A lower-ranked everyday candidate that cost priority may select.
Published ranking rule: Balanced: ranks through bestRank + 1; then lower uncached estimate, evidence class (independent, mixed, official-only), editorial rank, direct provider, and stable provider/model/evidence IDs.
- Primary model
- DeepSeek V4 Flash
DeepSeek
(deepseek)· 1M context$0.14 input$0.28 output/ 1M$0.003 cache read / 1M - Planning estimate
- $1.68 / month10M input + 1M output / month · uncached input + output; not a spend prediction
- Budget fit
- Within monthly budget $100
- Connection facts
DeepSeek ·
deepseek-v4-flashProvider documentation(opens in a new tab) · Direct API route; dsh is a developer preview and is limited to this route.
No cheaper evidence-matched background offer passed the same-provider gates. No image-capable evidence-matched vision offer passed the same-provider gates.
Evidence sources (2)
- Independent DeepSeek V4 Flash article(opens in a new tab) — Independent analysis supports qualitative value positioning; Hastat does not reproduce its score table.
- DeepSeek official pricing(opens in a new tab) — Official pricing context complements the exact current Models.dev offer.
Caveats
- The independent article concerns the exact 0731 generation/current alias.
- Low price is never treated as intelligence evidence.