DeepSeek › DeepSeek V4.1 Flash 1017 › Pricing
DeepSeek V4.1 Flash 1017 pricing
API list price by DeepSeek · checked Oct 23, 2026
$0.30 / $1.20per 1M tokens in / out
$0.006cache read · −98%
$0.26per task at max?
#2on OpenRouter by tokens · 16.5T / week
Price sheetper 1M tokens
| Input | $0.30 | list |
| Output | $1.20 | |
| Cache read | $0.006 | −98% vs input |
| Context · max output | 1M · 384K | tokens |
Where to buy23 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Relace | $0.05 | $0.45 | 1M |
| DeepInfra | $0.06 | $0.18 | — |
| InferenceNet | $0.08 | $0.50 | 1M |
| Decart | $0.09 | $0.18 | 1M |
| DigitalOcean | $0.098 | $0.20 | 1M |
| Cloudflare | $0.10 | $0.60 | 1M |
| SiliconFlow | $0.13 | $0.28 | 1M |
| Morph | $0.14 | $0.60 | 1M |
| AtlasCloud | $0.14 | $0.28 | 1M |
| Baidu | $0.14 | $0.28 | 1M |
| Parasail | $0.14 | $0.28 | 1M |
| Alibaba | $0.15 | $0.30 | 1M |
| Wafer | $0.16 | $0.50 | 1M |
| Azure | $0.21 | $0.56 | 1M |
| Featherless | $0.23 | $0.90 | — |
| Crusoe | $0.29 | $1.20 | 1M |
| BaseTen | $0.30 | $1.20 | 1M |
| deepseeklab | $0.30 | $1.20 | — |
| Fireworks | $0.30 | $1.20 | 1M |
| GMICloud | $0.30 | $1.20 | 1M |
| Novita | $0.30 | $1.20 | — |
| PrimeIntellect | $0.30 | $1.20 | 1M |
| Together | $0.30 | $1.20 | 1M |
In DeepSeek's line-upper 1M in / out
| DeepSeek OCR | $0.03 / $0.10 | −91% |
| DeepSeek R1 Distill Llama 8B | $0.20 / $0.32 | −56% |
| DeepSeek R1 Distill Qwen 32B | $0.27 / $0.27 | −49% |
| DeepSeek V4.1 Flash 1017 | $0.30 / $1.20 | this model |
| DeepSeek R1 Distill Qwen 14B | $0.43 / $1.12 | +15% |
| R1 0528 | $0.39 / $1.63 | +32% |
| DeepSeek R1 Distill Qwen 7B | $0.68 / $0.80 | +35% |
Cheaper for the same workvs DeepSeek V4.1 Flash 1017 at max
| GPT-6.1 Sol medium | -18% | score +6% | $0.21 |
| MiMo v2.6 Pro thinkingOpen | -49% | score +3% | $0.13 |
| Claude Haiku 5.5 max | -19% | score -4% | $0.21 |
| MiniMax M3.1 Flash thinking | -16% | score -5% | $0.22 |
| GPT-6 Sol medium | -6% | score -12% | $0.25 |
Pricing questions
How much does DeepSeek V4.1 Flash 1017 cost?›
$0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.006. One Intelligence Index task costs about $0.26 at the default effort.
Is DeepSeek V4.1 Flash 1017 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 $0.006 per 1M, 98% below the input price.
Is DeepSeek V4.1 Flash 1017 cheaper than DeepSeek V4.1 Flash?›
It costs the same per token: $0.30 / $1.20.
What is a cheaper alternative to DeepSeek V4.1 Flash 1017?›
GPT-6.1 Sol at medium effort costs -18% per task with a score +6% on Humanity's Last Exam.