Editorial evidence rank 2 · independent
A reviewed second-tier everyday candidate where the direct offer can be cost-effective.
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 Pro
DeepSeek (deepseek)· 1M context$0.43 input$0.87 output/ 1M$0.004 cache read / 1M - Planning estimate
- $5.22 / month10M input + 1M output / month · uncached input + output; not a spend prediction
- Budget fit
- Within monthly budget $100
- Background role
- DeepSeek V4 FlashDeepSeek
(deepseek)· $0.14 input · $0.28 output / 1M · $1.68 full-volume estimate - Connection facts
- DeepSeek ·
deepseek-v4-proProvider documentation(opens in a new tab) · Direct API route; dsh is a developer preview and is limited to this route.
Background uses DeepSeek V4 Flash via DeepSeek; its full-volume estimate is cheaper than the primary. No image-capable evidence-matched vision offer passed the same-provider gates.
Evidence sources (2)
- Independent DeepSeek V4 Pro model page(opens in a new tab) — Independent model coverage informs qualitative ordering; no proprietary scores are reproduced.
- DeepSeek official pricing(opens in a new tab) — First-party pricing is a cross-check; the selected live Models.dev offer supplies the estimate.
Caveats
- Model evaluations do not prove performance in the selected harness.
- Only exact current and 0813 aliases match.
