DeepSeek › DeepSeek V4 Flash 0731 › Pricing
DeepSeek V4 Flash 0731 pricing
API list price by DeepSeek · checked Oct 26, 2026
$0.14 / $0.28per 1M tokens in / out
$0.023cache read · −84%
$0.15per task at max?
Price sheetper 1M tokens
| Input | $0.14 | list |
| Output | $0.28 | |
| Cache read | $0.023 | −84% vs input |
| Context | 1M | tokens |
Saved AA secondary quote for this exact release; not a refreshed first-party tariff.
In DeepSeek's line-upper 1M in / out
| DeepSeek OCR 2 | $0.03 / $0.03 | −83% |
| DeepSeek OCR | $0.03 / $0.10 | −73% |
| DeepSeek R1 Distill Llama 8B | $0.20 / $0.32 | +31% |
| DeepSeek R1 Distill Qwen 32B | $0.27 / $0.27 | +54% |
| DeepSeek V4.1 Flash 1017 | $0.30 / $1.20 | 3× |
| DeepSeek R1 Distill Qwen 14B | $0.43 / $1.12 | 3.4× |
| R1 0528 | $0.39 / $1.63 | 4× |
Cheaper for the same workvs DeepSeek V4 Flash 0731 at max
| MiMo v2.6 Pro thinkingOpen | -11% | score +35% | $0.13 |
| GPT-6.1 Terra high | -10% | score +28% | $0.13 |
| GPT-6.1 Sol low | -13% | score +23% | $0.13 |
| Claude Haiku 5.5 xhigh | -17% | score +20% | $0.12 |
| GPT-6 Luna max | -55% | score +11% | $0.068 |
Pricing questions
How much does DeepSeek V4 Flash 0731 cost?›
$0.14 per 1M input tokens and $0.28 per 1M output tokens. Cached input is $0.023. One Intelligence Index task costs about $0.15 at the default effort.
Is DeepSeek V4 Flash 0731 free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.023 per 1M, 84% below the input price.
Is DeepSeek V4 Flash 0731 cheaper than DeepSeek V4 Flash 0420?›
No: $0.14 / $0.28 against $0.094 / $0.19, 49% more per token.
What is a cheaper alternative to DeepSeek V4 Flash 0731?›
MiMo v2.6 Pro at thinking effort costs -11% per task with a score +35% on .