Skip to content

Listings

All listings for DeepSeek V4 Flash 0731

Every priced listing we track for this model. Back to DeepSeek V4 Flash 0731

ProviderMax Input TokensInput $/1MOutput $/1MTok/sLatency
 Microsoft Azureazure_ai/DeepSeek-V4-Flash-0731Source: LiteLLM data
Data from LiteLLM
1M$0.44cache read $0.014$1.32——
 Aihubmixdeepseek-v4-flash-0731Source: AIHubMix data docs
Data from AIHubMix
1M$0.142cache read $0.0284$0.284——
 Aihubmixdeepseek-v4-flash-0731-fast · fastSource: AIHubMix data docs
Data from AIHubMix
1M$0.28cache read $0.07$1.40——
 Atlasclouddeepseek-ai/deepseek-v4-flash-0731 · fp4Source: AtlasCloud data
Data from AtlasCloud
1M$0.44cache read $0.028$1.32——
 Cortecs AIdeepseek-v4-flash-0731Sources: Cortecs EU Router data, Models.dev data
Data from Cortecs EU Router
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M
€0.074cache read €0.054
≈ $0.0812 USD (compared by USD value)
€0.371
≈ $0.4071 USD (compared by USD value)
——
 Eden AIInference by DeepInfradeepinfra/deepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.06cache read $0.015$0.18——
 Eden AIInference by Flexaiflexai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.13cache read $0.0195$0.26——
 Eden AIInference by FlexaiRegions: 🇪🇺 euflexai/DeepSeek-V4-Flash-0731@euSource: Models.dev data
Data from Models.dev
1M$0.13cache read $0.0195$0.26——
 Eden AIInference by Alibaba Cloudqwen/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.22cache read $0.022$0.66——
 Eden AIInference by Tensorxtensorx/deepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.25cache read $0.0625$0.30——
 Eden AIInference by Sferencesference/deepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.28cache read $0.07$0.56——
 Eden AIInference by Scalewayscaleway/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
256K$0.4396cache read $0.0879$0.8792——
 Eurouterdeepseek-v4-flash-0731Source: EURouter data
Data from EURouter
1M
€0.10cache read €0.02
≈ $0.1097 USD (compared by USD value)
€0.25
≈ $0.2743 USD (compared by USD value)
——
 Flowdotdeepseek-ai/DeepSeek-V4-Flash-0731Source: FlowDot data
Data from FlowDot
1M$0.06$0.18——
 Hugging FaceInference by Waferdeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.0443$0.30——
 Hugging FaceInference by DeepInfradeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.06$0.18——
 Hugging FaceInference by Relacedeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.07$0.14——
 Hugging FaceInference by Coheredeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.11$0.22——
 Hugging FaceInference by Digitaloceandeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.119$0.238——
 Hugging FaceInference by Basetendeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.13$0.26——
 Hugging FaceInference by Coreweavedeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.13$0.27——
 Hugging FaceInference by Inceptrondeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.13$0.495——
 Hugging FaceInference by Venicedeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.13$0.26——
 Hugging Facedeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.14$0.28——
 Hugging FaceInference by Nebius AI Studiodeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.14$0.28——
 Hugging FaceInference by Parasaildeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.14$0.28——
 Hugging FaceInference by Mancerdeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.15$0.50——
 Hugging FaceInference by Sail Researchdeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.15$0.30——
 Hugging FaceInference by Novita AIdeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.44$1.32——
 Hugging FaceInference by Primeintellectdeepseek-ai/DeepSeek-V4-Flash-0731Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.44$1.32——
 Kilodeepseek/deepseek-v4-flash-0731Sources: Kilo AI Gateway data, Models.dev data
Data from Kilo AI Gateway
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.0443cache read $0.035$0.30——
 LlmgatewayInference by DeepInfradeepseek-ai/DeepSeek-V4-Flash-0731Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.08cache read $0.016$0.18——
 Llmgatewaydeepseek-v4-flash-0731Source: LLMGateway data
Data from LLMGateway
1.1M$0.08cache read $0.016$0.18——
 LlmgatewayInference by Novita AIdeepseek/deepseek-v4-flash-0731Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.14cache read $0.028$0.28——
 LlmgatewayInference by Alibaba Clouddeepseek-v4-flash-0731Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.44cache read $0.044$1.32——
 LlmgatewayInference by Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4-flash-0731Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.44cache read $0.014$1.32——
 Meganovadeepseek-ai/DeepSeek-V4-Flash-0731Source: MegaNova data
Data from MegaNova
1M$0.09$0.18——
 Meliousdeepseek-v4-flash-0731Sources: Melious API data, Models.dev data
Data from Melious API
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, cache-read price, currency, currency basis, last updated, billing currency, converted
1M$0.1115cache read $0.0223$0.2788——
 NanoGPTdeepseek/deepseek-v4-flash-0731Sources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.044cache read $0.0014$0.132——
 NanoGPTdeepseek/deepseek-v4-flash-0731:thinking · thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.044cache read $0.0014$0.132——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by BaiduRegions: 🇨🇳 CNdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0462cache read $0.0015$0.1386246.11,998ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by BaiduRegions: 🇨🇳 CNdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0462cache read $0.0015$0.1386246.11,998ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by EngyRegions: GLBdeepseek/deepseek-v4-flash-0731Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0473cache read $0.0095$0.0945181.51,462ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by EngyRegions: GLBdeepseek/deepseek-v4-flash-0731:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.0473cache read $0.0095$0.0945181.51,462ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by HyperfusionRegions: 🇦🇪 AEdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0525$0.168——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by HyperfusionRegions: 🇦🇪 AEdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0525$0.168——
 NanoGPT
logs training unknown, per NanoGPT
Data privacy: logs_training_unknown · retains prompts Source: NanoGPT
policy notes
privacy: logs_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by GonkaaiRegions: GLBdeepseek/deepseek-v4-flash-0731Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0536$0.1092——
 NanoGPT
logs training unknown, per NanoGPT
Data privacy: logs_training_unknown · retains prompts Source: NanoGPT
policy notes
privacy: logs_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by GonkaaiRegions: GLBdeepseek/deepseek-v4-flash-0731:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.0536$0.1092——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.063cache read $0.0158$0.189165.71,492ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.063cache read $0.0158$0.189205.21,984ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by RelaceRegions: UNKdeepseek/deepseek-v4-flash-0731 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0735cache read $0.0147$0.147——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by RelaceRegions: UNKdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0735cache read $0.0147$0.147——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0924cache read $0.0029$0.2772129.71,833ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0924cache read $0.0029$0.2772129.71,833ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by MunitoRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731 · mxfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1155cache read $0.0231$0.294198.5868ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by MunitoRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731:thinking · thinking · mxfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1155cache read $0.0231$0.294133.9527ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0294$0.273332.31,280ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0294$0.273332.31,280ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0525$0.2835—440ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0525$0.2835—440ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by InceptronRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0284$0.5198——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by InceptronRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0284$0.5198——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0294$0.273——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.0294$0.273——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by WaferRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · nvfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.1313$0.241582.7988ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by WaferRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · nvfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365cache read $0.1313$0.241582.7988ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by ParasailRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0525$0.294178.92,109ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by ParasailRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0525$0.294178.92,109ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Mancerdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0525$0.525——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Mancerdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0525$0.525——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBdeepseek/deepseek-v4-flash-0731 · standard · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0441$0.315——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBdeepseek/deepseek-v4-flash-0731:thinking · standard, thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0441$0.315——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by TensorixRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0394$0.315——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by TensorixRegions: 🇪🇺 EUdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.0394$0.315——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBdeepseek/deepseek-v4-flash-0731 · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1739$0.4752——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBdeepseek/deepseek-v4-flash-0731:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1739$0.4752——
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.231cache read $0.0294$0.693——
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.231cache read $0.0294$0.693——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by RunanywhereRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3077cache read $0.0098$0.924——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by RunanywhereRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3077cache read $0.0098$0.924——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGdeepseek/deepseek-v4-flash-0731Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3696cache read $0.037$1.1088——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGdeepseek/deepseek-v4-flash-0731:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.3696cache read $0.037$1.1088169.51,920ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.4389cache read $0.0279$1.316759.54,982ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.4389cache read $0.0279$1.316759.54,982ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by ChutesRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0462$1.386——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by ChutesRegions: 🇺🇸 USdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0462$1.386——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by OllamaRegions: UNKdeepseek/deepseek-v4-flash-0731Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0147$1.386——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by OllamaRegions: UNKdeepseek/deepseek-v4-flash-0731:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0147$1.386——
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by PrimeintellectRegions: UNKdeepseek/deepseek-v4-flash-0731 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0147$1.386——
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by PrimeintellectRegions: UNKdeepseek/deepseek-v4-flash-0731:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.462cache read $0.0147$1.386——
 Nous Portaldeepseek/deepseek-v4-flash-0731:batch · batchSource: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
1M$0.048cache read $0.012$0.144——
 Nous Portaldeepseek/deepseek-v4-flash-0731Source: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
1M$0.054cache read $0.0135$0.162——
 OpenRouterInference by Baidudeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.044cache read $0.0014$0.132103713ms
 OpenRouterdeepseek/deepseek-v4-flash-0731Sources: Models.dev data, OpenRouter data docs
Data from OpenRouter
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.0443cache read $0.035$0.30——
 OpenRouterInference by Waferdeepseek/deepseek-v4-flash-0731 · us · nvfp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.0443cache read $0.035$0.30133314ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v4-flash-0731:batch · batch, fp8 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.048cache read $0.012$0.144——
 OpenRouterInference by DeepInfradeepseek/deepseek-v4-flash-0731 · fp8/flex · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.048cache read $0.012$0.144115.51,588ms
 OpenRouterdeepseek/deepseek-v4-flash-0731:batch · batchSource: OpenRouter data docs
Data from OpenRouter
1M$0.048cache read $0.012$0.144——
 OpenRouterInference by DeepInfradeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.06cache read $0.015$0.1878349ms
 OpenRouterInference by Relacedeepseek/deepseek-v4-flash-0731 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.07cache read $0.014$0.14139558ms
 OpenRouterInference by Streamlakedeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.088cache read $0.0028$0.264671,251ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v4-flash-0731 · fp8/priority · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.09cache read $0.0225$0.27141334ms
 OpenRouterInference by Coheredeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.11cache read $0.05$0.22178518ms
 OpenRouterInference by Digitaloceandeepseek/deepseek-v4-flash-0731Source: OpenRouter data docs
Data from OpenRouter
1M$0.119cache read $0.0238$0.238188713ms
 OpenRouterInference by Basetendeepseek/deepseek-v4-flash-0731 · fp32Source: OpenRouter data docs
Data from OpenRouter
1M$0.13cache read $0.028$0.26133314.5ms
 OpenRouterInference by Basetendeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.13cache read $0.028$0.26187371ms
 OpenRouterInference by Coreweavedeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.13cache read $0.05$0.27127426ms
 OpenRouterInference by Inceptrondeepseek/deepseek-v4-flash-0731 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.13cache read $0.027$0.495150460ms
 OpenRouterInference by Venicedeepseek/deepseek-v4-flash-0731Source: OpenRouter data docs
Data from OpenRouter
1M$0.13cache read $0.028$0.26156646ms
 OpenRouterInference by Waferdeepseek/deepseek-v4-flash-0731 · fast · nvfp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.13cache read $0.125$0.23144423ms
 OpenRouterInference by Nebius AI Studiodeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.14cache read $0.01$0.28196807ms
 OpenRouterInference by Parasaildeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.14cache read $0.05$0.2899457ms
 OpenRouterInference by Mancer 2deepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.15cache read $0.05$0.501151,267ms
 OpenRouterInference by Sail Researchdeepseek/deepseek-v4-flash-0731 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.15cache read $0.042$0.3042398ms
 OpenRouterInference by Sail Researchdeepseek/deepseek-v4-flash-0731 · us · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.15cache read $0.042$0.30531,147ms
 OpenRouterInference by SiliconFlowdeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.22cache read $0.028$0.6659.5863.5ms
 OpenRouterInference by Alibaba Clouddeepseek/deepseek-v4-flash-0731Source: OpenRouter data docs
Data from OpenRouter
1M$0.352cache read $0.0352$1.0561371,524ms
 OpenRouterInference by Alibaba Clouddeepseek/deepseek-v4-flash-0731 · us-east-1Source: OpenRouter data docs
Data from OpenRouter
1M$0.374cache read $0.0374$1.1221361,485ms
 OpenRouterInference by Novita AIdeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.418cache read $0.0266$1.25435863ms
 OpenRouterInference by Chutesdeepseek/deepseek-v4-flash-0731 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.44cache read $0.044$1.32871,264ms
 OpenRouterInference by Primeintellectdeepseek/deepseek-v4-flash-0731 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.44cache read $0.014$1.32191671ms
 Redpill
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek/deepseek-v4-flash-0731Source: RedPill data
Data from RedPill
1M$0.44$1.32——
 RequestyInference by DeepInfradeepinfra/deepseek-v4-flash-0731Source: Requesty data
Data from Requesty
1M$0.09cache read $0.018$0.18——
 RequestyInference by Novita AInovita/deepseek/deepseek-v4-flash-0731Source: Requesty data
Data from Requesty
1M$0.14cache read $0.028$0.28——
 RequestyInference by Tensorxtensorx/deepseek-v4-flash-0731Source: Requesty data
Data from Requesty
1M$0.25cache read $0.06$0.30——
 RequestyInference by Sferencesference/deepseek-v4-flash-0731Source: Requesty data
Data from Requesty
1M$0.28cache read $0.07$0.56——
 Thalamdeepseek-v4-flash-0731Source: Thalam Pricing
Data from Thalam Pricing
Not published by the provider$0.44$1.32——
 Vercel
policy notes
AI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy
deepseek/deepseek-v4-flash-0731Sources: Models.dev data, Vercel AI Gateway data
Data from Vercel AI Gateway
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.13cache read $0.028$0.26——
 Wavespeeddeepseek/deepseek-v4-flash-0731Source: WaveSpeed AI data
Data from WaveSpeed AI
1M$0.13cache read $0.027$0.495——
 Alibaba CloudRegions: 🇯🇵🇸🇬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1deepseek-v4-flash-0731Sources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, LiteLLM data, Models.dev data
Data from Alibaba Cloud Model Studio (DashScope) Multi-Region API
Fields by sourceFrom Alibaba Cloud Qwen: currency, last updated, input tokens, output tokens, unitFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$0.44cache read $0.04$1.32——
 Baidudeepseek-v4-flash-0731 · fp8Source: Baidu Qianfan
Data from Baidu Qianfan
Not published by the provider
CN¥3.00cache read CN¥0.10
≈ $0.4482 USD (compared by USD value)
CN¥9.00
≈ $1.3446 USD (compared by USD value)
——
 Basetendeepseek-ai/DeepSeek-V4-Flash-0731 · fp8Sources: Baseten data, LiteLLM data, Models.dev data
Data from Baseten
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports tool choice, supports response schema, supports prompt caching, max input tokens, max output tokens, cache-read priceFrom Models.dev: supports system messages, supports vision, supports image input
1M$0.13cache read $0.028$0.26——
 Bothubdeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.589$1.7671——
 Chutes
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek-ai/DeepSeek-V4-Flash-0731-TEE · tee · fp8Sources: Chutes data, Models.dev data
Data from Chutes
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.44cache read $0.044$1.32——
 Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.014$1.32——
 Confidential AIdeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.20cache read $0.018$0.40——
 CrusoeDeepSeek V4 Flash 0731Source: Crusoe Managed Inference
Data from Crusoe Managed Inference
Not published by the provider$0.14cache read $0.03$0.28——
 Databricksdatabricks/databricks-deepseek-v4-flash-0731Source: LiteLLM data
Data from LiteLLM
1M$0.14cache read $0.028$0.28cache write $0.14——
 DeepInfradeepseek-ai/DeepSeek-V4-Flash-0731 · fp8Sources: DeepInfra data, LiteLLM data, Models.dev data
Data from DeepInfra
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$0.06cache read $0.015$0.18——
 Digitaloceandeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.14cache read $0.028$0.28——
 Doubleworddeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.09cache read $0.018$0.18cache write $0.1125——
 Empiriolabsdeepseek-v4-flash-0731Sources: EmpirioLabs data, LiteLLM data, Models.dev data
Data from EmpirioLabs
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports response schema, max input tokens, max output tokensFrom Models.dev: supports vision
1M$0.424$1.272——
 Empiriolabsdeepseek-v4-flash-0731:variant1 · variant1Source: EmpirioLabs data
Data from EmpirioLabs
1M$0.44$1.32——
 Engydeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.045cache read $0.009$0.09——
 Featherless AIdeepseek-ai/DeepSeek-V4-Flash-0731Source: Featherless data
Data from Featherless
262K$0.14$0.28——
 Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731Source: LiteLLM data
Data from LiteLLM
1M$0.22cache read $0.007$0.66——
 FlexaiRegions: 🇪🇺 euDeepSeek-V4-Flash-0731Sources: flex.ai API data, flex.ai Pricing
Data from flex.ai API
Fields by sourceFrom flex.ai Pricing: cache-read price
1M$0.13cache read $0.0195$0.26——
 Gmiclouddeepseek-ai/DeepSeek-V4-Flash-0731 · fp8Sources: GMI Cloud data, LiteLLM data
Data from GMI Cloud
Fields by sourceFrom LiteLLM: offering name, max input tokens, supported input modalities, supported output modalities, max input tokens, currency, last updated, input tokens, output tokens, cache-read price
1M$0.286cache read $0.0091$0.858——
 Greenptdeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.1596cache read $0.0456$0.399——
 Inceptrondeepseek-ai/DeepSeek-V4-Flash-0731 · fp4Sources: Inceptron data, Models.dev data
Data from Inceptron
Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-write price
1M$0.13cache read $0.027$0.495——
 Ionetdeepseek-ai/DeepSeek-V4-Flash-0731Source: IO Intelligence (io.net) data
Data from IO Intelligence (io.net)
262K$0.1858cache read $0.0929$0.5036101.306391.456ms
 Iteracomputedeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.17cache read $0.005$0.70——
 Joingonkadeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
380K$0.0062$0.0185——
 Klavodeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.4361cache read $0.0848$1.3325——
 Llmgateway Providersalibaba/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.044$1.32——
 Lyceumdeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.25cache read $0.06$0.30——
 Mancerdeepseek-v4-flash-0731 · fp8Source: Mancer data
Data from Mancer
1M$0.15$0.50——
 Merge Gatewaydeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.13cache read $0.028$0.26——
 Merge Gatewaydeepseek/deepseek-v4-flash-0731-fast · fastSource: Models.dev data
Data from Models.dev
1M$0.28cache read $0.07$0.56——
 Moarkdeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.15$0.30——
 Nebius AI Studionebius/deepseek-ai/DeepSeek-V4-Flash-0731Source: LiteLLM data
Data from LiteLLM
1M$0.14cache read $0.01$0.28——
 Neosantaradeepseek-v4-flash-0731Source: Neosantara Inference data
Data from Neosantara Inference
1M$0.14cache read $0.03$0.28——
 Nextbitdeepseek:v4-flash-0731 · fp8Source: NextBit data
Data from NextBit
1M$0.352cache read $0.012$1.056——
 Novita AIdeepseek/deepseek-v4-flash-0731 · fp8Sources: LiteLLM data, Models.dev data, Novita AI data
Data from Novita AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$0.44cache read $0.028$1.32——
 Ofoxdeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.014$1.32——
 Openreasondeepseek-ai/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.1371$0.2743——
 Orcarouterdeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.22cache read $0.007$0.66——
 Parasailparasail-deepseek-v4-flash-0731 · 0731Source: Parasail data
Data from Parasail
1M$0.14cache read $0.05$0.28——
 Perplexityperplexity/perplexity/deepseek-v4-flash-0731Source: LiteLLM data
Data from LiteLLM
Not published by the provider$0.13cache read $0.028$0.26——
 Perplexity Agentdeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.13cache read $0.028$0.26——
 Phala
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.028$1.32——
 Ppiodeepseek/deepseek-v4-flash-0731Source: PPIO data
Data from PPIO
1M
CN¥3.00cache read CN¥1.00
≈ $0.4482 USD (compared by USD value)
CN¥9.00
≈ $1.3446 USD (compared by USD value)
——
 Primedeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.014$1.32——
 Runinfradeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.13cache read $0.01$0.27——
 Saggdeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
400K$0.0397$0.0794——
 ScalewayRegions: 🇫🇷 fr-pardeepseek-v4-flash-0731Sources: LiteLLM data, Models.dev data, Scaleway Model as a Service, Scaleway API data docs
Data from Scaleway API
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image inputFrom Scaleway Model as a Service: is available, regions
256K$0.40cache read $0.08$0.80——
 Sferencedeepseek-ai/DeepSeek-V4-Flash-0731Source: sference data
Data from sference
1M$0.28cache read $0.07$0.56——
 SiliconFlowdeepseek-ai/DeepSeek-V4-Flash-0731 · fp8Sources: Models.dev data, SiliconFlow data
Data from SiliconFlow
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, cache-read price, currency, currency basis, last updated
1M$0.22cache read $0.014$0.66——
 Standardcomputedeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44cache read $0.014$1.32——
 Stepping Stonedeepseek-ai/DeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
524K$0.5355cache read $0.0803$2.142——
 Streamlakedeepseek-v4-flash-0731 · fp8Sources: LiteLLM data, StreamLake Pricing
Data from StreamLake Pricing
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read price
1M$0.44cache read $0.014$1.32——
 Tensorixdeepseek/deepseek-v4-flash-0731 · fp4Sources: Tensorix data, Tensorix Pricing
Data from Tensorix
Fields by sourceFrom Tensorix Pricing: input tokens, output tokens, currency, unit, last updated
Not published by the provider$0.25$0.30——
 Tensorxdeepseek/deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.25cache read $0.06$0.30——
 Together AItogether_ai/deepseek-ai/DeepSeek-V4-Flash-0731Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input
1M$0.14cache read $0.03$0.28——
 Umans AIumans-deepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.14cache read $0.028$0.28——
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
deepseek-v4-flash-0731Source: Venice.ai data
Data from Venice.ai
1M$0.13cache read $0.028$0.26——
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
deepseek-v4-flash-0731-fast · fastSource: Venice.ai data
Data from Venice.ai
1M$0.35cache read $0.0875$0.70——
 Vultrdeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.10$0.25——
 WaferDeepSeek-V4-Flash-0731-Fast · fast · nvfp4Sources: Models.dev data, Wafer data
Data from Wafer
Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.13cache read $0.03$0.23——
 Wallydeepseek-v4-flash-0731Source: Models.dev data
Data from Models.dev
1M$0.293cache read $0.0093$0.88——
 Weights & Biasesdeepseek-ai/DeepSeek-V4-Flash-0731Sources: LiteLLM data, Models.dev data, Weights & Biases Inference data
Data from Weights & Biases Inference
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports vision, supports image input
262K$0.13cache read $0.05$0.27——
 WattDeepSeek-V4-Flash-0731Source: Models.dev data
Data from Models.dev
1M$0.44$1.32——

14 listings without a price are hidden.

Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works