DeepSeek V4.1 Flash 1017 — provider prices

45 providers offer this model. Cheapest input is $0.025, priciest is $0.450 — a 18.0x spread.

Providers
45
Cheapest
$0.025
Priciest
$0.450
Spread
18.0x

All quotes, cheapest first

ProviderInputOutput ContextQuantization
Particle AI$0.025$0.2501049Knot disclosed
Morph$0.035$0.3151049KFP8 — good balance
Relace$0.035$0.5001049KFP4 — lowest precision, expect quality loss
Wafer$0.038$0.5001049Kmxfp4
OpenInference$0.038$0.5001049KFP4 — lowest precision, expect quality loss
Particle AI$0.050$0.5001049Knot disclosed
DeepInfra$0.078$0.2351049KFP8 — good balance
InferenceNet$0.080$0.5501040KFP8 — good balance
InferenceNet$0.080$0.5501040KFP8 — good balance
DeepInfra$0.098$0.2941049KFP8 — good balance
Cloudflare$0.100$0.6001049Knot disclosed
Sail Research$0.101$0.1501049KFP4 — lowest precision, expect quality loss
Sail Research$0.101$0.1501049KFP4 — lowest precision, expect quality loss
Decart$0.123$0.4921049KFP4 — lowest precision, expect quality loss
StreamLake$0.144$0.5761024KFP8 — good balance
DeepInfra$0.147$0.4411049KFP8 — good balance
Baidu$0.150$0.6051049KFP8 — good balance
StepFun$0.150$0.6001000KFP8 — good balance
DeepSeek$0.150$0.6001049Knot disclosed
PrimeIntellect$0.156$1.201049Knot disclosed
Wafer$0.160$0.5001049Kmxfp4
Reka$0.160$1.101049Knot disclosed
Ionstream$0.165$0.4951049Knot disclosed
Alibaba$0.165$0.6601000Knot disclosed
ModelRun$0.170$0.6701049KFP4 — lowest precision, expect quality loss
DigitalOcean$0.180$0.7201049Knot disclosed
GMICloud$0.180$0.7201049KFP8 — good balance
Cohere$0.195$0.6601049Knot disclosed
AtlasCloud$0.195$0.7801049KFP8 — good balance
Novita$0.195$0.7801049KFP8 — good balance
Phala$0.200$1.201049Knot disclosed
Fireworks$0.210$0.8401049Knot disclosed
Modal$0.250$1.001049Knot disclosed
Crusoe$0.290$1.201049KFP8 — good balance
Relace$0.300$0.9001049KFP4 — lowest precision, expect quality loss
Near AI$0.300$1.201049Knot disclosed
Venice$0.300$1.201000KFP8 — good balance
Mistral$0.300$1.201049KFP8 — good balance
Nebius$0.300$1.201049KFP8 — good balance
SiliconFlow$0.300$1.201049KFP8 — good balance
Together$0.300$1.201049Knot disclosed
Fireworks$0.300$1.201049Knot disclosed
BaseTen$0.300$1.201049Knot disclosed
Parasail$0.300$1.201049KFP8 — good balance
Fireworks$0.450$1.801049Knot disclosed

USD per million tokens. Verified 2026-11-04. Source: OpenRouter public API.

Cheapest is Particle AI at $0.025 input. Check the quantization column before switching: undisclosed or FP4 quotes can produce noticeably worse output on reasoning and code tasks.

Related

All DeepSeek models · Price ranges · Cost calculator · Official pricing