DeepSeek: DeepSeek V4.1 Flash 1017

deepseek/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.

Modalities
In / out per 1M$0.30 / $1.20
Context1M
ReleasedOct 17, 2026

Providers

17 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Relace$0.05$0.15$0.011.02s110 tps100%
Morphfp8$0.05$0.60$0.010.63s90 tps100%
inference.netfp8$0.08$0.50$0.010.45s191 tps100%
DeepSeek$0.15$0.60$0.001.10s99 tps100%
Crusoefp8$0.29$1.20$0.010.94s114 tps100%
AtlasCloudfp8$0.30$1.20$0.030.98s105 tps100%
Together$0.30$1.20$0.010.35s218 tps100%
Fireworks$0.30$1.20$0.011.27s144 tps100%
Baseten$0.30$1.20$0.010.45s289 tps100%
Parasailfp8$0.30$1.20$0.010.87s114 tps100%
Prime Intellect$0.30$1.20$0.011.32s137 tps99.84%
Wafermxfp4$0.10$0.50$0.001.05s101 tps99.81%
Cloudflare$0.10$0.60$0.001.19s86 tps99.47%
DeepInfraus · fp8$0.10$0.29$0.001.20s68 tps99.42%
DeepInfraus · fp8$0.15$0.44$0.001.44s67 tps99.19%
DeepInfraus · fp8$0.08$0.24$0.006.74s34 tps98.46%
Alibaba Cloud Int.$0.33$1.32$0.031.35s79 tps96.33%

Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4.1 Flash 1017 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what DeepSeek V4.1 Flash 1017 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
DeepSeek V4.1 Flash 1017 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s20.0s40.0s60.0s80.0s
Oct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepSeek inference.net DeepInfra (us) DeepInfra (us) DeepInfra (us) Cloudflare Parasail Morph Baseten Relace Fireworks Prime Intellect Wafer Crusoe Together Alibaba Cloud Int. AtlasCloud
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepSeek inference.net DeepInfra (us) DeepInfra (us) DeepInfra (us) Cloudflare Parasail Morph Baseten Relace Fireworks Prime Intellect Wafer Crusoe Together Alibaba Cloud Int.

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.93%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.94%
100% 98% 97% 95%
Oct 18, 11:00 AMNow

Apps

Tools that most often run DeepSeek V4.1 Flash 1017, by tokens this week.

Activity

5116.2B tokens processed market-wide in the last month.

01000.0B2000.0B3000.0B4000.0B
Oct 17Oct 18Oct 19
Tokens

FAQ

Which model id do I use for DeepSeek V4.1 Flash 1017?
deepseek/deepseek-v4.1-flash-1017. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V4.1 Flash 1017 hold?
1,048,576 tokens per request, of which up to 393,216 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does DeepSeek V4.1 Flash 1017 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.30 per 1M input tokens and $1.20 per 1M output tokens.
Who built DeepSeek V4.1 Flash 1017?
DeepSeek, in the DeepSeek family.

Explore

Other models your pass can call.