DeepSeek V4 Flash API pricing
Published on-demand rates for DeepSeek's deepseek-v4-flash, captured 2026-08-10 from public pricing data and committed to our archive. Context window 1M tokens; first observed in our archive 2026-06-22.
| Meter | USD per 1M tokens |
|---|---|
| Input | $0.140 |
| Output | $0.280 |
| Cached input | $0.003 |
Standard on-demand rates. Excludes batch endpoints and negotiated pricing; confirm on DeepSeek's pricing page before committing.
What it costs on a real workload
The four frozen profiles the LLMPrice indices price, per 1M tokens processed, at the rates above. Where no cache-read rate is published, the whole input bills at the standard rate.
| Profile | In / out mix | Cached share | Cost |
|---|---|---|---|
| Retrieval | 800k / 200k | 70% | $0.091 |
| Chat | 500k / 500k | 30% | $0.189 |
| Content | 200k / 800k | 20% | $0.247 |
| Agent | 900k / 100k | 85% | $0.049 |
Profile definitions are frozen and published on the methodology page. Compare every model on these profiles →
Observed rate history
No repricing observed since this model entered our archive on 2026-06-22. When a rate moves, the change appears here and on the sitewide ticker.
Priced near this one
The models closest to DeepSeek V4 Flash on a retrieval workload, cheaper and more expensive alike. We publish no quality score, so this is what they cost and nothing more.
| Model | Provider | Input | Output | vs DeepSeek V4 Flash |
|---|---|---|---|---|
| Gemini 2.0 Flash Lite | $0.075 | $0.300 | 3% less | |
| GPT 5 Nano | OpenAI | $0.050 | $0.400 | 4% more |
| Mistral Small 3.2 | Mistral | $0.060 | $0.180 | 8% less |
| Ministral 3 3B | Mistral | $0.100 | $0.100 | 10% more |
Compared on the retrieval profile: 800k input, 200k output, 70% of input cached where the model offers a cache rate.
No affiliate or referral arrangements: the console link carries no parameters and nothing on this page is paid placement. DeepSeek V4 Flash is a trademark of its owner; LLMPrice.io is independent and unaffiliated.