# DeepSeek

Canonical: https://inetgeek.com/llm-apis/deepseek/

Hosted inference for the DeepSeek model family, priced per million tokens with peak and off-peak rates.

## Who it suits

Batch-shaped work that can run outside weekday mornings UTC, where off-peak halves an already low rate and a cache hit costs about 3% of a cache miss.

Consider something else if Capacity is expressed as concurrent requests rather than tokens per minute, which is a different thing to plan against, and the peak window lands on European working hours.

## What the documentation says

### Pricing

- Pricing model: Per million tokens, with every rate doubling at peak: off-peak is half price, and peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays. Cache hits are priced roughly 30x below cache misses. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)

### Inference

- Input price, top model: $1.32 per million input tokens for deepseek-v4-pro at peak on a cache miss, halving to $0.66 off-peak. A cache hit is $0.044 peak. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Output price, top model: $3.96 per million output tokens for deepseek-v4-pro at peak, $1.98 off-peak. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Input price, cheapest model: $0.44 per million input tokens for deepseek-v4-flash at peak on a cache miss, $0.22 off-peak, with output at $1.32 peak. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Context window: 1M tokens on every model in the current line. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Max output tokens: 384K tokens maximum. ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Prompt caching: Supported ([source](https://api-docs.deepseek.com/quick_start/pricing), read 2026-09-06)
- Rate limits: Concurrency rather than requests per minute: 500 concurrent requests on deepseek-v4-pro and 2,500 on deepseek-v4-flash, per account rather than per key. Exceeding it returns HTTP 429, and expansion is free on request. ([source](https://api-docs.deepseek.com/quick_start/rate_limit), read 2026-09-06)

## Compared with

- [DeepSeek vs Anthropic](https://inetgeek.com/compare/anthropic-vs-deepseek/)
- [DeepSeek vs OpenAI](https://inetgeek.com/compare/openai-vs-deepseek/)
- [DeepSeek vs Google Gemini API](https://inetgeek.com/compare/google-gemini-vs-deepseek/)