[DeepSeek](/ai-gateway/models/labs/deepseek) # DeepSeek V3 0324 DeepSeek V3 0324 is DeepSeek's open-source 671B Mixture-of-Experts language model released December 26, 2024. It achieves 3x the inference throughput of DeepSeek-V2 while matching closed-source models in published benchmark evaluations. 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. Tool Use [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-v3', 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-v3) [API](/ai-gateway/models/deepseek-v3/api) [About](/ai-gateway/models/deepseek-v3/about) [Providers](/ai-gateway/models/deepseek-v3/providers) [Throughput](/ai-gateway/models/deepseek-v3/throughput) [Latency](/ai-gateway/models/deepseek-v3/latency) [Uptime](/ai-gateway/models/deepseek-v3/uptime) [Status](/ai-gateway/models/deepseek-v3/status) [Similar](/ai-gateway/models/deepseek-v3/similar) [FAQ](/ai-gateway/models/deepseek-v3/faq) ## [Copy link to heading](#playground)Playground Try out DeepSeek V3 0324 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 V3 0324 ![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 V3 0324 ## [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. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![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) | 164K | 164K | 1.3s | 39tps | $0.27/M | $1.12/M | Read:$0.14/M Write:— | — | | | | 12/26/2024 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ## [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-pro-0813](/ai-gateway/models/deepseek-v4-pro-0813) | 1M | 0.6s | 179tps | $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 | 0.3s | 163tps | $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-flash](/ai-gateway/models/deepseek-v4-flash) | 1M | 1.0s | 160tps | $0.09/M | $0.18/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) ![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) +7 | | | 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-v4-pro](/ai-gateway/models/deepseek-v4-pro) | 1M | 0.5s | 156tps | $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 | 113tps | $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 | 1.0s | 44tps | $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-v3-0324)About DeepSeek V3 0324 DeepSeek V3 0324 was released December 26, 2024 as the third major iteration of DeepSeek's general-purpose language model line. It uses a sparse Mixture-of-Experts (MoE) architecture with 671B total parameters and 37B active per forward pass. Inference compute scales with the 37B active parameters rather than the full 671B, so throughput is roughly 3x that of DeepSeek-V2. Live throughput metrics appear on this page. The context window of 163.8K tokens was validated through Needle In A Haystack (NIAH) evaluations across the full range, confirming reliable retrieval rather than nominal coverage. The research paper and model weights are openly published. DeepSeek V3 0324 maintains full API backward compatibility with earlier DeepSeek integrations, reducing migration effort for teams upgrading from V2. Performance evaluations place it on par with closed-source models across knowledge, reasoning, code, and language understanding benchmarks. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: DeepSeek V3 0324's context window of 163.8K tokens supports long-document tasks. Plan output token budgets carefully for summarization and report generation, which can produce lengthy completions. - Zero Data Retention: Zero Data Retention 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-v3-0324)When to Use DeepSeek V3 0324 ### Best for - General-purpose language tasks: Summarization, question answering, code generation, and translation where broad capability matters more than specialization - High-throughput production pipelines: Fast token generation lowers latency and cost compared to slower alternatives of comparable quality (see live metrics on this page) - Long-document workflows: The context window of 163.8K tokens processes contracts, research papers, or large codebases in a single request - Upgrading from DeepSeek V2: API backward compatibility minimizes integration work when migrating ### Consider alternatives when - Deep multi-step reasoning: Use DeepSeek-R1 for extended chain-of-thought and math/code reasoning workloads - Hybrid thinking and tools: DeepSeek-V3.1 or later adds thinking and tool-use support on top of V3's foundation - Extremely long outputs: Tasks requiring output beyond the model's per-request limit need a larger-output alternative - Newer V3 capabilities: Newer V3 iterations may better suit rapidly evolving requirements beyond what V3 offers ## [Copy link to heading](#conclusion)Conclusion DeepSeek V3 0324 set the baseline for open-source language models that compete with closed releases on published benchmarks. It remains DeepSeek's V3 baseline for general-purpose production when you need backward compatibility, open weights, and API parity with earlier DeepSeek integrations.