DeepSeek V4 Pro pricing calculator
DeepSeek's flagship API model with very cheap cache hits.
- Input
- $1.32 / 1M
- Cached input
- $0.044 / 1M
- Output
- $3.96 / 1M
- Context window
- 1M
- Batch API
- No
- Reasoning
- Yes
NotePeak price shown. DeepSeek offers 50% off during off-peak hours.
Workload
Quick presets
1,000 tokens ≈ 750 English words.
Pro / Agent mode
Caching, batch, multi-turn loops, reasoning tokens
Cost comparison
Cheapest / month
$87.46
Grok 4.3
Most expensive / month
$108.42
DeepSeek V4 Pro
Tokens / request
1.5K in
400 out (cheapest model)
| Remove | |||||
|---|---|---|---|---|---|
| Grok 4.3CheapestxAI · $1.25 / $2.50 | $0.00287 | $2.88 | $87.46 | $1,049 | |
| Claude Haiku 4.5Anthropic · $1.00 / $5.00 | $0.0035 | $3.50 | $106.47 | $1,278 | |
| GPT-6.1 TerraOpenAI · $1.00 / $5.00 | $0.0035 | $3.50 | $106.47 | $1,278 | |
| DeepSeek V4 ProDeepSeek · $1.32 / $3.96 | $0.00356 | $3.56 | $108.42 | $1,301 |
Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: DeepSeek ↗ · Anthropic ↗ · OpenAI ↗ · xAI ↗
What DeepSeek V4 Pro costs for common workloads
Monthly estimates using the presets above, at list price.
| Workload | Per request / session | Monthly | Yearly |
|---|---|---|---|
| Small Chatbot1K chats/day, short prompts | $0.00198 | $60.23 | $722.70 |
| RAG App5K queries/day, 4K-token retrieved context | $0.00482 | $733.49 | $8,801 |
| Coding Agent200 sessions/day × 25 turns | $0.4083 | $2,484 | $29,809 |
| Enterprise Scale250K requests/day, batched | $0.00408 | $31,019 | $372,191 |
Compare DeepSeek V4 Pro head-to-head
- DeepSeek V4 Pro vs Claude Fable 5.2
- DeepSeek V4 Pro vs Claude Opus 5.5
- DeepSeek V4 Pro vs Claude Sonnet 5.5
- DeepSeek V4 Pro vs Claude Haiku 5.5
- DeepSeek V4 Pro vs GPT-6.2 Astra
- DeepSeek V4 Pro vs GPT-6.2 Sol
- DeepSeek V4 Pro vs GPT-6 Luna
- DeepSeek V4 Pro vs Gemini 4 Neon
- DeepSeek V4 Pro vs Gemini 4 Carbon
- DeepSeek V4 Pro vs Gemini 3.8 Flash
- DeepSeek V4 Pro vs DeepSeek V4.1 Flash
- DeepSeek V4 Pro vs Grok 4.7
Official pricing ↗ (DeepSeek) · API model ID deepseek-v4-pro
DeepSeek V4 Pro pricing FAQ
How much does DeepSeek V4 Pro cost per 1M tokens?
DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. Cached input is $0.044 per 1M. Prices were last verified on Nov 21, 2026.
How much does one DeepSeek V4 Pro request cost?
A typical request with 1,000 input tokens and 500 output tokens costs about $0.0033. At 1,000 such requests per day that is $100.39 per month.
Does DeepSeek V4 Pro support prompt caching?
Yes. Cached input tokens cost $0.044 per 1M, 97% less than regular input. Turn on Pro mode above to model your cache hit rate.
Is there a Batch API discount for DeepSeek V4 Pro?
No 50% batch discount is listed for DeepSeek V4 Pro. DeepSeek offers off-peak discounts instead.
What is the context window of DeepSeek V4 Pro?
DeepSeek V4 Pro supports up to 1M tokens of context and up to 375K output tokens per response. Peak price shown. DeepSeek offers 50% off during off-peak hours.
Is DeepSeek V4 Pro cheaper than Claude Haiku 4.5?
For a 1,000-in / 500-out request, DeepSeek V4 Pro costs $0.0033 and Claude Haiku 4.5 costs $0.0035, so DeepSeek V4 Pro is 6% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.
More AI cost tools
LLM API & Agent Cost Calculator
Compare per-request, monthly and yearly cost across 30+ models, with caching, batch and multi-turn agent modelling.
Open calculator →GBGPU & VRAM Calculator
See exactly how much VRAM a model needs (weights + KV cache + overhead) and which GPUs or Macs it fits on.
Open calculator →$/minVoice Agent Cost Calculator
Cost per minute and per call for STT + LLM + TTS + telephony voice agent stacks.
Open calculator →break-evenAPI vs Self-Hosting Break-Even
Find the monthly token volume where renting a dedicated GPU beats paying per token.
Open calculator →