FREE TOOL · PRICES VERIFIED AUGUST 31, 2026

DeepSeek API Pricing

Frontier-class open-weight models at commodity prices — plus an off-peak window that halves them again. Real per-million-token rates, a calculator for your workload, and the comparison against closed rivals.

MODELS
2
INPUT FROM
$0.44/1M
OUTPUT UP TO
$3.96/1M
MAX CONTEXT
1M
ESTIMATE YOUR WORKLOAD
MODELINPUT $/1MCACHED INOUTPUT $/1MBLENDEDCONTEXTYOUR COST
DeepSeek V4 Pro
deepseek-v4-pro-0813 · off-peak −50%
$1.32$0.044$3.96$1.981M$3.30
DeepSeek V4 Flash
deepseek-v4-flash-0731 · off-peak −50%
$0.44$0.014$1.32$0.661M$1.10

USD per 1M tokens from DeepSeek’s official pricing page as of August 31, 2026. Blended assumes a 3:1 input:output ratio. Get keys at the DeepSeek console.

HOW DEEPSEEK PRICING WORKS

Frontier quality at commodity prices — half price after hours.

DeepSeek keeps the menu short: V4 Pro, the frontier reasoning model, at $1.32 input / $3.96 output per 1M tokens with a 1M context, and V4 Flash at $0.44 / $1.32 for volume work. Both are text-only (pair them with a vision model if you need images) and both ship open weights, so you can also self-host or buy them from any inference provider.

The signature mechanic is the off-peak discount: between 16:30 and 00:30 UTC, everything bills at half price. Schedule batch jobs, evaluations, and backfills into that window and you get a batch-API-grade discount without a batch API — V4 Pro effectively drops to $0.66 / $1.98.

Cache hits are the other outlier: repeated prompt prefixes bill at $0.044 per 1M tokens on V4 Pro — about a thirtieth of the fresh rate, the deepest cache discount on this site. Agents with long stable system prompts run absurdly cheap here.

How much does the DeepSeek API cost?

DeepSeek V4 Pro costs $1.32 input / $3.96 output per 1M tokens, and V4 Flash $0.44 / $1.32 — with everything at half price during the off-peak window (16:30–00:30 UTC) and cache hits at roughly a thirtieth of the fresh input rate.

How does the DeepSeek off-peak discount work?

Requests processed between 16:30 and 00:30 UTC bill at 50% of the standard rate, input and output alike. There is nothing to configure — the discount applies automatically based on when the request lands. Time-shift bulk workloads into the window and your effective price halves.

Is DeepSeek really frontier quality?

V4 Pro sits in the frontier class on reasoning and coding benchmarks while costing a fraction of closed rivals — around $1.98/1M blended versus $8 for GPT-5.6 Sol and $10 for Claude Opus 5. The trade-offs: text-only input, and you are buying from a Chinese lab, which matters for some compliance postures.

Can I self-host DeepSeek?

Yes — the V4 models ship open weights, so you can run them on your own GPUs or through any inference provider. The prices on this page are DeepSeek’s first-party API rates, which are usually hard to beat at small scale once you count GPU costs.

Does DeepSeek have vision or audio models?

The V4 API models priced here are text-only. If your workload needs image, audio, or video input at a similar price point, look at GLM-5.3-Flash, MiMo-V2.5, or Gemini Flash-Lite — the matchup table below includes the closest alternatives.

HOW DEEPSEEK STACKS UP

DeepSeek vs. its closest rivals, tier by tier

BLENDED $/1M · 3:1 IN:OUT
OPEN FRONTIER
DeepSeek V4 Pro
$1.98/1M
GLM-5.3
$2.15/1M
Kimi K3
$6.00/1M
COMPARE
VS CLOSED MID-TIER
DeepSeek V4 Pro
$1.98/1M
GPT-5.6 Terra
$4.50/1M
Claude Sonnet 5
$4.00/1M
COMPARE
FAST TIER
DeepSeek V4 Flash
$0.66/1M
GLM-5.3-Flash
$0.119/1M
Qwen3.8-Flash
$0.23/1M
COMPARE

Also see: OpenAI API pricing · Claude API pricing · Gemini API pricing · Grok API pricing · Kimi API pricing · GLM API pricing · MiniMax API pricing · MiMo API pricing · all 58 models

BUILDING ON THE DEEPSEEK API?

Your users will spend these tokens. Meter them per API key.

ReqKey gives every key a credit balance — validate, deduct, enforce limits, and watch per-consumer DeepSeek spend in real time.