[DeepSeek](/ai-gateway/models/labs/deepseek) # Deepseek V4 Flash Deepseek V4 Flash is DeepSeek's April 23, 2026 efficiency-tier model in the V4 series. It pairs a hybrid attention architecture with a context window of 1.0M tokens and supports reasoning, tool use, and implicit caching. Your use is subject to DeepSeek's [Terms](https://cdn.deepseek.com/policies/en-US/deepseek-terms-of-use.html) & [Privacy](https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html) Policies. ReasoningTool UseImplicit Caching [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) AI SDKChat CompletionsMessagesResponses ``` 1import { streamText } from 'ai' 2 3const result = streamText({ 4 model: 'deepseek/deepseek-v4-flash', 5 prompt: 'Why is the sky blue?' 6}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/deepseek-v4-flash) [API](/ai-gateway/models/deepseek-v4-flash/api) [About](/ai-gateway/models/deepseek-v4-flash/about) [Providers](/ai-gateway/models/deepseek-v4-flash/providers) [Throughput](/ai-gateway/models/deepseek-v4-flash/throughput) [Latency](/ai-gateway/models/deepseek-v4-flash/latency) [Uptime](/ai-gateway/models/deepseek-v4-flash/uptime) [Status](/ai-gateway/models/deepseek-v4-flash/status) [Similar](/ai-gateway/models/deepseek-v4-flash/similar) [FAQ](/ai-gateway/models/deepseek-v4-flash/faq) ## [Copy link to heading](#playground)Playground Try out Deepseek V4 Flash by DeepSeek. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days. ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75)Deepseek V4 Flash ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=96&q=75) Deepseek V4 Flash ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. Token prices are 2× during 01:00–04:00 and 06:00–10:00 UTC. Listed prices are the off-peak rate. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![digitalocean logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdigitalocean.png%3Fv%3D1784246703962&w=48&q=75) [DigitalOcean](/ai-gateway/models/providers/digitalocean) Legal:[Terms](https://www.digitalocean.com/legal/terms-of-service-agreement)•[Privacy](https://www.digitalocean.com/legal/privacy-policy) | 262K | 52K | 0.5s | 187tps | $0.11/M | $0.22/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [DeepSeek](/ai-gateway/models/providers/deepseek) Legal:[Terms](https://cdn.deepseek.com/policies/en-US/deepseek-terms-of-use.html)•[Privacy](https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html) | 1M | 384K | 10.1s | 105tps | $0.22/M | $0.66/M | Read:$0.01/M Write:— | — | | | | 04/23/2026 | | | ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) [Novita AI](/ai-gateway/models/providers/novita) Legal:[Terms](https://novita.ai/legal/terms-of-service)•[Privacy](https://novita.ai/legal/privacy-policy) | 1M | 393K | 1.5s | 95tps | $0.14/M | $0.28/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | | ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) [DeepInfra](/ai-gateway/models/providers/deepinfra) Legal:[Terms](https://deepinfra.com/terms)•[Privacy](https://deepinfra.com/privacy) | 1M | 1M | 1.7s | 84tps | $0.09/M | $0.18/M | Read:$0.02/M Write:— | — | | | | 04/23/2026 | | | ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) [Fireworks](/ai-gateway/models/providers/fireworks) Legal:[Terms](https://fireworks.ai/terms-of-service)•[Privacy](https://fireworks.ai/privacy-policy) | 1M | 384K | 1.4s | 115tps | $0.14/M | $0.28/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | | ![azure logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fazure.png&w=48&q=75) [Azure](/ai-gateway/models/providers/azure) Legal:[Terms](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/code-of-conduct)•[Privacy](https://privacy.microsoft.com/en-us/privacystatement) | 1M | 128K | 8.7s | 22tps | $0.19/M | $0.51/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) [Alibaba Cloud](/ai-gateway/models/providers/alibaba) Legal:[Terms](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0)•[Privacy](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy) | 1M | 384K | 5.2s | 107tps | $0.20/M | $0.40/M | Read:$0.04/M Write:— | — | | | | 04/23/2026 | | | ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) [Baseten](/ai-gateway/models/providers/baseten) Legal:[Terms](https://www.baseten.co/terms-and-conditions/)•[Privacy](https://www.baseten.co/privacy-policy/) | 1M | 384K | 0.8s | 115tps | $0.13/M | $0.26/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | | ![wafer logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fwafer.png&w=48&q=75) [Wafer](/ai-gateway/models/providers/wafer) Legal:[Terms](https://www.wafer.ai/terms)•[Privacy](https://www.wafer.ai/privacy-policy) | 1M | 1M | 2.1s | 221tps | $0.28/M | $0.56/M | Read:$0.07/M Write:— | — | | | | 04/23/2026 | | | ![gmicloud logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgmicloud.png%3Fv%3D1785888489595&w=48&q=75) [GMICloud](/ai-gateway/models/providers/gmicloud) Legal:[Terms](https://www.gmicloud.ai/en/terms-and-conditions)•[Privacy](https://www.gmicloud.ai/en/privacy-policy) | 1M | 384K | 1.8s | 127tps | $0.13/M | $0.25/M | Read:$0.03/M Write:— | — | | | | 04/23/2026 | | ## [Copy link to heading](#throughput)Throughput24 hours 1W 1D P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#latency)Latency24 hours 1W 1D P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#uptime)Uptime24 hours 1W 1D 1H Direct request success rate on AI Gateway and per-provider. Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/uptime) for more info. 1W 1D 1H ## [Copy link to heading](#more-models-by-deepseek)More models by DeepSeek All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-flash-vision-exp](/ai-gateway/models/deepseek-v4-flash-vision-exp) | 1M | 1.5s | 114tps | $0.22/M | $0.66/M | Read:$0.01/M Write:— | — | +1 | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) | | | 08/21/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-pro-0813](/ai-gateway/models/deepseek-v4-pro-0813) | 1M | 0.7s | 99tps | $0.66/M | $1.98/M | Read:$0.02/M Write:— | — | | ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) +1 | | | 08/12/2026 | | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-flash-0731](/ai-gateway/models/deepseek-v4-flash-0731) | 1M | 0.4s | 216tps | $0.08/M | $0.15/M | Read:$0.01/M Write:— | — | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) +7 | | | 07/31/2026 | | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-pro](/ai-gateway/models/deepseek-v4-pro) | 1M | 0.4s | 162tps | $0.66/M | $1.98/M | Read:$0.02/M Write:— | — | | ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%2520cloud.png&w=48&q=75) ![azure logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fazure.png&w=48&q=75) ![baseten logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fbaseten.png&w=48&q=75) +5 | | | 04/23/2026 | | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v3.2](/ai-gateway/models/deepseek-v3.2) | 164K | 0.6s | 100tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) +1 | | | 12/01/2025 | | | ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v3.2-thinking](/ai-gateway/models/deepseek-v3.2-thinking) | 164K | 0.6s | 39tps | $0.26/M | $0.38/M | Read:$0.13/M Write:— | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) | | | 12/01/2025 | | ## [Copy link to heading](#about-deepseek-v4-flash)About Deepseek V4 Flash Deepseek V4 Flash was released April 23, 2026 as part of DeepSeek's V4 generation. The V4 series introduces a hybrid attention architecture that combines Compressed Sparse Attention (CSA) with Heavily Compressed Attention (HCA), along with ManifoldConstrained Hyper-Connections (mHC) that refine standard residual connections. The combination targets efficient long-context inference at the 1.0M tokens window. Deepseek V4 Flash positions as the efficiency tier of the V4 lineup. It handles instruction following, classification, short-form Q&A, and other tasks where latency and per-token cost matter more than maximum reasoning depth. Maximum output is 1.0M tokens, the same budget as DeepSeek V4 Pro, so single-call response length is not the differentiator. The split between Flash and Pro is about capability depth and cost. Deepseek V4 Flash supports tool use and reasoning, and the model is tagged for implicit caching. Implicit caching reduces input-token charges for repeated prefixes without requiring explicit cache-control headers in the request. Access is through AI Gateway with an AI Gateway API key or OIDC token, so you don't need a separate DeepSeek platform account. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: Deepseek V4 Flash is tuned for speed and cost on shorter tasks. If your workload involves multi-step reasoning, complex agentic flows, or long synthesis chains, DeepSeek V4 Pro is the better fit within the same generation. - Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-deepseek-v4-flash)When to Use Deepseek V4 Flash ### Best for - High-volume classification: Routing and short-answer pipelines where $0.09 input and $0.18 output keep unit economics tight - Short-form instruction following: Summarization of short inputs, structured extraction, and rewriting tasks without multi-step planning - Front-line agent steps: Intent detection and parameter parsing before handing off to a deeper-reasoning model - Implicit caching workloads: Long, repeated system prompts across many calls benefit from cached input pricing ### Consider alternatives when - Complex agent orchestration: Use DeepSeek V4 Pro within the same generation for multi-step reasoning and tool planning - Earlier-generation pricing: DeepSeek V3 family models may be lower cost when the 1.0M tokens window or V4 capabilities aren't required - Dedicated deep reasoning: DeepSeek-R1 remains the open-weights reasoning specialist for extended chain-of-thought workloads ## [Copy link to heading](#conclusion)Conclusion Deepseek V4 Flash is the efficiency tier of the V4 generation, suited to high-volume short-form tasks where cost and latency dominate. For deeper reasoning and agentic workflows within the same generation, step up to DeepSeek V4 Pro.