Vercel AI Gateway
Researched 1d agoGatewayVercel
Vercel AI Gateway offers 234 tracked models (179 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts. 67 retired models are listed below.
Covers 7 workload areas across 234 available models and 67 retired; last verified 2026-11-18.
Use it for
- Teams comparing token and batch pricing across this provider's models
- Operators routing coding, rag, and agents workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
234
Models available through this provider
Priced output routes
179
Models with output token pricing tracked
Cheapest output
$0.030
Mistral NeMo Instruct (2407) on this route
Batch-ready models
0
No batch pricing tracked
Latest model release
2026-11-18
1d since newest release
Freshness
2026-11-18
Researched 1d ago
Information
Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more. Pricing is pass-through at provider list rates with zero markup. Includes $5/month free tier; paid is pay-as-you-go. Features: automatic provider fallbacks, unified observability, streaming, tool use, vision, embeddings, image/video generation, BYOK mode. Integrates via @ai-sdk/gateway package or plain model ID strings in Vercel AI SDK.
Where this host wins
- Coding: 84 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 123 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 126 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 137 tracked models with context-token or InfiniteBench-class signal.
Getting started
Platform Overview
Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more. Pricing is pass-through at provider list rates with zero markup. Includes $5/month free tier; paid is pay-as-you-go. Features: automatic provider fallbacks, unified observability, streaming, tool use, vision, embeddings, image/video generation, BYOK mode. Integrates via @ai-sdk/gateway package or plain model ID strings in Vercel AI SDK. API details: API key via Authorization: Bearer <AI_GATEWAY_API_KEY>.
Available Models(234)
View all →All models available as Serverless
| Model | List price |
|---|---|
| — | |
| — | |
| — | |
| — | |
| — | |
| — | |
| — | |
| — | |
| — | |
| — |
Retired models(67)
View all →| Model | List price |
|---|---|
Mercury 2.5Deprecated Retired November 15, 2026 | — |
Kimi K2.6Deprecated Scheduled retirement: December 31, 2026 | — |
Qwen3.6 Max PreviewDeprecated Retired October 10, 2026 | — |
Trinity-Large-ThinkingDeprecated Retired November 2, 2026 | — |
KAT Coder Pro V2Deprecated Retired November 2, 2026 | — |
MiMo-V2-ProDeprecated Retired November 2, 2026 | — |
MiniMax M2.7 HighspeedDeprecated Retired November 18, 2026 | — |
Gemini 3.1 Flash Lite PreviewDeprecated Retired May 25, 2026 | — |
GPT-5.3 ChatDeprecated Retired August 10, 2026 | — |
Retired June 25, 2026 | — |