LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V4.1 Flash

deepseek·deepseek/deepseek-v4.1-flash·GA·Closed·deepseek series·NEW
DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use. Assume prompts and responses are logged by the provider and may be used for model training or service improvement. Do not send sensitive or confidential data.

DeepSeek V4.1 Flash is currently listed from a single provider. Its reference price is $0.156 per 1M input tokens and $0.312 per 1M output tokens.

The context window is 1,000,000 tokens, with an output limit of 384,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image.

Specs & pricing

Input / output per 1M tokens
Reference price·NanoGPT
$0.156 / $0.312
Blended $0.195 · Cache read $0.031
Lowest paid·NanoGPTGateway
$0.156 / $0.312
Blended $0.195
Context
1,000,000
Output limit
384,000
Knowledge cutoff
—
Released / updated
2026-09-08 / 2026-09-08
Capabilities
✓ Reasoning✓ Tool use✓ Structured output? Temperature✓ Attachments
Modalities
TextImage

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.156$0.312$0.031—1,000,000384,000

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.

Your usage cost

1NanoGPT$31.86
The cheapest paid channel is the only channel.

Reasoning control

effort = noneeffort = loweffort = higheffort = max

Related models

DeepSeek V4.1 Flash Betasame series$0.22 / $0.66DeepSeek V4 Flash Vision Exp Uncensoredsame series$0.44 / $1.60DeepSeek V4 Flash Latestsame series$0.14 / $0.28Qwen3.7 Flashcheaper alternative$0.03 / $0.118Qwen Flashcheaper alternative$0.022 / $0.216Laguna S 2.1cheaper alternative$0 / $0Qwen Turbocheaper alternative$0.044 / $0.087

Price historyone sample accumulated per data sync

Input list $0.156Output list $0.312Min blended $0.195

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-09). Each future sync adds a point, and once accumulated a line is drawn here.

Data partly from models.dev (MIT) · NanoGPT official docs ↗