DeepSeek API pricing
Prices per million tokens for the 4 DeepSeek models we track, with context windows and what a typical task costs. The cheapest is DeepSeek V4 Flash 0731 at $0.042 input and $0.169 output per million tokens; the largest context window is DeepSeek V4 Flash 0731's 1.0M tokens. Updated 25 Oct 2026.
| Model | Input / 1M | Output / 1M | Context | Tools | Reasoning |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | $0.042 | $0.169 | 1.0M | Yes | Yes |
| DeepSeek V4.1 Flash 1017 | $0.150 | $0.600 | 1.0M | Yes | Yes |
| DeepSeek V4.1 Flash | $0.020 | $1.00 | 1.0M | Yes | Yes |
| DeepSeek V4 Pro 0813 | $0.660 | $1.98 | 1.0M | Yes | Yes |
What DeepSeek models cost per task
Using the listed prices, for three common jobs: a chat turn (2,000 tokens in, 500 out), summarising a 100,000-token document into 2,000 tokens, and a long agent run (1 million in, 50,000 out).
- DeepSeek V4 Flash 0731: chat turn $0.0002, document $0.0046, agent run $0.051
- DeepSeek V4.1 Flash 1017: chat turn $0.0006, document $0.016, agent run $0.180
- DeepSeek V4.1 Flash: chat turn $0.0005, document $0.0040, agent run $0.070
- DeepSeek V4 Pro 0813: chat turn $0.0023, document $0.070, agent run $0.759
How DeepSeek compares with other providers
Across all 40 models we track, the cheapest DeepSeek model ranks #1 by output price. For a model-by-model comparison, see the full price table or the guide to choosing an LLM.
Other providers: Anthropic pricing · OpenAI pricing · Google pricing · Meta pricing · Mistral AI pricing · Qwen (Alibaba) pricing · xAI pricing · Moonshot AI pricing · Z.ai pricing
Prices and limits come from OpenRouter's public model catalogue, last synced 25 Oct 2026. DeepSeek's own API pricing can differ and changes often; confirm on its pricing page before you commit.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.