Skip to content

Listings

All listings for DeepSeek V4.1 Flash 1017

Every priced listing we track for this model. Back to DeepSeek V4.1 Flash 1017

ProviderMax Input TokensInput $/1MOutput $/1M$/input imageTok/sLatency
Run by the model's maker
 DeepSeek
deepseek-flashSources: DeepSeek data, LiteLLM data, Models.dev data
Version: 17 Oct 2026.DeepSeek gives the version for deepseek-flash as DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supported endpoints, supports streaming, supports native streaming, supports function calling, supports parallel function calling, supports tool choice, supports system messages, supports response schema, supports prompt caching, supports reasoning, supports web search, supports assistant prefill, supports vision, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read price, cache-write priceFrom Models.dev: max completion tokens, supports image input
1M$0.30cache read $0.006$1.20———
Run by the model's maker
 DeepSeek
deepseek/deepseek-flashSource: LiteLLM data
Version: 17 Oct 2026.LiteLLM says DeepSeek runs this listing. DeepSeek gives its current version as DeepSeek-V4.1-Flash-1017.
1M$0.30cache read $0.006$1.20———
 Microsoft Azureazure_ai/deepseek-v4.1-flash-1017Source: LiteLLM data
Version: 17 Oct 2026.LiteLLM lists the model id as azure_ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Aihubmixdeepseek-v4.1-flash-1017Source: AIHubMix data docs
Version: 17 Oct 2026.AIHubMix lists the model id as deepseek-v4.1-flash-1017.
1M$0.155cache read $0.0031$0.62———
 Atlasclouddeepseek-ai/deepseek-v4.1-flash-1017 · fp8Source: AtlasCloud data
Version: 17 Oct 2026.AtlasCloud lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Cortecs AIdeepseek-v4.1-flash-1017Sources: Cortecs EU Router data, Models.dev data
Version: 17 Oct 2026.Cortecs EU Router lists the model id as deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, max input tokens, max output tokens, supports image input
1M
€0.092cache read €0.005
≈ $0.101 USD (compared by USD value)
€0.55
≈ $0.6036 USD (compared by USD value)
———
 Eden AIInference by Flexaiflexai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as flexai/deepseek-v4.1-flash-1017.
1M$0.08cache read $0.0055$0.605———
 Eden AIInference by Alibaba Cloudqwen/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as qwen/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 Eden AIInference by Tencenttencent/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as tencent/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 Eden AIInference by DeepInfradeepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepinfra/deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.20cache read $0.006$0.60———
 Eden AIInference by Cloudflare Workers AIcloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Eden AIInference by Nebius AI Studionebius/deepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as nebius/deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30$1.20———
 Eden AIInference by Together AItogether_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as together_ai/deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Eden AIInference by Sferencesference/deepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as sference/deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.35cache read $0.03$1.32———
 Eden AIInference by Tensorxtensorx/deepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as tensorx/deepseek/deepseek-v4.1-flash-1017.
1M$0.50cache read $0.125$1.50———
 Eden AIInference by Scalewayscaleway/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as scaleway/deepseek-v4.1-flash-1017.
256K$0.6594cache read $0.1319$1.9782———
 Eurouterdeepseek-v4.1-flash-1017Source: EURouter data
Version: 17 Oct 2026.EURouter lists the model id as deepseek-v4.1-flash-1017.
1M$0.20cache read $0.005$0.60———
 Evolinkdeepseek-v4.1-flash-1017Sources: EvoLink data, EvoLink Pricing
Version: 17 Oct 2026.EvoLink lists the model id as deepseek-v4.1-flash-1017.
Fields by sourceFrom EvoLink Pricing: input tokens, output tokens, currency, unit, last updated
Not published by the provider$0.2941$1.1765———
 Fastrouterdeepseek/deepseek-v4.1-flash-1017Source: FastRouter data
Version: 17 Oct 2026.FastRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.098cache read $0.0029$0.294———
 Flowdotaccounts/fireworks/models/deepseek-v4p1-flash-1017Source: FlowDot data
Version: 17 Oct 2026.FlowDot lists the model id as accounts/fireworks/models/deepseek-v4p1-flash-1017.
1M$0.50$0.50———
 Hugging FaceInference by Waferdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.036$0.50———
 Hugging FaceInference by Sail Researchdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.04$0.10———
 Hugging FaceInference by Open Inferencedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.05$0.75———
 Hugging FaceInference by Pearl Researchdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.05$0.30———
 Hugging FaceInference by Primeintellectdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.0568$0.70———
 Hugging FaceInference by Morphdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.059$0.52———
 Hugging FaceInference by Particle AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.06$0.55———
 Hugging FaceInference by Inference Netdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.08$0.666———
 Hugging FaceInference by DeepInfradeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.098$0.294———
 Hugging FaceInference by Cloudflare Workers AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.10$0.60———
 Hugging FaceInference by Dekallmdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.10$0.60———
 Hugging FaceInference by Inceptrondeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.10$0.60———
 Hugging FaceInference by Coheredeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.115$0.40———
 Hugging FaceInference by Antdigitaldeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.12$0.48———
 Hugging FaceInference by Relacedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.12$0.50———
 Hugging FaceInference by Riverdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.12$0.48———
 Hugging FaceInference by Digitaloceandeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.15$0.60———
 Hugging FaceInference by Makoradeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.15$0.80———
 Hugging FaceInference by Modelrundeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.17$0.67———
 Hugging FaceInference by Nebius AI Studiodeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.18$0.72———
 Hugging FaceInference by Ionstreamdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.21$0.62———
 Hugging FaceInference by PrimaLabsdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.24$0.96———
 Hugging FaceInference by Modaldeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.25$1.00———
 Hugging FaceInference by Crusoedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.29$1.20———
 Hugging FaceInference by Basetendeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Coreweavedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Fireworks AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging Facedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Mistral AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging Face
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.
Inference by Near AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Novita AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Parasaildeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Reka AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Together AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Hugging FaceInference by Venicedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Hugging Face Inference Providers data
Version: 17 Oct 2026.Hugging Face Inference Providers lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30$1.20———
 Kilodeepseek/deepseek-v4.1-flash-1017Sources: Kilo AI Gateway data, Models.dev data
Version: 17 Oct 2026.Kilo AI Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.30cache read $0.007$1.20———
 Kilodeepseek/deepseek-v4.1-flash-1017-fast · fastSources: Kilo AI Gateway data, Models.dev data
Version: 17 Oct 2026.Kilo AI Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017-fast.
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.60cache read $0.014$2.40$0.00——
 Llmgatewaydeepseek-v4.1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
1.1M$0.08cache read $0.0055$0.605———
 LlmgatewayInference by DeepSeekdeepseek-flashSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.15cache read $0.003$0.60———
 LlmgatewayInference by DeepSeekdeepseek-flashSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway says DeepSeek runs this listing. DeepSeek gives its current version as DeepSeek-V4.1-Flash-1017.
Not published by the provider$0.15cache read $0.003$0.60———
 LlmgatewayInference by DeepSeekdeepseek-flash · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway says DeepSeek runs this listing. DeepSeek gives its current version as DeepSeek-V4.1-Flash-1017.
Not published by the provider$0.15cache read $0.003$0.60———
 LlmgatewayInference by Reka AIdeepseek41-flash-20261017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.15cache read $0.003$0.60———
 LlmgatewayInference by Reka AIdeepseek41-flash-20261017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek41-flash-20261017.
Not published by the provider$0.15cache read $0.003$0.60———
 LlmgatewayInference by DeepInfradeepseek-ai/DeepSeek-V4.1-Flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.20cache read $0.006$0.60———
 LlmgatewayInference by DeepInfradeepseek-ai/DeepSeek-V4.1-Flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
Not published by the provider$0.20cache read $0.006$0.60———
 LlmgatewayInference by Alibaba Clouddeepseek-v4.1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Alibaba Clouddeepseek-v4.1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4.1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4.1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as @cf/deepseek-ai/deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Fireworks AIaccounts/fireworks/models/deepseek-v4p1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Fireworks AIaccounts/fireworks/models/deepseek-v4p1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as accounts/fireworks/models/deepseek-v4p1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Inference Netdeepseek-v4.1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.007$1.00———
 LlmgatewayInference by Inference Netdeepseek-v4.1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.007$1.00———
 LlmgatewayInference by Mistral AIdeepseek-v4-1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.007$1.20———
 LlmgatewayInference by Mistral AIdeepseek-v4-1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4-1-flash-1017.
Not published by the provider$0.30cache read $0.007$1.20———
 LlmgatewayInference by Novita AIdeepseek/deepseek-v4.1-flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Novita AIdeepseek/deepseek-v4.1-flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Together AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 LlmgatewayInference by Together AIdeepseek-ai/DeepSeek-V4.1-Flash-1017 · latestSource: LLMGateway data
Version: 17 Oct 2026.LLMGateway lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
Not published by the provider$0.30cache read $0.006$1.20———
 Meganovadeepseek-ai/DeepSeek-V4.1-Flash-1017Source: MegaNova data
Version: 17 Oct 2026.MegaNova lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.10$0.30———
 Meliousdeepseek-v4.1-flash-1017Sources: Melious API data, Models.dev data
Version: 17 Oct 2026.Melious API lists the model id as deepseek-v4.1-flash-1017.
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$0.3345cache read $0.0335$1.338———
 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 CoralbricksRegions: UNKdeepseek/deepseek-v4.1-flash-1017 · standardSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0053cache read $0.0032$0.5985—125.62,712ms
 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 CoralbricksRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · standard, thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0053cache read $0.0032$0.5985—156.32,420ms
 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 Runinfradeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0368cache read $0.0121$0.6825———
 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 Runinfradeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0368cache read $0.0121$0.6825———
 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 Sail ResearchRegions: GLBdeepseek/deepseek-v4.1-flash-1017 · standard · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.042cache read $0.0074$0.105—145.51,470ms
 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 Sail ResearchRegions: GLBdeepseek/deepseek-v4.1-flash-1017:thinking · standard, thinking · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.042cache read $0.0074$0.105—240.81,593ms
 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 Pearl ResearchRegions: UNKdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0525cache read $0.0032$0.315—286.51,288ms
 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 Pearl ResearchRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0525cache read $0.0032$0.315—268.41,476ms
 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-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0596cache read $0.0033$0.735———
 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-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0596cache read $0.0033$0.735———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by MorphRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.062cache read $0.0053$0.546———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by MorphRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.062cache read $0.0053$0.546———
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by OpenscaleRegions: 🇸🇬 SGdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.063cache read $0.0032$0.252———
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by OpenscaleRegions: 🇸🇬 SGdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.063cache read $0.0032$0.252———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by WaferRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · mxfp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0693cache read $0.0068$0.525—202.83,377ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by WaferRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · mxfp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0693cache read $0.0068$0.525—202.83,377ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0788cache read $0.0016$0.315—296.91,847ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0788cache read $0.0016$0.315—293.84,504ms
 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 FiftyxRegions: UNKdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.0798cache read $0.0016$0.2993—190.74,333ms
 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 FiftyxRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.0798cache read $0.0016$0.2993—211.33,593ms
 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 DiscretestackRegions: 🇪🇺 EUdeepseek/deepseek-v4.1-flash-1017 · mxfp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.10cache read $0.0042$0.60—392.5619ms
 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 DiscretestackRegions: 🇪🇺 EUdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · mxfp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.10cache read $0.0042$0.60—429.91,044ms
 NanoGPTdeepseek/deepseek-v4.1-flash-1017Sources: Models.dev data, NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
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$0.10cache read $0.0042$0.60———
 NanoGPTdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSources: Models.dev data, NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
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$0.10cache read $0.0042$0.60———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Reka AIRegions: UNKdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.10cache read $0.0042$0.60———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Reka AIRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.10cache read $0.0042$0.60———
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1026cache read $0.0022$0.4141—249.1973ms
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1026cache read $0.0022$0.4141—162.12,012ms
 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 Ambientdeepseek/deepseek-v4.1-flash-1017 · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1029cache read $0.003$0.3087—107.63,210ms
 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 Ambientdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1029cache read $0.003$0.3087—65.83,320ms
 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 Cloudflare Workers AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.105cache read $0.0032$0.63—128.92,792ms
 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 Cloudflare Workers AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.105cache read $0.0032$0.63—213.73,215ms
 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 DekallmRegions: 🇮🇩 IDdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.105cache read $0.0032$0.63———
 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 DekallmRegions: 🇮🇩 IDdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.105cache read $0.0032$0.63———
 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-v4.1-flash-1017 · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.105cache read $0.0063$0.63———
 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-v4.1-flash-1017:thinking · thinking · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.105cache read $0.0063$0.63———
 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 RelaceRegions: UNKdeepseek/deepseek-v4.1-flash-1017 · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.126cache read $0.0032$0.525———
 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 RelaceRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.126cache read $0.0032$0.525———
 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 RiverRegions: FI/ISdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.126cache read $0.0025$0.504———
 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 RiverRegions: FI/ISdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.126cache read $0.0025$0.504———
 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 RunwareRegions: UNKdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1418cache read $0.0095$0.567———
 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 RunwareRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1418cache read $0.0095$0.567———
 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 ScxRegions: GLBdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1418cache read $0.0032$0.567———
 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 ScxRegions: GLBdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1418cache read $0.0032$0.567—280.45,858ms
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.147cache read $0.0044$0.441—160.3728ms
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.147cache read $0.0044$0.441—148.11,550ms
 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 DeepSeekRegions: 🇨🇳 CNdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1575cache read $0.0032$0.63—144.7983ms
 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 DeepSeekRegions: 🇨🇳 CNdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1575cache read $0.0032$0.63—121.21,027ms
 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 NeuralwattRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1575cache read $0.0158$0.63———
 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 NeuralwattRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1575cache read $0.0158$0.63———
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1575cache read $0.0032$0.63———
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1575cache read $0.0032$0.63———
 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 Novita AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1733cache read $0.0035$0.693—117.72,050ms
 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 Novita AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1733cache read $0.0035$0.693—138.32,383ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.189cache read $0.0038$0.756———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.189cache read $0.0038$0.756—166.51,466ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Nebius AI StudioRegions: GLBdeepseek/deepseek-v4.1-flash-1017 · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.189cache read $0.0038$0.756—217.9431ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Nebius AI StudioRegions: GLBdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp4Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.189cache read $0.0038$0.756—511.2840ms
 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-v4.1-flash-1017 · bf16Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.1922$0.8178———
 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-v4.1-flash-1017:thinking · thinking · bf16Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.1922$0.8178———
 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 RunanywhereRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.2048cache read $0.0063$1.05———
 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 RunanywhereRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.2048cache read $0.0063$1.05———
 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 EntrimRegions: 🇪🇺 EUdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.21cache read $0.0053$0.63—7163,306ms
 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 EntrimRegions: 🇪🇺 EUdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.21cache read $0.0053$0.63—7163,306ms
 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 KitaniRegions: GLBdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.2625cache read $0.0063$1.155—215.26,510ms
 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 KitaniRegions: GLBdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.2625cache read $0.0063$1.155—213.77,554ms
 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 ModalRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.2625cache read $0.0053$1.05———
 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 ModalRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.2625cache read $0.0053$1.05———
 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 HeabsyRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.2712cache read $0.0055$1.0847—410.11,420ms
 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 HeabsyRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.2712cache read $0.0055$1.0847—410.11,420ms
 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 CrusoeRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.3045cache read $0.0074$1.26———
 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 CrusoeRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.3045cache read $0.0074$1.26———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0074$1.26———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0074$1.26———
 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 CoreweaveRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0063$1.26———
 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 CoreweaveRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0063$1.26———
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0063$1.26—261842ms
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0063$1.26—261842ms
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0063$1.26—260.3417ms
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0063$1.26—169.3688ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Together AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0063$1.26—220.8563ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Together AIRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0063$1.26—280.71,658ms
 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 VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.315cache read $0.0079$1.26———
 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 VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.315cache read $0.0079$1.26———
 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 CoralbricksRegions: UNKdeepseek/deepseek-v4.1-flash-1017Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.4725cache read $0.0095$1.89———
 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 CoralbricksRegions: UNKdeepseek/deepseek-v4.1-flash-1017:thinking · thinkingSource: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.4725cache read $0.0095$1.89—563.412,042ms
 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-v4.1-flash-1017 · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017.
Not published by the provider$0.525cache read $0.1313$1.575———
 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-v4.1-flash-1017:thinking · thinking · fp8Source: NanoGPT
Version: 17 Oct 2026.NanoGPT lists the model id as deepseek/deepseek-v4.1-flash-1017:thinking.
Not published by the provider$0.525cache read $0.1313$1.575———
 Near AI
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-v4.1-flash-1017Sources: Models.dev data, NEAR AI Cloud data
Version: 17 Oct 2026.NEAR AI Cloud lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.30cache read $0.006$1.20———
 Nous Portaldeepseek/deepseek-v4.1-flash-1017:batch · batchSource: Nous Portal Inference Gateway data
Version: 17 Oct 2026.Nous Portal Inference Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017:batch.
1M$0.035cache read $0.0029$0.149———
 Nous Portaldeepseek/deepseek-v4.1-flash-1017Source: Nous Portal Inference Gateway data
Version: 17 Oct 2026.Nous Portal Inference Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 OpenRouterInference by Particle AIdeepseek/deepseek-v4.1-flash-1017 · us/flexSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.03cache read $0.015$0.275—145736ms
 OpenRouterdeepseek/deepseek-v4.1-flash-1017:batch · batchSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017:batch.
1M$0.035cache read $0.0029$0.149———
 OpenRouterInference by Together AIdeepseek/deepseek-v4.1-flash-1017:batch · batchSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017:batch.
1M$0.035cache read $0.0029$0.149———
 OpenRouterInference by Morphdeepseek/deepseek-v4.1-flash-1017:batch · batch, fp8 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017:batch.
1M$0.036cache read $0.003$0.15———
 OpenRouterInference by Waferdeepseek/deepseek-v4.1-flash-1017 · us · mxfp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.036cache read $0.01$0.50—192323ms
 OpenRouterInference by Sail Researchdeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.04cache read $0.007$0.10—1181,607ms
 OpenRouterInference by Sail Researchdeepseek/deepseek-v4.1-flash-1017 · fp4/us · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.04cache read $0.007$0.10—1211,362ms
 OpenRouterInference by Ambientdeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.045cache read $0.0025$0.25—601,780ms
 OpenRouterInference by Openinferencedeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.05cache read $0.002$0.75—181635.5ms
 OpenRouterInference by Pearl Researchdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.05cache read $0.003$0.30—1441,332ms
 OpenRouterInference by Sail Researchdeepseek/deepseek-v4.1-flash-1017:batch · batch, fp4 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017:batch.
1M$0.05cache read $0.004$0.15———
 OpenRouterInference by Primeintellectdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.0568cache read $0.0031$0.70—165468ms
 OpenRouterInference by Morphdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.059cache read $0.005$0.52—117452ms
 OpenRouterInference by Particle AIdeepseek/deepseek-v4.1-flash-1017 · usSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.06cache read $0.03$0.55—151496ms
 OpenRouterInference by Waferdeepseek/deepseek-v4.1-flash-1017 · mxfp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.066cache read $0.0065$0.50—203293ms
 OpenRouterInference by Streamlakedeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.075cache read $0.0015$0.30—812,348ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v4.1-flash-1017 · fp8/flex · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.0784cache read $0.0024$0.2352—802,158ms
 OpenRouterInference by Inferencenetdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.08cache read $0.008$0.666—124448.5ms
 OpenRouterInference by Inferencenetdeepseek/deepseek-v4.1-flash-1017 · us · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.08cache read $0.008$0.666—121290ms
 OpenRouterInference by Baidudeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.0977cache read $0.0021$0.3944—125697ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.098cache read $0.0029$0.294—114673ms
 OpenRouterInference by Cloudflare Workers AIdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.10cache read $0.003$0.60—1171,435.5ms
 OpenRouterInference by Dekallmdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.10cache read $0.003$0.60—57.51,538ms
 OpenRouterInference by Inceptrondeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.10cache read $0.006$0.60—981,468ms
 OpenRouterInference by StepFundeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.105cache read $0.0021$0.42—2011,185ms
 OpenRouterInference by Coheredeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.115cache read $0.0025$0.40—137891ms
 OpenRouterInference by Ant Digitaldeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.12cache read $0.0024$0.48—1071,692ms
 OpenRouterInference by Relacedeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.12cache read $0.003$0.50—1401,091ms
 OpenRouterInference by Riverdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.12cache read $0.0024$0.48—67612ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v4.1-flash-1017 · fp8/priority · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.147cache read $0.0044$0.441—125897.5ms
 OpenRouterInference by DeepSeekdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60—1141,203.5ms
 OpenRouterInference by Digitaloceandeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60—186664.5ms
 OpenRouterInference by Makoradeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.006$0.80—1451,045ms
 OpenRouterdeepseek/deepseek-v4.1-flash-1017Sources: Models.dev data, OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.15cache read $0.003$0.60———
 OpenRouterInference by SiliconFlowdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60—176679ms
 OpenRouterInference by Novita AIdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.165cache read $0.0033$0.66—1221,260ms
 OpenRouterInference by Modelrundeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.17cache read $0.006$0.67—163788ms
 OpenRouterInference by Alibaba Clouddeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.18cache read $0.0036$0.72—136776ms
 OpenRouterInference by Nebius AI Studiodeepseek/deepseek-v4.1-flash-1017 · fp4Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.18cache read $0.0036$0.72—247484ms
 OpenRouterInference by Ionstreamdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.21cache read $0.0105$0.62—164.5723ms
 OpenRouterInference by PrimaLabsdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.24cache read $0.0048$0.96—1321,223ms
 OpenRouterInference by Modaldeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.25cache read $0.005$1.00—101485ms
 OpenRouterInference by Crusoedeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.29cache read $0.007$1.20—179735ms
 OpenRouterInference by Basetendeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.007$1.20—130.5644.5ms
 OpenRouterInference by Coreweavedeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—132521ms
 OpenRouterInference by Fireworks AIdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—1711,007ms
 OpenRouterInference by Mistral AIdeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.007$1.20—2051,041ms
 OpenRouter
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.
Inference by Near AIdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—54809ms
 OpenRouterInference by Parasaildeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—137601ms
 OpenRouterInference by Reka AIdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—136682ms
 OpenRouterInference by Together AIdeepseek/deepseek-v4.1-flash-1017Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20—190616ms
 OpenRouterInference by Venicedeepseek/deepseek-v4.1-flash-1017 · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.0075$1.20—743,441ms
 OpenRouterInference by Fireworks AIdeepseek/deepseek-v4.1-flash-1017 · usSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.45cache read $0.009$1.80—196513ms
 OpenRouterInference by Basetendeepseek/deepseek-v4.1-flash-1017 · fastSource: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.60cache read $0.014$2.40—565294ms
 OpenRouterInference by Morphdeepseek/deepseek-v4.1-flash-1017 · fast · fp8Source: OpenRouter data docs
Version: 17 Oct 2026.OpenRouter lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.60cache read $0.014$2.40—273298ms
 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-v4.1-flash-1017Source: RedPill data
Version: 17 Oct 2026.RedPill lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30$1.20———
 RequestyInference by DeepSeekdeepseek/deepseek-v4.1-flashSource: Requesty data
Version: 17 Oct 2026.Requesty says DeepSeek runs this listing. DeepSeek gives its current version as DeepSeek-V4.1-Flash-1017.
1M$0.30cache read $0.006$1.20———
 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-v4.1-flash-1017Sources: Models.dev data, Vercel AI Gateway data
Version: 17 Oct 2026.Vercel AI Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, max input tokens, max output tokens, supports image input
1M$0.30cache read $0.007$1.20———
 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-v4.1-flash-1017-fast · fastSources: Models.dev data, Vercel AI Gateway data
Version: 17 Oct 2026.Vercel AI Gateway lists the model id as deepseek/deepseek-v4.1-flash-1017-fast.
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, max input tokens, max output tokens, supports image input
1M$0.60cache read $0.014$2.40———
 Wavespeeddeepseek/deepseek-v4.1-flash-1017Source: WaveSpeed AI data
Version: 17 Oct 2026.WaveSpeed AI lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 Abliteratedllmdeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.27cache read $0.0054$1.08———
 Aianddeepseek-ai/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.02$0.60———
 Alibaba CloudRegions: 🇯🇵🇸🇬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1deepseek-v4.1-flash-1017Sources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen
Version: 17 Oct 2026.Alibaba Cloud Model Studio (DashScope) Multi-Region API lists the model id as deepseek-v4.1-flash-1017.
Fields by sourceFrom Alibaba Cloud Qwen: currency, last updated, input tokens, output tokens, unit
Not published by the provider$0.30$1.20———
 Ambientdeepseek/deepseek-v4.1-flash-1017 · fp4Sources: Ambient data, Models.dev data
Version: 17 Oct 2026.Ambient lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-write price
1M$0.045cache read $0.0025$0.25———
 Arceedeepseek/deepseek-v4.1-flash-1017Sources: Arcee AI data, Models.dev data
Version: 17 Oct 2026.Arcee AI lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: 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
1M$0.30cache read $0.006$1.20———
 Baidudeepseek-v4.1-flash-1017 · fp8Source: Baidu Qianfan
Version: 17 Oct 2026.Baidu Qianfan lists the model id as deepseek-v4.1-flash-1017.
Not published by the provider
CN¥2.00cache read CN¥0.04
≈ $0.2988 USD (compared by USD value)
CN¥8.00
≈ $1.1952 USD (compared by USD value)
———
 Basetendeepseek-ai/DeepSeek-V4.1-Flash-1017Sources: Baseten data, LiteLLM data, Models.dev data
Version: 17 Oct 2026.Baseten lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports tool choice, supports response schema, supports prompt caching, supports vision, max input tokens, max output tokens, cache-read priceFrom Models.dev: supports system messages, supports image input
1M$0.30cache read $0.007$1.20———
 Basetendeepseek-ai/DeepSeek-V4.1-Flash-1017-Fast · fastSources: Baseten data, LiteLLM data, Models.dev data
Version: 17 Oct 2026.Baseten lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast.
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports tool choice, supports response schema, supports prompt caching, supports vision, max input tokens, max output tokens, cache-read priceFrom Models.dev: supports system messages, supports image input
1M$0.60cache read $0.014$2.40———
 BytePlus
policy notes
service may store your Customer Data for content safety purposes; input and output triggered by the filter are retained for 180 days in *Malaysia — BytePlus ModelArk data-processing documentation has a strict internal account and data rights management policy and cannot access Customer Data unless authorized by the customer — BytePlus ModelArk data-processing documentation Source: BytePlus ModelArk data-processing documentation
deepseek-v4-1-flash-261017Sources: BytePlus ModelArk Pricing, Models.dev data
Version: 17 Oct 2026.BytePlus ModelArk Pricing lists the model id as deepseek-v4-1-flash-261017.
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, cache-read price
1M$0.15cache read $0.003$0.60———
 Cheapest Tokendeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Chutesdeepseek-ai/DeepSeek-V4.1-Flash-1017Sources: Chutes data, Models.dev data
Version: 17 Oct 2026.Chutes lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.195cache read $0.02$0.78———
 Cline Passcline-pass/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as cline-pass/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 Cloudflare AI Gatewaydeepseek-ai/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.007$1.20———
 Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4.1-flash-1017Sources: Cloudflare Workers AI, Models.dev data
Version: 17 Oct 2026.Cloudflare Workers AI lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: context length, max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.30cache read $0.006$1.20———
 Databricksdatabricks/databricks-deepseek-v4-1-flash-1017Source: LiteLLM data
Version: 17 Oct 2026.LiteLLM lists the model id as databricks/databricks-deepseek-v4-1-flash-1017.
1M$0.30cache read $0.007$1.20cache write $0.30———
 DeepInfradeepseek-ai/DeepSeek-V4.1-Flash-1017 · fp8Sources: DeepInfra data, LiteLLM data, Models.dev data
Version: 17 Oct 2026.DeepInfra lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
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, supports vision, 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 image input
1M$0.14cache read $0.0042$0.42———
 Digitaloceandeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Doubleworddeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60cache write $0.1875———
 Empiriolabsdeepseek-v4-1-flash-1017Sources: EmpirioLabs data, LiteLLM data
Version: 17 Oct 2026.EmpirioLabs lists the model id as deepseek-v4-1-flash-1017.
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports response schema, max input tokens, max output tokens
1M$0.20cache read $0.02$0.80———
 Engydeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.03cache read $0.006$0.12———
 Entrimdeepseek-ai/DeepSeek-V4.1-Flash-1017 · fp8Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.20cache read $0.005$0.60———
 Featherless AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Featherless data
Version: 17 Oct 2026.Featherless lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
262K$0.225$0.90———
 Fiftyxdeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.064cache read $0.0012$0.24———
 Fireworks AIfireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-flex · flexSource: LiteLLM data
Version: 17 Oct 2026.LiteLLM lists the model id as fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-flex.
1M$0.15cache read $0.003$0.60———
 Fireworks AIaccounts/fireworks/models/deepseek-v4p1-flash-1017Sources: Fireworks AI data, LiteLLM data, Models.dev data
Version: 17 Oct 2026.Fireworks AI lists the model id as accounts/fireworks/models/deepseek-v4p1-flash-1017.
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, supports vision, 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 image input
1M$0.30cache read $0.006$1.20———
 Fireworks AIRegions: 🇺🇸 usfireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-usSource: LiteLLM data
Version: 17 Oct 2026.LiteLLM lists the model id as fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us.
1M$0.45cache read $0.009$1.80———
 FlexaiRegions: 🇪🇺 euDeepSeek-V4.1-Flash-1017Sources: flex.ai API data, flex.ai Pricing
Version: 17 Oct 2026.flex.ai API lists the model id as DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom flex.ai Pricing: cache-read price
1M$0.08cache read $0.0055$0.605———
 Gmiclouddeepseek-ai/deepseek-v4.1-flash-1017 · fp8Sources: GMI Cloud data, LiteLLM data
Version: 17 Oct 2026.GMI Cloud lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
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$0.18cache read $0.0036$0.72———
 Greenptdeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.4022cache read $0.0447$1.6199———
 Hopperdeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.09cache read $0.007$0.85———
 Huawei Maasdeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.2999cache read $0.03$1.1994———
 Hyperdeepseek-v4.1-flash-1017Sources: Charm Hyper data, Models.dev data
Version: 17 Oct 2026.Charm Hyper lists the model id as deepseek-v4.1-flash-1017.
Fields by sourceFrom Models.dev: supports function calling, supports system messages, max input tokens, max output tokens, supports image input
1M$0.33cache read $0.03$1.31———
 Inceptrondeepseek-ai/DeepSeek-V4.1-Flash-1017 · fp4Sources: Inceptron data, Models.dev data
Version: 17 Oct 2026.Inceptron lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
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$0.10cache read $0.006$0.60———
 Infersiadeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.35cache read $0.01$1.25———
 Isoquantdeepseek-v4.1-flash-1017-fast · fastSource: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017-fast.
1M$0.035cache read $0.005$0.37———
 Iteracomputedeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.14cache read $0.006$0.55———
 Kelndeepseek-ai/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.01$1.20———
 Kitanideepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.25cache read $0.006$1.10———
 Kitanideepseek/deepseek-v4.1-flash-1017-thinking · thinkingSource: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017-thinking.
1M$0.25cache read $0.006$1.10———
 Klavodeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.2907cache read $0.0182$1.2114———
 Liquiddeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.059cache read $0.0026$0.206———
 Llmgateway Providersalibaba/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as alibaba/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Merge Gatewaydeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.15cache read $0.003$0.60———
 Mistral AIdeepseek-v4-1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4-1-flash-1017.
1M$0.30cache read $0.007$1.20———
 Modulardeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.17cache read $0.02$1.20———
 MorphRegions: 🇺🇸 USmorph-dsv41flash-1017 · fp8Source: Morph data
Version: 17 Oct 2026.Morph names the Hugging Face repository deepseek-ai/DeepSeek-V4.1-Flash-1017, which holds this version.
1M$0.059cache read $0.005$0.52———
 MorphRegions: 🇺🇸 USmorph-dsv41flash-1017-fast · fp8Source: Morph data
Version: 17 Oct 2026.Morph names the Hugging Face repository deepseek-ai/DeepSeek-V4.1-Flash-1017, which holds this version.
1M$0.60cache read $0.014$2.40———
 Munitodeepseek-ai/deepseek-v4.1-flash-1017 · fp8Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.27cache read $0.0054$1.00———
 Nebius AI Studionebius/deepseek-ai/DeepSeek-V4.1-Flash-1017 · fp4Sources: LiteLLM data, Models.dev data
Version: 17 Oct 2026.LiteLLM lists the model id as nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, max output tokens, supports image input
1M$0.30cache read $0.006$1.20———
 Novita AIdeepseek/deepseek-v4.1-flash-1017 · fp8Sources: Models.dev data, Novita AI data
Version: 17 Oct 2026.Novita AI lists the model id as deepseek/deepseek-v4.1-flash-1017.
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-read price
1M$0.30cache read $0.006$1.20———
 Ofoxdeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Ollamadeepseek-v4.1-flash:1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash:1017.
1M$0.15cache read $0.003$0.60———
 Openinferencedeepseek-ai/DeepSeek-V4.1-Flash-1017 · fp4Source: OpenInference data
Version: 17 Oct 2026.OpenInference lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.05cache read $0.002$0.80———
 Parasailparasail-deepseek-v41-flash-1017 · 1017Source: Parasail data
Version: 17 Oct 2026.Parasail lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.30cache read $0.006$1.20———
 Particle AIdeepseek-ai/deepseek-v41-flash-1017Source: Particle AI data docs
Version: 17 Oct 2026.Particle AI lists the model id as deepseek-ai/deepseek-v41-flash-1017.
Not published by the provider$0.25cache read $0.03$1.00———
 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-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.75cache read $0.15$1.60———
 Primedeepseek/deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek/deepseek-v4.1-flash-1017.
1M$0.0568cache read $0.0031$0.70cache write $0.0568———
 Runcratedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-ai/deepseek-v4.1-flash-1017.
1M$0.1029cache read $0.0031$0.3087———
 ScalewayRegions: 🇫🇷 fr-pardeepseek-v4.1-flash-1017Sources: Models.dev data, Scaleway Model as a Service, Scaleway API data docs
Version: 17 Oct 2026.Scaleway API lists the model id as deepseek-v4.1-flash-1017.
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, convertedFrom Scaleway Model as a Service: max output tokens, is available, regions
256K$0.672cache read $0.134$2.016———
 Scx AIDeepSeek-V4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.30cache read $0.006$1.20———
 Sferencedeepseek-ai/DeepSeek-V4.1-Flash-1017Source: sference data
Version: 17 Oct 2026.sference lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
1M$0.35cache read $0.03$1.32———
 Streamlakedeepseek-v4-1-flash-1017 · fp8Sources: LiteLLM data, StreamLake Pricing
Version: 17 Oct 2026.StreamLake Pricing lists the model id as deepseek-v4-1-flash-1017.
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, supports vision, max input tokens, max output tokens, cache-read price
1M$0.30cache read $0.006$1.20———
 SyntheticRegions: 🇺🇸 UShf:deepseek-ai/DeepSeek-V4.1-Flash-1017 · fp8Sources: Models.dev data, Synthetic data
Version: 17 Oct 2026.Synthetic lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
524K$0.60cache read $0.03$1.20———
 Tensorixdeepseek/deepseek-v4.1-flash-1017 · fp8Sources: Tensorix data, Tensorix Pricing
Version: 17 Oct 2026.Tensorix lists the model id as deepseek/deepseek-v4.1-flash-1017.
Fields by sourceFrom Tensorix Pricing: input tokens, output tokens, currency, unit, last updated
Not published by the provider$0.50$1.50———
 Together AIdeepseek-ai/DeepSeek-V4.1-Flash-1017Sources: LiteLLM data, Together AI data
Version: 17 Oct 2026.Together AI lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
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, supports vision, max input tokens, max output tokens, cache-read price
1M$0.30cache read $0.006$1.20———
 Umans AIumans-deepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as umans-deepseek-v4.1-flash-1017.
1M$0.15cache read $0.028$0.60———
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
deepseek-v4-1-flash-1017 · fp8Source: Venice.ai data
Version: 17 Oct 2026.Venice.ai lists the model id as deepseek-v4.1-flash-1017.
1M$0.30cache read $0.0075$1.20———
 WaferDeepSeek-V4.1-Flash-1017 · mxfp4Sources: Models.dev data, Wafer data
Version: 17 Oct 2026.Wafer lists the model id as DeepSeek-V4.1-Flash-1017.
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 $0.01$0.50———
 Wallydeepseek-v4.1-flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.195cache read $0.006$1.00———
 Weights & Biasesdeepseek-ai/DeepSeek-V4.1-Flash-1017Sources: LiteLLM data, Models.dev data, Weights & Biases Inference data
Version: 17 Oct 2026.Weights & Biases Inference lists the model id as deepseek-ai/DeepSeek-V4.1-Flash-1017.
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, supports vision, 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 image input
1M$0.30cache read $0.006$1.20———
 WattDeepSeek-V4.1-Flash-1017Source: Models.dev data
Version: 17 Oct 2026.Models.dev lists the model id as deepseek-v4.1-flash-1017.
1M$0.30$1.20———

20 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