VERIFIED PRICERETIRED MODEL128KTEXT MODELPROMPT CACHING
DeepSeek V3 API Pricing
DeepSeek V3 is retired from the current price table; this archive preserves the $0.27/$1.10 baseline. $0.27/M input, $1.1/M output, and $0.07/M cached input. It is kept for the Jan 2025 price shock and migration comparisons against V4 Flash.
Input - per 1M tokens
$0.27/M
Source DeepSeek retired
Output - per 1M tokens
$1.10/M
Use for cost checks retired
Cached input
$0.07/M
Cache hit price discounted
Effective - agentic blend
$0.19/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Calculator pre-loaded with DeepSeek V3 rates. Tweak spend, output mix, or cache hit rate to compare this model with nearby alternatives.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
AGENT LOOP
Repo-wide bug fix
$0.016/task
LONG DOC
Reading 100-page contracts
$0.027/doc
RAG SUPPORT
Support agent ticket triage
$0.002/ticket
ASSISTANT TURN
Research planning turn
$0.003/turn
§ 03 / TAPE
Price history.
Input · $0.27/M
Output · $1.1/M
Cached · $0.07/M
DEC 26 Launch-era V3 price at $0.27/M input and $1.10/M outputMAY 18 Archive row; current DeepSeek page lists V4 Flash and V4 Pro instead
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · deepseek-tokenizer-estimate · ≈4.2 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| DeepSeek V3 | $0.27 cache $0.07 | $1.10 | $0.19 current page | 128K | Cheap DeepSeek workloads |
| DeepSeek V4 Flash | $0.14 cache $0.00 | $0.28 | $0.05 cheaper | 1M | Cheap DeepSeek workloads |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 cheaper | 1M | Low-cost reasoning |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 pricier | 400K | Open-weight multimodal work |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Open-weight multimodal work |
| Gemini 2.5 Flash | $0.30 cache $0.03 | $2.50 | $0.27 pricier | 1M | Open-weight multimodal work |
| Grok 4.3 | $1.25 cache $0.20 | $2.50 | $0.56 pricier | 1M | Grok long-context agents |
Frequently asked.
Short answers for teams checking DeepSeek V3 pricing, status, and migration choices.
Q · 01 Is DeepSeek V3 still available? +
DeepSeek V3 is retired. Keep this page for pricing history, old invoices, and migration planning.
Q · 02 How much does DeepSeek V3 cost? +
DeepSeek V3 is listed at $0.27/M input and $1.1/M output.
Q · 03 Is cached-input pricing included? +
Yes. Cached input is shown at $0.07/M.
Q · 04 What should teams compare it against? +
Use the shelf to compare nearby current models. Snapshot replacement:
deepseek-v4-flash.Q · 05 Why keep this page? +
These pages preserve live price checks, preview economics, and migration context in one consistent calculator format.