Provider
DeepSeek API pricing: every model compared
DeepSeek offers 11 models through its API in our data, priced from $0.259 to $0.9553 per million input tokens. The newest is DeepSeek V4.1 Flash, first listed on 2026-09-10.
- Models
- 11
- Cheapest input
- $0.259
- Priciest input
- $0.9553
- Largest context
- 1,048,576
- With caching
- 7 of 11
- Open weights
- all
Cheapest
DeepSeek V3.2DeepSeek$0.259 in · $0.42 outLargest context
DeepSeek V4 Flash Vision ExpDeepSeek1,048,576 tokensLine-up
Every DeepSeek model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $1.20 | 1,048,576 | 2026-09-10 |
| DeepSeek V4 Flash Vision Exp | $0.2156 | $0.6468 | 1,048,576 | 2026-08-21 |
| DeepSeek V4 Pro 0423 | $0.9553 | $1.9105 | 1,024,000 | 2026-04-24 |
| DeepSeek V3.2 | $0.259 | $0.42 | 163,840 | 2025-12-01 |
| DeepSeek V3.2 Exp | $0.27 | $0.41 | 163,840 | 2025-09-29 |
| DeepSeek V3.1 Terminus | $0.27 | $1 | 163,840 | 2025-09-22 |
| DeepSeek V3.1 | $0.25 | $0.95 | 163,840 | 2025-08-21 |
| R1 0528 | $0.50 | $2.15 | 163,840 | 2025-05-28 |
| DeepSeek V3 0324 | $0.29 | $1.14 | 128,000 | 2025-03-24 |
| R1 | $0.70 | $2.50 | 64,000 | 2025-01-20 |
| DeepSeek V3 | $0.2574 | $1.0287 | 128,000 | 2024-12-26 |
Prices in US dollars per 1M tokens, newest first. Release dates are when our source first listed the model.
Overview
DeepSeek’s pricing at a glance
The spread between DeepSeek’s cheapest and most expensive model is large: DeepSeek V4 Pro 0423 costs 4× more per input token than DeepSeek V3.2. Picking the smallest model that does the job well is usually the biggest saving available, ahead of any discount.
7 of 11 of the line-up has a cached-input price, which helps chatbots and agents that resend the same instructions. 1 of 11 can run through a batch API at a discount, for work that can wait up to a day. 2 of 11 accept images as input.
FAQ
DeepSeek API questions
How much does the DeepSeek API cost?
DeepSeek's 11 models range from $0.259 to $0.9553 per million input tokens, and output costs more than input on almost every model. The exact bill depends on your token volumes, which you can estimate in the LLM cost calculator.
What is DeepSeek's cheapest model?
By blended price (three parts input to one part output) it is DeepSeek V3.2, at $0.259 input and $0.42 output per million tokens. The most expensive is DeepSeek V4 Pro 0423.
Which DeepSeek model has the largest context window?
DeepSeek V4 Flash Vision Exp, with 1,048,576 tokens per request.
Does DeepSeek offer prompt caching or batch discounts?
In our data, 7 of 11 of DeepSeek's models have a published cached-input price and 1 of 11 have a published batch price. Both can cut costs substantially for repeated prompts or work that can wait.