LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

deepseek-ai/DeepSeek-V4.1-Flash-Fast

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

Specs & pricing

Input / output per 1M tokens
Reference price·Baseten
$0.60 / $2.40
Blended $1.05 · Cache read —
Lowest paid·Vercel AI GatewayCloud
$0.30 / $1.20
Blended $0.53 · 2× spread
Context
1,048,576
Output limit
32,768
Knowledge cutoff
2025-05
Released / updated
2026-09-10 / 2026-09-10
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImage

Available at 2 providers2 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Vercel AI GatewayCloud$0.30$1.20$0.006—1,048,5761,000,000
Baseten
deepseek-ai/DeepSeek-V4.1-Flash-Fast
Cloud$0.60$2.40——1,048,57632,768

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 = mediumeffort = higheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 2 providers.

Your usage cost

1Vercel AI Gateway$84.72
2Baseten$240.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.40$02026-09-302026-10-042026-09-30 · Input list $0.602026-10-04 · Input list $0.602026-09-30 · Output list $2.402026-10-04 · Output list $2.402026-09-30 · Min blended $1.052026-10-04 · Min blended $0.53

Related models

DeepSeek Flash Latestsame series$0.003 / $2.40DeepSeek V4.1 Flashsame series$0.15 / $0.60DeepSeek V4.1 Flash (EU)same series$0.50 / $1.50GLM-5.3-Flashcheaper alternative$0.15 / $0.50GPT-5.6 Lunacheaper alternative$0.20 / $1.20Qwen3.8 Flashcheaper alternative$0.15 / $0.47
Data partly from models.dev (MIT) · Baseten official docs ↗