AI Gateway Ecosystem
Connect your applications to hundreds of leading AI models with a single unified API.
SpaceXAI
Access the latest advanced models and proprietary frameworks through our infrastructure.
OpenAI
Utilize state-of-the-art GPT models seamlessly integrated into your current development workflow.
Anthropic
Deploy powerful Claude models for complex reasoning tasks with standardized endpoint access.
Gemini
Scale your production applications using Google's versatile and multimodal intelligence capabilities.
OSS Models
Experiment with top-tier open source architectures like Hermes and OpenCode with ease.
Unified Integration
Stream text, image, and audio content using one consistent API format across all providers.
Developer Tooling
Streamline your development process with SDKs optimized for rapid deployment and testing.
Global Access
Get an API key today and start building the future of AI applications with full reliability.
No markup on tokens
0%
Pay provider prices, never a cent more.
Invoicing is available with no payment processing fees. See the AI Gateway pricing docs.
Ongoing promotions
Explore free and discounted models on AI Gateway. Promotional pricing applies automatically at request time. 21 live now.
TypeSafe AI
Reliable model platform offering secure and consistent performance for your technical infrastructure.
SpaceXAI
$2/M$1.20/M
$6/M$3.60/M
Tako
Advanced search engine capabilities optimized for speed and semantic accuracy across large datasets.
Jev
Efficient AI model optimized for deployment, currently available at no cost for standard users.
Grok 4.7
GLM 5.3 FlashZ.AI-50%$0.15/M$0.08/M$0.50/M$0.25/MTextGemini 3.8 FlashGoogle-50%$1.50/M$0.75/M$7.50/M$3.75/MTextGLM 5.2Z.AI-35%$0.75/M$0.49/M$2.40/M$1.56/MTextGemini 3.7 FlashGoogle-50%$1.50/M$0.75/M$7.50/M$3.75/MTextMiMo M2.5Xiaomi-15%$0.14/M$0.12/M$0.28/M$0.24/MTextMiniMax M3MiniMax-20%$0.30/M$0.24/M$1.20/M$0.96/MTextLaguna S 2.1PoolsideFree$0$0TextMiMo V2.5 ProXiaomi-30%$0.44/M$0.30/M$0.87/M$0.61/MText
Tako Search
High-performance search technology designed for scale, now accessible with a free usage tier.
Availability strategy
Max
Cost efficiency
Opt
Latency control
Low
Claude Fable 5.1
Auth
Provider Status
Fail
Primary model
Main
Fallback option
Auto
Bedrock engine
AWS
Infrastructure to build, scale, and secure a faster web.
No markup, just fair prices. Pay exactly what providers charge with no hidden platform fees for your infrastructure.
Our Services
Works with your existing AI stack
AI Gateway Integrations
Move existing OpenAI, Anthropic, and AI SDK integrations to AI Gateway with a base URL swap.
- X_AI_API_KEY
- ANTHROPIC_API_KEY
- OPEN_AI_API_KEY
+ AI_GATEWAY_API_KEY
Grok 4.7 Update
Grok 4.7 is now available on AI Gateway with 40% off on specific services. Read more about the release from 21 September.
View DetailsGLM 5.3 FlashX
GLM 5.3 FlashX is now available on the AI Gateway. Check out the latest performance improvements released on 18 September.
View DetailsGPT-Live 1 Launch
GPT-Live 1 is now available on AI Gateway. Experience real-time interactions with the new model deployed on 17 September.
View DetailsFull Changelog
Stay updated with our latest releases and technical improvements. Browse the complete history of our development changelogs.
View AllHow Zo Computer improved AI reliability 20×
Rob Cheung, Co-founder
20x
Improvement in AI reliability after switching
30s
To adopt a new model, down from an hour
25%
Improvement in average latency on model calls
Security and compliance
Route only to ZDR providers, no training or prompt logging, configurable per request or team-wide.
Take control
Manage usage across teams with budgets, quotas, and full request visibility.
API key management
Create, view, and delete keys from the dashboard, CLI, or API.
Dashboard observability
Usage, spend, requests, TTFT, and token counts at team and project scope.
Live on AWS Marketplace
Buy with private offers, using your existing cloud commits.
Every modality you need
Text, image, video, realtime, speech, transcription, embeddings, and reranking through one endpoint.
Works with the tools your team already uses
Route 11+ AI coding agents through AI Gateway. Get unified observability and tracking.
Anthropic’s coding agent. Route it through AI Gateway’s Anthropic-compatible endpoint, then switch between Claude models mid-session.
OpenAI’s coding agent. Route it through AI Gateway’s Responses API so usage joins the rest of your AI spend, and pick a model.
Terminal coding agent with bring your own key support. Add your AI Gateway key and a custom base URL to switch models.
Open-source terminal coding agent with native AI Gateway support. Connect once, then switch between any model on the fly.
Autonomous coding agent for VS Code. Select Vercel AI Gateway as the provider for detailed token and cache metrics.
Terminal CLI for AI code generation and debugging, with access to every model in the catalog.
Get started
This quickstart walks you through making your first text generation request with AI Gateway.
Frequently asked questions
We offer tokens at list price from the upstream providers with no markup, including when you bring your own keys. Certain capabilities are available at higher plan tiers and metered separately. Invoicing is available with no payment processing fees. See the pricing page for details.
AI Gateway gives you one integration, automatic failover, unified spend tracking, and one invoice across every major provider. Going direct means signing N contracts and stitching together N billing dashboards.
Almost certainly. AI Gateway supports the AI SDK, OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and an OpenResponses-compatible endpoint. Migrating is typically a base URL swap with no code changes.
Text, image, video, embeddings, and reranking, all through the same endpoint. Browse the full model catalog for specific models and providers.
AI Gateway supports Zero Data Retention routing, a no-training guarantee, and team-wide provider allowlists. See the security overview for full details.
A dashboard with usage, spend, request volume, TTFT, and token counts, broken down by model, provider, and project. For deeper analysis, the Custom Reporting API lets you pull the same data into your own tools.
Yes, through BYOK. Bring your own keys for almost every supported provider and your existing commitments flow through. We try BYOK first and only fall back to system credentials on failure.
AI Gateway uses pre-purchased credits by default. Top up in the dashboard and usage is drawn down per request. Enterprise customers can switch to a single consolidated invoice from Vercel covering every provider in their routing pool. For invoicing, reach out to sales for more details.
Yes. AI Gateway is live on AWS Marketplace and available to purchase via AWS private offers. Procure it directly through AWS Marketplace and apply the spend toward your existing AWS cloud commits, within your existing budgets and procurement processes.