LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

deepseek-v4.1-flash-latest

deepseek·deepseek/deepseek-v4.1-flash-latest·GA·Closed·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·DevPass (LLM Gateway)Gateway
$0.078 / $0.59
Blended $0.20 · 3.9× spread
Context
1,048,576
Output limit
393,216
Knowledge cutoff
—
Released / updated
2026-10-17 / 2026-10-17
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

deepseek-v4.1-flash-latest is offered by 18 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is DevPass (LLM Gateway) at $0.078 / $0.587 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 3.9× across the providers that host it.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 262,144 to 1,050,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Available at 18 providers18 with public prices

  • ProviderInput / Output
  • DevPass (LLM Gateway)Gateway
    $0.078 / $0.59
    Cache read $0.0053Context 1,050,000 ⚠Output limit 1,050,000
  • LLM GatewayGateway
    $0.078 / $0.59
    Cache read $0.0053Context 1,048,576Output limit 1,048,576
  • LLM GatewayGateway
    $0.14 / $0.54
    Cache read $0.003Context 1,050,000 ⚠Output limit 1,050,000
  • LLM GatewayGateway
    $0.14 / $0.55
    Cache read $0.0035Context 1,048,576Output limit 1,048,576
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,000,000 ⚠Output limit 1,000,000
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,050,000 ⚠Output limit 393,216
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.01Context 1,048,576Output limit 1,048,576
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,048,576Output limit 1,048,576
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,000,000 ⚠Output limit 393,216
  • LLM GatewayGateway
    $0.20 / $0.60
    Cache read $0.006Context 1,048,576Output limit 393,216
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
DevPass (LLM Gateway)Gateway$0.078$0.59$0.0053—1,050,000 ⚠1,050,000
LLM GatewayGateway$0.078$0.59$0.0053—1,048,5761,048,576
LLM GatewayGateway$0.14$0.54$0.003—1,050,000 ⚠1,050,000
LLM GatewayGateway$0.14$0.55$0.0035—1,048,5761,048,576
LLM GatewayGateway$0.15$0.60$0.003—1,000,000 ⚠1,000,000
LLM GatewayGateway$0.15$0.60$0.003—1,050,000 ⚠393,216
LLM GatewayGateway$0.15$0.60$0.01—1,048,5761,048,576
LLM GatewayGateway$0.15$0.60$0.003—1,048,5761,048,576
LLM GatewayGateway$0.15$0.60$0.003—1,000,000 ⚠393,216
LLM GatewayGateway$0.20$0.60$0.006—1,048,576393,216

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 = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max

Your usage cost

Common scenarios
1DevPass (LLM Gateway)$36.19
2LLM Gateway$36.19
3LLM Gateway$38.16
4LLM Gateway$39.05
5LLM Gateway$42.36
6LLM Gateway$42.36
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.24$02026-11-132026-11-18
2026-11-18Input list —Output list —Min blended $0.20

Related models

DeepSeek V4.1 Flash 1017 Abliterated Thinkingsame series—DeepSeek V4.1 Flash Uncensoredsame series—OrcaCyber DeepSeek V4.1 Flashsame series—DeepSeek V4.1 Flash 1017 Uncensored Thinkingsame lab—
Data partly from models.dev (MIT)