Migrate from Vercel AI Gateway

Native AI SDK
OpenAI SDK
Anthropic SDK

// Before
import { generateText } from "ai";

const { text } = await generateText({
  model: "anthropic/claude-opus-4.7",
  prompt: "Say hello in one word",
});
// Auth read from AI_GATEWAY_API_KEY (or VERCEL_OIDC_TOKEN) in the environment

// After
import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const concentrate = createOpenAI({
  baseURL: "https://api.concentrate.ai/v1",
  apiKey: process.env.CONCENTRATE_API_KEY,
});

const { text } = await generateText({
  model: concentrate("anthropic/claude-opus-4-6"),
  prompt: "Say hello in one word",
});

# Before
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://ai-gateway.vercel.sh/v1",
    api_key=os.environ["AI_GATEWAY_API_KEY"],
)

# After
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.concentrate.ai/v1",
    api_key=os.environ["CONCENTRATE_API_KEY"],
)

Watch the base URL. On Vercel, the Anthropic SDK points at https://ai-gateway.vercel.sh with no /v1 (the SDK appends /v1/messages itself), while the OpenAI surfaces use …/v1. On Concentrate both surfaces share the same …/v1 base.

# Before
from anthropic import Anthropic
import os

client = Anthropic(
    base_url="https://ai-gateway.vercel.sh",
    api_key=os.environ["AI_GATEWAY_API_KEY"],
)

# After
# (Concentrate also exposes an Anthropic-compatible Messages API at /v1/messages.)
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.concentrate.ai/v1",
    api_key=os.environ["CONCENTRATE_API_KEY"],
)

Prerequisites

A Concentrate AI account with an active API key

An existing Vercel AI Gateway integration

This guide assumes you are calling AI Gateway from the AI SDK (@ai-sdk/gateway), the OpenAI SDK (Chat Completions or Responses), the Anthropic SDK, fetch, requests, or another HTTP client.

Quick Start for Claude Code users

If you use Claude Code, you can install a skill that walks through this migration interactively. It searches your project for AI Gateway usage, collapses the per-surface base URLs (including the Anthropic-base-URL trap), strips Vercel-specific headers, decomposes providerOptions.gateway, maps model slugs, and generates a verification script. Drop the skill into your ~/.claude/skills/ directory:

mkdir -p ~/.claude/skills/migrate-vercel && \
  curl -fsSL https://concentrate.ai/scripts/migrate-vercel.md \
  -o ~/.claude/skills/migrate-vercel/SKILL.md

Then start a Claude Code session in your project and ask it to “migrate from Vercel AI Gateway to Concentrate” or run /migrate-vercel. Claude will load the skill and run the steps.

If you were running Claude Code itself through AI Gateway (via ANTHROPIC_BASE_URL=https://ai-gateway.vercel.sh), point it at Concentrate instead. See the Claude Code integration guide.

Step 1: Update Your Environment Variables

Replace your AI Gateway key (and any BYOK provider keys) with a single Concentrate key:

# Before
export AI_GATEWAY_API_KEY="vck_..."
export BASE_URL="https://ai-gateway.vercel.sh/v1"

# After
export CONCENTRATE_API_KEY="sk-cn-v1-..."
export BASE_URL="https://api.concentrate.ai/v1"

If you authenticated with a Vercel OIDC token (VERCEL_OIDC_TOKEN, auto-provisioned on Vercel deployments and valid for ~12 hours), that mechanism does not carry over. Concentrate keys never expire unless revoked, so the process.env.AI_GATEWAY_API_KEY || process.env.VERCEL_OIDC_TOKEN fallback pattern collapses to a single CONCENTRATE_API_KEY. If you ran any BYOK credentials, you no longer need OPENAI_API_KEY, ANTHROPIC_API_KEY, AWS credentials, or any other upstream provider key.

Step 2: Update Your Client

The two big changes are collapsing the base URL onto https://api.concentrate.ai/v1 and dropping Vercel-specific headers and providerOptions.gateway fields. If you used the native @ai-sdk/gateway provider, swap to @ai-sdk/openai pointed at Concentrate. Concentrate does not ship a dedicated SDK because the OpenAI-compatible shape covers every endpoint.

Anthropic base-URL difference. Vercel’s Anthropic surface uses https://ai-gateway.vercel.sh with no /v1; the OpenAI surfaces use …/v1. Concentrate uses the same https://api.concentrate.ai/v1 base for every surface, so if you were special-casing the Anthropic base URL, remove that branch.

# Before
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://ai-gateway.vercel.sh/v1",
    api_key=os.environ["AI_GATEWAY_API_KEY"],
)

# After
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.concentrate.ai/v1",
    api_key=os.environ["CONCENTRATE_API_KEY"],
)

response = client.chat.completions.create(
    model="anthropic/claude-opus-4-6",
    messages=[{"role": "user", "content": "Say hello in one word"}],
)
print(response.choices[0].message.content)

Step 3: Remove Vercel-Specific Headers

None of AI Gateway’s custom headers carry over to Concentrate, so they should come out. They’re dead weight in your client config and mislead future readers. Expand the tables below for the full mapping if any of these are in your code.

Request header mapping

Vercel header	Concentrate replacement
`Authorization: Bearer vck_...`	Standard `Authorization: Bearer sk-cn-v1-...`
`x-api-key` (Anthropic surface only)	Standard `Authorization: Bearer sk-cn-v1-...`. Concentrate’s Messages API also accepts `x-api-key` for Anthropic-SDK compatibility
`http-referer` (app attribution)	Drop. No per-request app attribution; analytics roll up by key/team/org
`x-title` (app attribution)	Drop. No per-request app attribution
Auto-injected o11y headers (`VERCEL_DEPLOYMENT_ID`, `VERCEL_PROJECT_ID` via the AI SDK)	Drop. Concentrate records its own per-request telemetry in the dashboard

Response header mapping

Vercel response surface	Concentrate equivalent
`providerMetadata.gateway` (routing info, cost, service tier in the response body)	No body field. The resolved provider and cost are recorded per request in the dashboard
Request / trace id	`X-Request-Id` (Concentrate returns its own per-request id, surfaced in dashboard logs)
Rate-limit headers	Standard `X-RateLimit-*` headers. See Errors for 429 semantics

Step 4: Decompose Your `providerOptions.gateway`

AI Gateway layers routing, fallback, caching, and compliance controls onto the standard request body under providerOptions.gateway (and a few top-level fields). A naïve “just change the base URL” migration silently drops these. Concentrate has no providerOptions.gateway primitive. Each behavior is either on by default or expressed as a body param on the request. Expand the table below for the full mapping.

`providerOptions.gateway` key mapping

Vercel option	Concentrate equivalent
`order: [...]` (ordered provider fallback)	`routing.provider.fallbacks` (ordered)
`only: [...]` (allowed provider set)	Pin via the model slug (`provider/model-id`), or constrain with `routing.provider.fallbacks`
`sort: 'cost'`	`model: "auto"` with `routing.model.sort: "cost"`
`sort: 'ttft'` (time to first token)	`model: "auto"` with `routing.model.sort: "latency"`
`sort: 'tps'` (throughput)	`model: "auto"` with `routing.model.sort: "performance"`
`models: [...]` (model-level fallback chain)	`routing.model.fallbacks` (ordered)
`byok: { provider: [{...}] }` (request-scoped BYOK)	Drop. Concentrate owns provider credentials at no per-token BYOK fee
`providerTimeouts: {...}` (per-provider failover timeouts)	Automatic failover on any provider error across your fallback chain, plus the 90% per-feature uptime gate
`caching: 'auto'` (auto cache breakpoints)	Provider-native prompt caching on Anthropic + AWS Bedrock. Manual `cache_control: { type: 'ephemeral' }` is honored too
`zeroDataRetention: true`	Key-level Zero Data Retention, not a request param
`disallowPromptTraining: true`	Covered by ZDR-certified provider routing. Configure at the key level
`serviceTier: 'flex' \| 'priority'`	No equivalent today. Concentrate routes for uptime and latency automatically
`reasoning: { effort, max_tokens, ... }`	Pass reasoning controls in the standard request body. The Responses API normalizes reasoning across providers

Concentrate has conditional routing, but it conditions on request capabilities (feature support, ZDR flag, per-feature uptime, cache affinity), not on a per-request provider allow-list or sort key handed in the body. If your code relied on only/order/sort to steer specific requests, express the durable cases as routing.* body params or pin the model slug.

Step 5: Update Model Identifiers

Concentrate accepts model strings in two forms:

Bare slug, e.g. gpt-5.5, claude-haiku-4-5, auto. Routing picks a provider.
provider/model-id, e.g. bedrock/claude-haiku-4-5, openai/gpt-5.5. Pins the request to a specific provider.

Vercel always uses the provider/model form (e.g. anthropic/claude-opus-4.7, openai/gpt-5.5, xai/grok-4.3), so most strings carry over directly once you reconcile version suffixes against GET /v1/models. One thing to know about the slashed form: the prefix is the provider that serves the request, not the model’s author. For most popular names the two are the same string (openai, anthropic, mistral, cohere). They diverge whenever a model is hosted by something other than its author:

Author	Provider serving the request	Concentrate slug
Anthropic (`claude-haiku-4-5`)	Anthropic	`anthropic/claude-haiku-4-5`
Anthropic (same model, different host)	AWS Bedrock	`bedrock/claude-haiku-4-5`
Anthropic (same model, different host)	Azure	`azure/claude-haiku-4-5`
Google (`gemini-3.5-flash`)	Google AI Studio	`ai-studio/gemini-3.5-flash`
Meta (`llama-3-8b-instruct`)	AWS Bedrock	`bedrock/llama-3-8b-instruct`

Bare slugs work in all of these cases. Use them when you don’t care which provider serves the request. Use the provider/ prefix when you specifically want to pin to one host (for ZDR compliance, contractual reasons, or latency in a specific region). The only universally required slug change is auto-routing:

Vercel AI Gateway	Concentrate AI
`sort: 'cost' \| 'ttft' \| 'tps'` in `providerOptions.gateway`	`model: "auto"` with explicit `routing.model.sort` (`cost` / `latency` / `performance`)

For the authoritative list of supported provider/model-id pairs, call GET /v1/models or browse the Model Fortress.

Step 6: Reconnect Observability

Concentrate’s dashboard covers the major surfaces you used in the AI Gateway dashboard.

Vercel AI Gateway surface	Concentrate equivalent
Request logs (every routing decision, cost, outcome)	Per-request logs at concentrate.ai
Spend monitoring / budgets	Org / team / developer / key spend rollups and per-key spend limits
App attribution (`http-referer` / `x-title`)	No per-request attribution. Roll up by key/team/org
Routing metadata (`providerMetadata.gateway`)	Resolved provider recorded per request in the dashboard
Observability traces (Vercel Observability → AI)	Per-request logs; `previous_response_id` on the Responses API links related requests into a stateful tree
BYOK ($0 markup)	Not applicable. Concentrate owns provider credentials at no per-token BYOK fee

Exporting your AI Gateway history

Vercel’s dashboards do not import into Concentrate, and the reverse is also true. Historical request logs stay where they were created. If your migration is driven by compliance or audit requirements, export your history from the Vercel dashboard before deprovisioning.

Step 7 (Optional): Adopt the Responses API

If you used Vercel’s OpenAI Responses surface (or the native AI SDK), Concentrate’s native Responses API is the direct successor: it supports streaming, tool calling, structured output, multi-modal input, and web search through a single normalized shape across every provider, and previous_response_id links related requests into a server-managed conversation tree.

curl https://api.concentrate.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CONCENTRATE_API_KEY" \
  -d '{
    "model": "anthropic/claude-opus-4-6",
    "input": "What is the capital of France?"
  }'

Why migrate to Concentrate

How it works

AI Gateway exposes three request schemas across two base URLs, plus a native AI SDK provider. Migrating collapses all of them onto Concentrate’s single base URL https://api.concentrate.ai/v1.

Vercel surface	Vercel base URL
OpenAI Chat Completions	`https://ai-gateway.vercel.sh/v1`
OpenAI Responses	`https://ai-gateway.vercel.sh/v1`
Anthropic Messages	`https://ai-gateway.vercel.sh` (no `/v1`)
Native AI SDK (`@ai-sdk/gateway`)	resolved automatically from a plain string model id

Concentrate’s Responses API is the closest one-to-one target for Vercel’s Responses surface and the native AI SDK, reachable from the standard OpenAI SDK or any HTTP client.

Team-scale spend management

Concentrate organizes billing around an organization → team → developer → key hierarchy. Set budgets at any level and roll spend up into a single dashboard. Per-team budgets and per-developer attribution come from the key itself, so there’s no per-request http-referer / x-title attribution to maintain.

Feature-aware resiliency

Beyond ordered model and provider fallbacks (routing.model.fallbacks, routing.provider.fallbacks), Concentrate’s routing layer ships:

Uptime gate. Providers whose per-feature success rate drops below 90% are skipped.
Feature degradation. If no provider supports the full requested feature set (e.g. json_schema), the request is downgraded to json_object or text instead of failing.
Cache-affinity routing. When multiple providers can serve a request, the one where your actor already has cached tokens is preferred.

All on by default. No providerOptions.gateway block to author per request.

Strategy-driven auto routing

model: "auto" accepts an explicit optimization target via routing.model.sort: cost, latency, or performance (default). See Auto Routing. This maps cleanly onto Vercel’s sort metrics (cost / ttft / tps).

Native Responses and Messages APIs

Like AI Gateway’s Responses and Anthropic surfaces, Concentrate exposes a first-class Responses API and an Anthropic-compatible Messages API, both on the same …/v1 base, with no per-surface base-URL difference.

Managed provider credentials by default

Concentrate is BYOK-free. Point at a model and Concentrate owns the upstream credentials. Any provider keys you carried for AI Gateway’s BYOK mode can be retired after migrating, and like Vercel, there’s no per-token markup.

Troubleshooting

Model not found

Bare slugs (gpt-5.5, claude-haiku-4-5) and provider/model-id slugs both work. If you’re using a provider/ prefix and getting a miss, double-check the prefix is a provider (e.g. bedrock, azure, ai-studio) and not just the author (e.g. meta, google), and reconcile the version suffix against GET /v1/models.

Invalid API key error

Concentrate keys start with sk-cn-v1-. If you are still sending a Vercel vck_... key (or a VERCEL_OIDC_TOKEN) as the Authorization bearer, you will see a 401. Verify the value in your dashboard and confirm there are no extra spaces or quotes.

Requests succeed but nothing shows up in the Concentrate dashboard

Confirm the base URL is https://api.concentrate.ai/v1, not ai-gateway.vercel.sh. If the SDK is still pointed at Vercel it is logging against your AI Gateway dashboard, not Concentrate.

My Anthropic requests 404 after migrating

Vercel’s Anthropic surface uses https://ai-gateway.vercel.sh with no /v1; Concentrate uses https://api.concentrate.ai/v1 for every surface. If you copied the Vercel Anthropic base URL verbatim, you dropped the /v1 segment. Set the base URL to https://api.concentrate.ai/v1.

My provider routing stopped applying

providerOptions.gateway (order, only, sort, models, providerTimeouts) has no effect on Concentrate. Express fallbacks via routing.model.fallbacks / routing.provider.fallbacks body params, or use model: "auto" with a routing strategy.

Cache hit rate dropped after migrating

Concentrate uses provider-native prompt caching, currently supported on Anthropic and AWS Bedrock. There is no gateway-stored cache, so Vercel’s caching: 'auto' auto-breakpoints become provider-native caching. Caches are seeded per API key by default; pass prompt_cache_key in the request body if you want to set the seed explicitly.

Connection errors

Confirm the base URL is https://api.concentrate.ai/v1 (no per-surface variant like the /v1-less Anthropic base). Test the connection manually:

curl https://api.concentrate.ai/v1/responses/health

Next Steps

API Reference

Explore the full API capabilities

Available Models

Browse all supported models

Auto Routing

Optimize model selection automatically

Get Support

Contact our support team

Feedback

If you hit anything that didn’t translate cleanly (especially around providerOptions.gateway, BYOK, service tiers, app attribution, or the Anthropic base-URL difference), email support@concentrate.ai. The capability gaps called out above are tracked, and migration friction reports directly shape what we ship next.

​Prerequisites

​Quick Start for Claude Code users

​Step 1: Update Your Environment Variables

​Step 2: Update Your Client

​Step 3: Remove Vercel-Specific Headers

​Step 4: Decompose Your providerOptions.gateway

​Step 5: Update Model Identifiers

​Step 6: Reconnect Observability

​Exporting your AI Gateway history

​Step 7 (Optional): Adopt the Responses API

​Why migrate to Concentrate

​Troubleshooting

​Next Steps

API Reference

Available Models

Auto Routing

Get Support

​Feedback

Prerequisites

Quick Start for Claude Code users

Step 1: Update Your Environment Variables

Step 2: Update Your Client

Step 3: Remove Vercel-Specific Headers

Step 4: Decompose Your `providerOptions.gateway`

Step 5: Update Model Identifiers

Step 6: Reconnect Observability

Exporting your AI Gateway history

Step 7 (Optional): Adopt the Responses API

Why migrate to Concentrate

Troubleshooting

Next Steps

Feedback