LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V4.1 Flash 1017 Ultrafast

deepseek·deepseek/deepseek-v4-1-flash-1017-ultrafast·GA·Open weights·deepseek series·NEW
Fast DeepSeek model for efficient chat, coding help, and agent loops

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Vercel AI GatewayCloud
$2.40 / $9.60
Blended $4.20 · 1.3× spread
Context
1,000,000
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-10-23 / 2026-11-06
Capabilities
✓ Reasoning✓ Tool use✓ Structured output? Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • Vercel AI GatewayCloud
    deepseek/deepseek-v4.1-flash-1017-ultrafast
    $2.40 / $9.60
    Cache read $0.048Context 1,048,576 ⚠Output limit 1,048,576
  • Venice AIGateway
    $3.00 / $12.00
    Cache read $0.06Context 1,000,000Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Vercel AI Gateway
deepseek/deepseek-v4.1-flash-1017-ultrafast
Cloud$2.40$9.60$0.048—1,048,576 ⚠1,048,576
Venice AIGateway$3.00$12.00$0.06—1,000,000131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = higheffort = max

Your usage cost

Common scenarios
1Vercel AI Gateway$677.76
2Venice AI$847.20
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $4.20

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-19). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

DeepSeek V4.1 Flash 1017 Abliterated CSF (jcartu)same series—DeepSeek V4.1 Flash 1017 Abliteratedsame series—DeepSeek V4.1 Flash 1017 Abliterated Thinkingsame series—
Data partly from models.dev (MIT)