# DeepSeek V4.1 Flash API pricing

No price from the maker itself is on record for DeepSeek V4.1 Flash. The lowest of 63 providers is engy: $0.03 per 1M input tokens and $0.12 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 384K output tokens per request.

- Type: Text
- Context: 1.05M
- Max output: 384K
- Released: 2026-09-10
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [engy](https://engy.ai/pricing) | deepseek-v4.1-flash | $0.03 | $0.12 | $0.006 | Lowest |
| [ZenMux](https://docs.zenmux.ai) | deepseek/deepseek-v4.1-flash | $0.075 | $0.3 | $0.0015 |  |
| [Subconscious](https://docs.subconscious.dev) | subconscious/deepseek-v4.1-flash-marathon | $0.14 | $0.28 | $0.0028 |  |
| [NanoGPT](https://docs.nano-gpt.com) | deepseek/deepseek-v4.1-flash | $0.022 | $0.4 | $0.004 |  |
| [NanoGPT](https://docs.nano-gpt.com) | deepseek/deepseek-v4.1-flash:thinking | $0.022 | $0.4 | $0.004 |  |
| [OpenRouter](https://openrouter.ai/models) | deepseek/deepseek-v4.1-flash | $0.022 | $0.4 | $0.004 |  |
| [Kenari](https://kenari.id/docs) | deepseek-v4-1-flash | $0.157143 | $0.314286 | $0.003714 |  |
| [Standard Compute](https://docs.standardcompute.com/models) | deepseek/deepseek-v4.1-flash | $0.14 | $0.42 | $0.0042 |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | deepseek-v4.1-flash | $0.135 | $0.54 | $0.0027 |  |
| [LLM Gateway](https://llmgateway.io/docs) | luminal/deepseek-v4.1-flash | $0.135 | $0.54 | $0.0027 |  |
| [LLM Gateway](https://llmgateway.io/docs) | reka-ai/deepseek-v4.1-flash | $0.135 | $0.54 | $0.007 |  |
| [LLM Gateway](https://llmgateway.io/docs) | consensusprotocol/deepseek-v4.1-flash | $0.15 | $0.55 | $0.005 |  |
| [CommandCode](https://commandcode.ai/docs/provider) | deepseek/deepseek-v4.1-flash-fast | $0.16 | $0.58 | $0.016 |  |
| [302.AI](https://doc.302.ai) | deepseek-flash | $0.15 | $0.6 | $0.003 |  |
| [ClinePass](https://docs.cline.bot/getting-started/clinepass) | cline-pass/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [CommandCode](https://commandcode.ai/docs/provider) | deepseek/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [Eden AI](https://docs.edenai.co) | qwen/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [Eden AI](https://docs.edenai.co) | tencent/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [LLM Gateway](https://llmgateway.io/docs) | runware/deepseek-v4.1-flash | $0.15 | $0.6 | $0.01 |  |
| [LLM Gateway](https://llmgateway.io/docs) | scx-ai-gp/deepseek-v4.1-flash | $0.15 | $0.6 | $0.01 |  |
| [LLM Gateway](https://llmgateway.io/docs) | tencent/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | deepseek/deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [Ollama Cloud](https://docs.ollama.com/cloud) | deepseek-v4.1-flash | $0.15 | $0.6 | $0.003 |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | deepseek/deepseek-flash | $0.15 | $0.6 | $0.003 |  |
| [Vultr](https://api.vultrinference.com/) | deepseek-v4.1-flash | $0.15 | $0.6 | — |  |
| [AIHubMix](https://docs.aihubmix.com) | deepseek-v4.1-flash | $0.155 | $0.62 | $0.0031 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | deepseek-ai/DeepSeek-V4.1-Flash | $0.13 | $0.65 | $0.002 |  |
| [Deep Infra](https://deepinfra.com/models) | deepseek-ai/DeepSeek-V4.1-Flash | $0.2 | $0.6 | $0.006 |  |
| [Eden AI](https://docs.edenai.co) | deepinfra/deepseek-ai/DeepSeek-V4.1-Flash | $0.2 | $0.6 | $0.006 |  |
| [LLM Gateway](https://llmgateway.io/docs) | deepinfra/deepseek-v4.1-flash | $0.2 | $0.6 | $0.006 |  |
| [above.dev](https://above.dev/docs) | deepseek-v4.1-flash | $0.165 | $0.66 | $0.0033 |  |
| [IteraCompute](https://iteracompute.com/docs.html) | deepseek/deepseek-v4-flash-0731 | $0.17 | $0.7 | $0.005 |  |
| [IteraCompute](https://iteracompute.com/docs.html) | deepseek/deepseek-v4.1-flash | $0.17 | $0.7 | $0.005 |  |
| [Arcee](https://docs.arcee.ai) | deepseek/deepseek-v4.1-flash | $0.22 | $0.66 | $0.007 | Beta |
| [LLM Gateway](https://llmgateway.io/docs) | fireworks/deepseek-v4.1-flash | $0.22 | $0.66 | $0.007 |  |
| [Morph](https://docs.morphllm.com/api-reference/introduction) | morph-dsv41flash | $0.12 | $0.8 | $0.008 |  |
| [Fireworks AI](https://fireworks.ai/docs/) | accounts/fireworks/routers/deepseek-v4p1-flash-spot | $0.21 | $0.84 | $0.0042 |  |
| [Boundless](https://inference.boundless.network/models) | deepseek-v4.1-flash | $0.2 | $1 | $0.01 |  |
| [Vancine](https://vancine.com/docs) | deepseek-v4.1-flash | $0.24 | $0.96 | $0.0048 |  |
| [Prime Inference](https://docs.primeintellect.ai/inference/overview) | deepseek/deepseek-v4.1-flash | $0.039 | $1.2 | $0.0012 |  |
| [Melious](https://melious.ai/docs/reference/models) | deepseek-v4.1-flash | $0.223 | $1.115 | $0.01115 |  |
| [AKI.IO](https://aki.io/docs/) | deepseek-v4.1-flash-552b | $0.280375 | $1.1215 | $0.11215 |  |
| [CoralBricks](https://www.coralbricks.ai/docs) | deepseek-v4.1-flash-fast | $0.25 | $1.2 | $0.005 |  |
| [Eden AI](https://docs.edenai.co) | greenpt/deepseek-v4.1-flash | $0.244794 | $1.22397 | $0.01224 |  |
| [Alibaba (China)](https://www.alibabacloud.com/help/en/model-studio/models) | deepseek-v4.1-flash | $0.29754 | $1.19015 | $0.01488 |  |
| [AI/ML API](https://docs.aimlapi.com) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [Azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 | Beta |
| [Azure Cognitive Services](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 | Beta |
| [Baseten](https://docs.baseten.co/inference/model-apis/overview) | deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.007 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | deepseek-v4.1-flash | $0.3 | $1.2 | $0.075 |  |
| [CrossModel](https://www.crossmodel.ai/docs) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [DigitalOcean](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) | deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [Eden AI](https://docs.edenai.co) | arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.075 |  |
| [Eden AI](https://docs.edenai.co) | together_ai/deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.006 |  |
| [Fireworks AI](https://fireworks.ai/docs/) | accounts/fireworks/models/deepseek-v4p1-flash | $0.3 | $1.2 | $0.006 |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | — |  |
| [Kilo Gateway](https://kilo.ai) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [LLM Gateway](https://llmgateway.io/docs) | alibaba/deepseek-v4.1-flash | $0.3 | $1.2 | $0.03 |  |
| [LLM Gateway](https://llmgateway.io/docs) | baidu/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [LLM Gateway](https://llmgateway.io/docs) | together-ai/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [Modal](https://modal.com/docs/guide/endpoints) | deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.03 |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [Ofox](https://ofox.ai/docs) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [Together AI](https://docs.together.ai/docs/serverless-models) | deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.006 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | deepseek/deepseek-v4.1-flash | $0.3 | $1.2 | $0.007 |  |
| [Wally](https://docs.runanywhere.ai/wally-cloud/api) | deepseek-v4.1-flash | $0.3 | $1.2 | $0.006 |  |
| [GreenPT](https://docs.greenpt.ai) | deepseek-v4.1-flash | $0.255552 | $1.27776 | $0.012778 |  |
| [Vivgrid](https://docs.vivgrid.com/models) | deepseek-v4.1-flash | $0.31 | $1.23 | $0.01 |  |
| [Synthetic](https://synthetic.new/pricing) | hf:deepseek-ai/DeepSeek-V4.1-Flash | $0.6 | $1.2 | $0.03 |  |
| [Eden AI](https://docs.edenai.co) | tensorx/deepseek/deepseek-v4.1-flash | $0.5 | $1.5 | $0.125 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | deepseek-v4.1-flash | $0.5 | $1.5 | $0.05 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | deepseek-v4.1-flash@eu | $0.5 | $1.5 | $0.05 |  |
| [TensorX](https://docs.tensorx.ai/) | deepseek/deepseek-v4.1-flash | $0.5 | $1.5 | $0.13 |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/deepseek-v4.1-flash | $0.6 | $1.45 | $0.01 |  |
| [Tinfoil](https://docs.tinfoil.sh) | deepseek-v4-1-flash | $0.6 | $1.45 | $0.01 | Beta |
| [Eden AI](https://docs.edenai.co) | scaleway/deepseek-v4.1-flash | $0.669 | $2.007 | $0.1338 |  |
| [Baseten](https://docs.baseten.co/inference/model-apis/overview) | deepseek-ai/DeepSeek-V4.1-Flash-Fast | $0.6 | $2.4 | $0.014 |  |
| [Inco](https://platform.inco.ai/docs) | deepseek-v4.1-flash:fast | $0.6 | $2.4 | $0.012 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | deepseek/deepseek-v4.1-flash-fast | $0.6 | $2.4 | $0.014 |  |
| [Wally](https://docs.runanywhere.ai/wally-cloud/api) | deepseek-v4.1-flash-fast | $0.6 | $2.4 | $0.014 |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | deepseek-ai/DeepSeek-V4.1-Flash:peft:262144 | $0.6 | $3.6 | $0.12 |  |
| [above.dev](https://above.dev/docs) | deepseek-v4-flash | $0.165 | $0.66 | $0.0033 | Deprecated |
| [Neon](https://neon.com/docs) | deepseek-v4-1-flash | $0.3 | $1.2 | $0.03 | Deprecated |
| [Venice AI](https://docs.venice.ai) | deepseek-v4-1-flash | $0.3 | $1.2 | $0.0075 | Deprecated |
| [Alibaba Token Plan](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview) | deepseek-v4.1-flash | $0 | $0 | $0 |  |
| [Alibaba Token Plan (China)](https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview) | deepseek-v4.1-flash | $0 | $0 | $0 |  |
| [NaN](https://nan.builders/docs/models) | deepseek-v4-flash | $0 | $0 | — |  |
| [Nvidia](https://docs.api.nvidia.com/nim/) | deepseek-ai/deepseek-v4.1-flash | $0 | $0 | — |  |
| [SCNet Token Plan](https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html) | DeepSeek-V4.1-Flash | $0 | $0 | $0 |  |
| [SenseNova (China)](https://platform.sensenova.cn/docs) | deepseek-v4.1-flash | $0 | $0 | $0 |  |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/deepseek/deepseek-v4.1-flash/