Pricingby IbisDeepSeek V4.1 Flash 1017
DeepSeek · Open weights · 1M context · released Oct 17, 2026 · checked 8h ago
Ways to buy 24
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Decart fp4, cheapest · cached $0.018 | $0.09 | $0.18 | $0.09 / $0.18-57% vs list | $0.018 | -57% vs list |
fp8-flex, fp8 · cached $0.0024 | $0.078 | $0.235 | $0.078 / $0.235-55% vs list | $0.0024 | -55% vs list |
fp8 · cached $0.0029 | $0.098 | $0.294 | $0.098 / $0.294-44% vs list | $0.0029 | -44% vs list |
| InferenceNet fp8 · cached $0.008 | $0.08 | $0.5 | $0.08 / $0.5-30% vs list | $0.008 | -30% vs list |
| InferenceNet us, fp8 · cached $0.008 | $0.08 | $0.5 | $0.08 / $0.5-30% vs list | $0.008 | -30% vs list |
| Relace Default region · cached $0.008 | $0.05 | $0.6 | $0.05 / $0.6-29% vs list | $0.008 | -29% vs list |
| Morph fp8 · cached $0.007 | $0.08 | $0.6 | $0.08 / $0.6-20% vs list | $0.007 | -20% vs list |
fp8-priority, fp8 · cached $0.0044 | $0.147 | $0.441 | $0.147 / $0.441-16% vs list | $0.0044 | -16% vs list |
Default region · cached $0.003 | $0.1 | $0.6 | $0.1 / $0.6-14% vs list | $0.003 | -14% vs list |
| Wafer mxfp4 · cached $0.003 | $0.16 | $0.5 | $0.16 / $0.5-7% vs list | $0.003 | -7% vs list |
The lab's own API · cached $0.003 | $0.15 | $0.6 | $0.15 / $0.6List price | $0.003 | List price |
| Reka Default region · cached $0.003 | $0.15 | $0.6 | $0.15 / $0.6Same as list | $0.003 | Same as list |
fp8 · cached $0.007 | $0.29 | $1.2 | $0.29 / $1.2+97% vs list | $0.007 | +97% vs list |
| AtlasCloud fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
Default region · cached $0.007 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.007 | +100% vs list |
Default region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| GMICloud fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| Phala Default region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
| PrimeIntellect Default region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
fp8 · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
Default region · cached $0.006 | $0.3 | $1.2 | $0.3 / $1.2+100% vs list | $0.006 | +100% vs list |
Default region · cached $0.033 | $0.33 | $1.32 | $0.33 / $1.32+120% vs list | $0.033 | +120% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $27.00 direct.
Kong AI Gateway$27.00+0%
LiteLLM$27.00+0%
Vercel AI Gateway$27.00+0%
Requesty$28.35+5%
Eden AI$28.48+5.5%
OpenRouter$28.48+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Martian GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Portkey.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · |
DeepSeek · 1M | $0.216 | $0.647 | $0.216 / $0.647 | $0.323 | 1M | on DeepInfra (fp8) | · |
DeepSeek · 1MCheapest: $0.329 on Baidu (fp8) | $0.66 | $1.98 | $0.66 / $1.98 | $0.99 | 1M | $0.329 on Baidu (fp8) | · |
DeepSeek · 1M | $0.044 | $0.132 | $0.044 / $0.132 | $0.066 | 1M | on StreamLake (fp8) | · |
Z.ai · 1M | $0.35 | $1.1 | $0.35 / $1.1 | $0.538 | 1M | on Baidu (fp8) | · |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · |
NVIDIA · 1M | $0.1 | $0.4 | $0.1 / $0.4 | $0.175 | 1M | on Crusoe (bf16) | · |
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
About DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name.
Takes text, image in and returns text. First listed Oct 18, 2026. Up to 393K output tokens. Blended price $0.262 per 1M tokens at 3 input to 1 output. Overall score 3 on leadersboard.fru.dev (rank 29). Model id deepseek-v4-1-flash-1017.
Price history
List price since Oct 18, 2026, from daily reads of the OpenRouter catalog.
DeepSeek V4.1 Flash 1017
Input $0.2 to $0.16, Output $0.8 to $0.5, on wafer/mxfp4
Input $0.059 to $0.08, on morph/fp8
Questions
How much does DeepSeek V4.1 Flash 1017 cost?
$0.15 per million input tokens and $0.6 per million output tokens, with cached input at $0.003.
What is the context window of DeepSeek V4.1 Flash 1017?
1M tokens, with up to 393K tokens of output.
Where is DeepSeek V4.1 Flash 1017 cheapest?
Of 24 routes tracked, Decart is cheapest at $0.09 input and $0.18 output per million tokens.
Has DeepSeek V4.1 Flash 1017's price changed?
Yes. The output price went from $0.8 to $0.5, first seen Oct 20, 2026.