Pricing & Benchmarks
DeepSeek V4.1 Flash is DeepSeek's mid reasoning model, released in 2026-09. The API costs $0.30 per 1M input tokens and $1.20 per 1M output tokens ($0.52 blended at a 3:1 ratio), with cached input at $0.0060. It supports a 1M-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 39.5, ranking #22 of 72 models tracked on this site, with a median output speed of 241 tokens/sec.
Explore provider routes and additional benchmark sources for DeepSeek V4.1 Flash
| Provider | DeepSeek |
| Input price / 1M tokens | $0.30 |
| Output price / 1M tokens | $1.20 |
| Cached input / 1M tokens | $0.0060 |
| Blended price (3:1) | $0.52 |
| Context window | 1M |
| Max output tokens | 384K |
| Knowledge cutoff | — |
| License | open weights |
| Input modalities | T+I |
| Output speed (tok/s) | 241 |
| Released | 2026-09 |
| Artificial Analysis Intelligence Index | 39.5 |
| Humanity's Last Exam | 39.2% |
Where DeepSeek V4.1 Flash fits
On a blended 3:1 basis DeepSeek V4.1 Flash costs $0.52 per 1M tokens, cheaper than 77% of the 84 priced models in this index. It sits in the mid-tier bracket where most production chat, RAG and summarization workloads run: meaningfully cheaper than flagships while keeping most of their capability. Measured output speed of 241 tokens/sec is well above the index median of 107, making it suitable for interactive, user-facing use. The weights are open, so it can be self-hosted for data-residency or cost reasons instead of consumed via API. Cached input is priced at $0.0060 (98% below standard input), which rewards prompt structures with long stable prefixes — see our caching guide.
Price history
| Period | Input $/1M | Output $/1M | Cached $/1M |
|---|---|---|---|
| 2026-09-10 → current | $0.30 | $1.20 | $0.0060 |
No list-price changes recorded since tracking began. Full dataset: price-history.json (CC BY 4.0).
Alternatives at a similar price
- MiniMax M3 (MiniMax) — $0.52/1M blended, AA Index 29.2
- MiniMax M2.7 (MiniMax) — $0.52/1M blended, AA Index 22.8
- Solar Pro 4 (Upstage) — $0.52/1M blended, AA Index 28.2
- Gemini 3.1 Flash-Lite (Google) — $0.56/1M blended, AA Index 15.6
About DeepSeek
DeepSeek publishes open-weights models at disruptive prices. Even after its August 2026 switch to peak/off-peak billing, the V4 line costs a fraction of Western equivalents, off-peak hours (everything outside 01:00–04:00 and 06:00–10:00 UTC on weekdays) halve the bill again, and V4.1 Flash added native vision in September at $0.30/$1.20 peak.