DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017
- context
- 1.05M
- modalities
- text, image → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Long context, Low cost
Overview
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. V4.1 Flash is a sparse mixture-of-experts model...
Providers
- AlibabaView Alibaba
- AtlasCloudView AtlasCloud
- BaiduView Baidu
- BaseTenView BaseTen
- CloudflareView Cloudflare
- CohereView Cohere
- CrusoeView Crusoe
- DecartView Decart
- DeepInfraView DeepInfra
- DeepSeekView DeepSeek
- DigitalOceanView DigitalOcean
- FireworksView Fireworks
- GMICloudView GMICloud
- InferenceNetView InferenceNet
- IonstreamView Ionstream
- MakoraView Makora
- MistralView Mistral
- ModalView Modal
- ModelRunView ModelRun
- MorphView Morph
- Near AIView Near AI
- NebiusView Nebius
- NovitaView Novita
- OpenInferenceView OpenInference
- ParasailView Parasail
- Particle AIView Particle AI
- PhalaView Phala
- PrimeIntellectView PrimeIntellect
- RekaView Reka
- RelaceView Relace
- Sail ResearchView Sail Research
- SiliconFlowView SiliconFlow
- StepFunView StepFun
- StreamLakeView StreamLake
- TogetherView Together
- VeniceView Venice
- WaferView Wafer
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.33 | $1.32 |
| AtlasCloud | $0.195 | $0.78 |
| Baidu | $0.28 | $1.13 |
| BaseTen | $0.30 | $1.20 |
| Cloudflare | $0.10 | $0.60 |
| Cohere | $0.195 | $0.66 |
| Crusoe | $0.29 | $1.20 |
| Decart | $0.123 | $0.492 |
| DeepInfradeepinfra/fp8 · fp8 | $0.098 | $0.294 |
| DeepInfradeepinfra/fp8/flex · fp8 | $0.0784 | $0.2352 |
| DeepInfradeepinfra/fp8/priority · fp8 | $0.147 | $0.441 |
| DeepSeek | $0.30 | $1.20 |
| DigitalOcean | $0.18 | $0.72 |
| Fireworksfireworks | $0.30 | $1.20 |
| Fireworksfireworks/spot | $0.21 | $0.84 |
| Fireworksfireworks/us | $0.45 | $1.80 |
| GMICloud | $0.30 | $1.20 |
| InferenceNetinference-net/fp8 · fp8 | $0.08 | $0.55 |
| InferenceNetinference-net/us · fp8 | $0.08 | $0.55 |
| Ionstream | $0.165 | $0.495 |
| Makora | $0.15 | $1.20 |
| Mistral | $0.30 | $1.20 |
| Modal | $0.25 | $1.00 |
| ModelRun | $0.17 | $0.67 |
| Morph | $0.05 | $0.192 |
| Near AI | $0.30 | $1.20 |
| Nebius | $0.30 | $1.20 |
| Novita | $0.195 | $0.78 |
| OpenInference | $0.035 | $0.50 |
| Parasail | $0.30 | $1.20 |
| Particle AI | $0.05 | $0.50 |
| Phala | $0.20 | $1.20 |
| PrimeIntellect | $0.24 | $1.20 |
| Reka | $0.06 | $0.60 |
| Relacerelace | $0.07 | $0.50 |
| Relacerelace/fast · fp4 | $0.30 | $0.90 |
| Relacerelace/fp4 · fp4 | $0.035 | $0.50 |
| Sail Researchsail-research/fp4 · fp4 | $0.101 | $0.15 |
| Sail Researchsail-research/fp4/us · fp4 | $0.101 | $0.15 |
| SiliconFlow | $0.30 | $1.20 |
| StepFun | $0.195 | $0.78 |
| StreamLake | $0.15 | $0.60 |
| Together | $0.30 | $1.20 |
| Venice | $0.30 | $1.20 |
| Waferwafer/mxfp4 · mxfp4 | $0.13 | $0.50 |
| Waferwafer/us · mxfp4 | $0.038 | $0.50 |
Alibaba
- input / 1M
- $0.33
- output / 1M
- $1.32
AtlasCloud
- input / 1M
- $0.195
- output / 1M
- $0.78
Baidu
- input / 1M
- $0.28
- output / 1M
- $1.13
BaseTen
- input / 1M
- $0.30
- output / 1M
- $1.20
Cloudflare
- input / 1M
- $0.10
- output / 1M
- $0.60
Cohere
- input / 1M
- $0.195
- output / 1M
- $0.66
Crusoe
- input / 1M
- $0.29
- output / 1M
- $1.20
Decart
- input / 1M
- $0.123
- output / 1M
- $0.492
DeepInfra
deepinfra/fp8 · fp8
- input / 1M
- $0.098
- output / 1M
- $0.294
DeepInfra
deepinfra/fp8/flex · fp8
- input / 1M
- $0.0784
- output / 1M
- $0.2352
DeepInfra
deepinfra/fp8/priority · fp8
- input / 1M
- $0.147
- output / 1M
- $0.441
DeepSeek
- input / 1M
- $0.30
- output / 1M
- $1.20
DigitalOcean
- input / 1M
- $0.18
- output / 1M
- $0.72
Fireworks
fireworks
- input / 1M
- $0.30
- output / 1M
- $1.20
Fireworks
fireworks/spot
- input / 1M
- $0.21
- output / 1M
- $0.84
Fireworks
fireworks/us
- input / 1M
- $0.45
- output / 1M
- $1.80
GMICloud
- input / 1M
- $0.30
- output / 1M
- $1.20
InferenceNet
inference-net/fp8 · fp8
- input / 1M
- $0.08
- output / 1M
- $0.55
InferenceNet
inference-net/us · fp8
- input / 1M
- $0.08
- output / 1M
- $0.55
Ionstream
- input / 1M
- $0.165
- output / 1M
- $0.495
Makora
- input / 1M
- $0.15
- output / 1M
- $1.20
Mistral
- input / 1M
- $0.30
- output / 1M
- $1.20
Modal
- input / 1M
- $0.25
- output / 1M
- $1.00
ModelRun
- input / 1M
- $0.17
- output / 1M
- $0.67
Morph
- input / 1M
- $0.05
- output / 1M
- $0.192
Near AI
- input / 1M
- $0.30
- output / 1M
- $1.20
Nebius
- input / 1M
- $0.30
- output / 1M
- $1.20
Novita
- input / 1M
- $0.195
- output / 1M
- $0.78
OpenInference
- input / 1M
- $0.035
- output / 1M
- $0.50
Parasail
- input / 1M
- $0.30
- output / 1M
- $1.20
Particle AI
- input / 1M
- $0.05
- output / 1M
- $0.50
Phala
- input / 1M
- $0.20
- output / 1M
- $1.20
PrimeIntellect
- input / 1M
- $0.24
- output / 1M
- $1.20
Reka
- input / 1M
- $0.06
- output / 1M
- $0.60
Relace
relace
- input / 1M
- $0.07
- output / 1M
- $0.50
Relace
relace/fast · fp4
- input / 1M
- $0.30
- output / 1M
- $0.90
Relace
relace/fp4 · fp4
- input / 1M
- $0.035
- output / 1M
- $0.50
Sail Research
sail-research/fp4 · fp4
- input / 1M
- $0.101
- output / 1M
- $0.15
Sail Research
sail-research/fp4/us · fp4
- input / 1M
- $0.101
- output / 1M
- $0.15
SiliconFlow
- input / 1M
- $0.30
- output / 1M
- $1.20
StepFun
- input / 1M
- $0.195
- output / 1M
- $0.78
StreamLake
- input / 1M
- $0.15
- output / 1M
- $0.60
Together
- input / 1M
- $0.30
- output / 1M
- $1.20
Venice
- input / 1M
- $0.30
- output / 1M
- $1.20
Wafer
wafer/mxfp4 · mxfp4
- input / 1M
- $0.13
- output / 1M
- $0.50
Wafer
wafer/us · mxfp4
- input / 1M
- $0.038
- output / 1M
- $0.50
Use this model
through Nautili
Route requests to DeepSeek V4.1 Flash 1017 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.