[OpenAI](/ai-gateway/models/labs/openai) # GPT-4o GPT-4o is OpenAI's first natively multimodal "omni" model, unifying text, audio, image, and video processing within a single end-to-end trained architecture and delivering audio response times averaging 320 milliseconds, comparable to human conversational latency. Your use is subject to OpenAI's [Terms](https://openai.com/policies/terms-of-use) & [Privacy](https://openai.com/policies/privacy-policy) Policies. File InputImplicit CachingTool UseVision (Image)Web Search [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: 'openai/gpt-4o', 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/gpt-4o) [API](/ai-gateway/models/gpt-4o/api) [About](/ai-gateway/models/gpt-4o/about) [Providers](/ai-gateway/models/gpt-4o/providers) [Throughput](/ai-gateway/models/gpt-4o/throughput) [Latency](/ai-gateway/models/gpt-4o/latency) [Uptime](/ai-gateway/models/gpt-4o/uptime) [Status](/ai-gateway/models/gpt-4o/status) [Similar](/ai-gateway/models/gpt-4o/similar) [FAQ](/ai-gateway/models/gpt-4o/faq) ## [Copy link to heading](#playground)Playground Try out GPT-4o by OpenAI. 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. ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75)GPT-4o ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=96&q=75) GPT-4o ## [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 | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![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) | 128K | 16K | 0.6s | 148tps | $2.50/M | $10/M | Read:$1.25/M Write:— | $14/K \+ input costs | +2 | | | | 05/13/2024 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [OpenAI](/ai-gateway/models/providers/openai) Legal:[Terms](https://openai.com/policies/terms-of-use)•[Privacy](https://openai.com/policies/privacy-policy) | 128K | 16K | 0.6s | 86tps | $2.50/M+1 more | $10/M+1 more | Read:$1.25/M+1 more Write:— | $10/K \+ input costs | +2 | | | | 05/13/2024 | | ## [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-openai)More models by OpenAI All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Free Tier | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt-5.6-luna](/ai-gateway/models/gpt-5.6-luna) | 1.1M | 1.1s | 192tps | $0.20/MFast $0.40/M+1 more | $1.20/MFast $2.40/M+1 more | Read: $0.02/M+1 more Write: $0.25/M+1 more | $10/K \+ input costs | +4 | ![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) ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 07/09/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt\-5.6-sol](/ai-gateway/models/gpt-5.6-sol) | 1.1M | 2.2s | 147tps | $4/M$2/M Fast $4/M+1 more | $20/M$10/M Fast $20/M+1 more | Read: $0.40/M$0.20/M+1 more Write: $5/M$2.50/M+1 more | $10/K \+ input costs | +4 | ![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) ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 07/09/2026 | | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt-5.6-terra](/ai-gateway/models/gpt-5.6-terra) | 1.1M | 2.2s | 110tps | $2/MFast $4/M+1 more | $12/MFast $24/M+1 more | Read: $0.20/M+1 more Write: $2.50/M+1 more | $10/K \+ input costs | +4 | ![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) ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 07/09/2026 | | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt-5.5](/ai-gateway/models/gpt-5.5) | 1M | 0.5s | 101tps | $5/MFast $12.50/M+1 more | $30/MFast $75/M+1 more | Read: $0.50/M+1 more Write: — | $10/K \+ input costs | +4 | ![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) ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 04/24/2026 | | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt-5.4](/ai-gateway/models/gpt-5.4) | 1.1M | 2.0s | 88tps | $2.50/MFast $5/M+1 more | $15/MFast $30/M+1 more | Read: $0.25/M+1 more Write: — | $10/K \+ input costs | +4 | ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 03/05/2026 | | | ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) [openai/gpt-5-nano](/ai-gateway/models/gpt-5-nano) | 400K | 4.4s | 196tps | $0.05/M | $0.40/M | Read:$0.005/M Write:— | $14/K \+ input costs | +3 | ![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) ![openai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fopenai.png&w=48&q=75) | | | | 08/07/2025 | | ## [Copy link to heading](#about-gpt-4o)About GPT-4o GPT-4o was announced on May 13, 2024 at OpenAI's Spring Updates event. The "o" stands for "omni," reflecting the model's foundational design: rather than connecting separate specialist models for different modalities, GPT-4o was trained end-to-end across text, audio, image, and video. This architectural choice enables sub-400-millisecond audio responses. Prior approaches chained a speech recognition model, a language model, and a text-to-speech model together, introducing latency at each boundary. GPT-4 Turbo-based voice averaged 5.4 seconds per turn. GPT-4o matched GPT-4 Turbo on text and code in English while costing less in the API, with notable improvements on non-English text. This made it the default for developers who previously used GPT-4 Turbo: an upgrade in multimodal capability at a lower price. The model accepts any combination of text, audio, image, and video as input and can generate text, audio, and image outputs. This flexibility spans real-time voice assistants, vision pipelines that analyze photographs or documents, and agents that process video frames alongside textual context. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: For applications that mix modalities (for example, a voice interface that also accepts image uploads), a single model endpoint simplifies both architecture and cost accounting compared to separate specialist models. - 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-gpt-4o)When to Use GPT-4o ### Best for - Real-time voice applications: Native audio processing eliminates pipeline latency between speech recognition, reasoning, and synthesis - Mixed-modality workflows: Processing both images and text together for visual question answering or document analysis with figures - Cost-efficient GPT-4 quality: Applications that need GPT-4-class text quality with lower API cost than GPT-4 Turbo - Multilingual applications: Products that benefit from GPT-4o's improved non-English text performance - Evolving multimodal products: Apps that may expand from text-only to multimodal inputs over time with a single model supporting that evolution ### Consider alternatives when - Maximum coding capability: GPT-4.1 benchmarks are meaningfully better for some coding use cases - Cost-driven workloads: GPT-4.1 mini provides sufficient quality at lower cost - Deep multi-step reasoning: The o-series reasoning models' chain-of-thought approach is superior for complex analytical problems ## [Copy link to heading](#conclusion)Conclusion GPT-4o introduced native omni-modal processing as a practical API capability, eliminating the latency penalties of chained pipeline architectures and matching GPT-4 Turbo quality at lower cost. For applications that need a single model to handle text, audio, and vision inputs reliably, it remains a strong foundation through AI Gateway.